my_arXiv_daily

KO | EN

gitlite — search

#javascript #llm #go #golang #android #machine-learning #deep-learning #docker #java #cli #kubernetes #awesome-list #ios #openai

(★ 212)

No description available.

파일 탐색기

최종 버전 다운로드 (.zip)

- - bug_report.md
  - config.yml
  - feature_request.md
  - question.md
- - cv-arxiv-daily.yml
  - update_paper_links.yml
- PULL_REQUEST_TEMPLATE.md
- 4-ga-2-1.png
- 4-ga-3-1.png
- 4-ga-5-1.png
- 4-ga-7.png
- 4-ga-8.png
- 4-ga-9.png
- 5-pages-1.png
- _config.yml
- cv-arxiv-daily-web.json
- cv-arxiv-daily-wechat.json
- cv-arxiv-daily.json
- index.md
- README.md
- wechat.md
.gitignore
CODE_OF_CONDUCT.md
config.yaml
daily_arxiv.py
git.sh
LICENSE
README.md
requirements.txt
skill.md

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/BaiShuanghao/my_arXiv_daily

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd my_arXiv_daily

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. Python

쉬움 추천

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Python 3 설치 시 'Add Python to PATH' 옵션을 꼭 체크하세요 (Windows).

pip install -r requirements.txt

requirements.txt 등에 명시된 파이썬 라이브러리를 설치합니다.

python <실행할 파일명>.py # README에서 정확한 실행 파일명을 확인하세요

파이썬 스크립트(또는 모듈)를 실행합니다.

✅ 에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

## Updated on 2026.08.23
> Usage instructions: [here](./docs/README.md#usage)

<details>
 <summary>Table of Contents</summary>
 <ol>
 <li><a href=#robot-&-agent>Robot & Agent</a></li>
 <li><a href=#robotic-manipulation>Robotic Manipulation</a></li>
 <li><a href=#vision-language-action-model>Vision Language Action Model</a></li>
 <li><a href=#imitation-learning>Imitation Learning</a></li>
 </ol>
</details>

## Robot & Agent

|Publish Date|Title|Authors|PDF|Code|
|---|---|---|---|---|
|**2026-08-20**|**RMWorld: Task-Aware Radio World Models with Value-of-Information Guided Multi-Trial Learning for Multi-UAV Communication Control**|Xiucheng Wang et.al.|[2608.20126](https://arxiv.org/abs/2608.20126)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-20**|**Planning-Oriented End-to-End Autonomous Driving: Architectures, Evaluation, and Emerging Paradigms**|Yanchen Guan et.al.|[2608.20111](https://arxiv.org/abs/2608.20111)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-20**|**Orthogonal JEPA: Factorized Predictive States for Latent World Models**|Taoyong Cui et.al.|[2608.20065](https://arxiv.org/abs/2608.20065)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-08-20**|**ADAPT: Physics-Aware Diffusion-based World Models for Adaptive Predictive Transferable HVAC Control**|Xu Yang et.al.|[2608.19804](https://arxiv.org/abs/2608.19804)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-20**|**An Irreducible Quantum Advantage in Aligning World Models with Reality**|Josep Lumbreras et.al.|[2608.19779](https://arxiv.org/abs/2608.19779)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-20**|**Keeping the Franka Emika Panda alive: a ROS 2 stack with a reliable position interface**|Antonio Langella et.al.|[2608.19740](https://arxiv.org/abs/2608.19740)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-20**|**SafeBranch: Branch-Pair Safety Alignment for Embodied Agents**|Hyunse Lee et.al.|[2608.19729](https://arxiv.org/abs/2608.19729)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-20**|**RFWM: Physics-Guided World Model for Dynamic Wireless Radiance Field Generation**|Zijiu Yang et.al.|[2608.19709](https://arxiv.org/abs/2608.19709)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-20**|**World-Model-Grounded LLM Planning for AUV and ASV Navigation Near Offshore Wind Farms**|Markus Buchholz et.al.|[2608.19661](https://arxiv.org/abs/2608.19661)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-20**|**Magnetically Self-Sealed MR Haptic Actuator With PWM-Based Excitation and High-Fidelity Torque Control**|Dong Qiang et.al.|[2608.19635](https://arxiv.org/abs/2608.19635)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-19**|**Beyond Multimodal Alignment: Certifying Physical Language through Response Substitution and Ordered Execution**|Kaizhen Tan et.al.|[2608.19492](https://arxiv.org/abs/2608.19492)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-20**|**DA-WAM: Decision-Aligned Future Latents for Driving World Models**|Ruiguo Zhong et.al.|[2608.19085](https://arxiv.org/abs/2608.19085)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-08-19**|**RoboEdit: Turning Human Manipulation Videos into Scalable Robot Experience**|Yaowei Guo et.al.|[2608.18948](https://arxiv.org/abs/2608.18948)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-19**|**Decision-Metric Alignment in Latent World Models: Diagnostics and Action-Conditioned Objectives for MPC Planning**|Jiawei Wang et.al.|[2608.18746](https://arxiv.org/abs/2608.18746)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-08-19**|**Vision-Language Models for Egocentric Video: From Hand-Object Interaction to Embodied AI**|Mohammad Zamani et.al.|[2608.18671](https://arxiv.org/abs/2608.18671)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-19**|**Reinforced Planning with Latent World Models**|Armin Sommer et.al.|[2608.18669](https://arxiv.org/abs/2608.18669)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-08-19**|**Progressive Experience Fusion for Multi-Task World Model Control in Endovascular Navigation**|Harry Robertshaw et.al.|[2608.18647](https://arxiv.org/abs/2608.18647)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-08-19**|**Partition the Support, Reconstruct the Residual: Training-Free Sparse Attention for Video Generation and World Models**|Pardis Taghavi et.al.|[2608.18484](https://arxiv.org/abs/2608.18484)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-08-19**|**The Embodiment Gap in Robot Foundation Models**|Yukiyasu Domae et.al.|[2608.18433](https://arxiv.org/abs/2608.18433)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-18**|**A Task-Agnostic Control Strategy for Dynamic Assistance with Pneumatically Actuated Soft Exosuits**|Anoush Sepehri et.al.|[2608.18364](https://arxiv.org/abs/2608.18364)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-18**|**GigaBrain-WBC-0.5: A Behavior World Model for Robust Whole-Body Control with Environment Interaction**|Ziyang Cheng et.al.|[2608.18234](https://arxiv.org/abs/2608.18234)|null|
|**2026-08-18**|**Revisiting the "Push-T" Robot Manipulation Task with Agentic Robotics**|Shuangyu Xie et.al.|[2608.18227](https://arxiv.org/abs/2608.18227)|null|
|**2026-08-18**|**Hydra-0: Action Flow for Generalist World Modeling and Control**|Hongyu Li et.al.|[2608.18077](https://arxiv.org/abs/2608.18077)|null|
|**2026-08-18**|**Towards Zero-Shot Task Transfer with Neurosymbolic World Models**|Isidoro Tamassia et.al.|[2608.17959](https://arxiv.org/abs/2608.17959)|null|
|**2026-08-18**|**An Omitted Mode Is a Rare Rule: The Sampling-Verification Danger Law in Continuous Code World Models**|Javier Aguilar Martín et.al.|[2608.17956](https://arxiv.org/abs/2608.17956)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-18**|**Edge-Native Embodied Intelligence for Action-Aware Wireless Edge Networks**|Yiru Wang et.al.|[2608.17774](https://arxiv.org/abs/2608.17774)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-18**|**Electromagnetic World Model for 6G: A Unified Framework for Joint Environment Reconstruction and Channel Prediction**|Yizhu Zhao et.al.|[2608.17769](https://arxiv.org/abs/2608.17769)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-18**|**Offline Multi-Agent Reinforcement Learning with a Physics-Informed World Model for Cooperative Mixed Traffic Control**|Lu Liu et.al.|[2608.17739](https://arxiv.org/abs/2608.17739)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-18**|**HODAgent: Towards On-Demand, Responsive Humanoids for Physical World Human Interaction**|Wang Warren Chen et.al.|[2608.17584](https://arxiv.org/abs/2608.17584)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-18**|**No Gaussian Required: Contrastive Inverse Dynamics for JEPA World Models**|Jack Boylan et.al.|[2608.17542](https://arxiv.org/abs/2608.17542)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-18**|**GroupForward: Building Referable 3D Scenes via Instance-Grouped Feed-Forward Gaussian Splatting**|Qijian Tian et.al.|[2608.17535](https://arxiv.org/abs/2608.17535)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-18**|**Calibrated Predictive Safety for Heterogeneous Robots: An Action-Conditioned JEPA Framework with Model-Based Safety Shields**|Kaiming Zhong et.al.|[2608.17496](https://arxiv.org/abs/2608.17496)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-18**|**If, Then, Otherwise: Diagnosing Conditional Branching in Vision-Language Navigation**|Seoyoung Lee et.al.|[2608.17318](https://arxiv.org/abs/2608.17318)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-08-17**|**Q-Learning With World Models**|Perry Dong et.al.|[2608.17163](https://arxiv.org/abs/2608.17163)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-17**|**Inference-Time Attention Steering for Vision-Language-Action Driving Models**|Darshan Nagendra Prasad et.al.|[2608.17095](https://arxiv.org/abs/2608.17095)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-17**|**$τ_0$ -VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation**|Xiaowei Cai et.al.|[2608.16885](https://arxiv.org/abs/2608.16885)|**[link](https://huggingface.co/models/sii-research/tau-0-vla)**|
|**2026-08-17**|**HarnessEval-W: Agentifying the Evaluation of Visual Worlds**|Weiliang Chen et.al.|[2608.16859](https://arxiv.org/abs/2608.16859)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-17**|**Security of Foundation-Model-Powered Embodied Agents: Attack Surfaces, Attacks, Defenses, and Evaluation**|Jiawei Liu et.al.|[2608.16843](https://arxiv.org/abs/2608.16843)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-17**|**CaliBench: Are the Stochastic Dynamics of Video World Models Physically Calibrated?**|Jonathan Sadeghi et.al.|[2608.16829](https://arxiv.org/abs/2608.16829)|null|
|**2026-08-17**|**When State Becomes an Attack Surface: State-Semantic Injection in LLM-Driven Embodied Agents**|Jiawei Liu et.al.|[2608.16806](https://arxiv.org/abs/2608.16806)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-17**|**Neurosymbolic Embodied Agents**|Mohammad Albinhassan et.al.|[2608.16794](https://arxiv.org/abs/2608.16794)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-17**|**Design Optimization for Large High-Force Soft Robot Manipulators Under Gravitational Loads**|Isara Cholaseuk et.al.|[2608.16728](https://arxiv.org/abs/2608.16728)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-17**|**Chronocooked: A Benchmark for Implicit Interval Timing in Reinforcement Learning Agents**|Amrapali Pednekar et.al.|[2608.16666](https://arxiv.org/abs/2608.16666)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-08-17**|**Orbit-Planner: Towards Latent World Models for On-Orbit Obstacle Avoidance of Satellite Agents**|Zhijian Li et.al.|[2608.16651](https://arxiv.org/abs/2608.16651)|**[link](https://huggingface.co/datasets/warriorLZJ/Orbit_Planner)**|
|**2026-08-17**|**Zetta $ζ$ : An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence**|Xin Ding et.al.|[2608.16590](https://arxiv.org/abs/2608.16590)|**[link](https://github.com/BraveBoBo/awesome-robot-memory)**|
|**2026-08-17**|**NebulaVLA: A Dual-Frequency Vision-Language-Action Model With Guide Action for Robotic Manipulation**|Cong Zhao et.al.|[2608.16503](https://arxiv.org/abs/2608.16503)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-17**|**DriveCache: Action-Aware Caching for Driving World Model Inference**|Jianchun Yang et.al.|[2608.16354](https://arxiv.org/abs/2608.16354)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-17**|**Principled Authority Switching for Shared Autonomy in Human-Robot Teams**|Sandeep Banik et.al.|[2608.16293](https://arxiv.org/abs/2608.16293)|null|
|**2026-08-17**|**SCALE: State-Calibrated Latent Embeddings for JEPA Planning in the Right Geometry**|Jiaming Hu et.al.|[2608.16287](https://arxiv.org/abs/2608.16287)|null|
|**2026-08-17**|**GaussianDWM++: Language-Grounded 3D Gaussian Driving World Model for Unified Scene Understanding, Editing, and Multi-Modal Generation**|Tianchen Deng et.al.|[2608.16234](https://arxiv.org/abs/2608.16234)|**[link](https://github.com/cakerdsp/geometry-vision-daily)**|
|**2026-08-17**|**Pluralistic Human-Robot Interaction: Designing for Robot Interaction with Diverse Communities**|Raj Korpan et.al.|[2608.16049](https://arxiv.org/abs/2608.16049)|**[link](https://github.com/Ed1sonChen/DailyArxiv)**|
|**2026-08-16**|**GigaBrain-0.7: Scaling Embodied Foundation Models to Emergent Capabilities with a Three-System Architecture**| GigaBrain Team et.al.|[2608.15875](https://arxiv.org/abs/2608.15875)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-16**|**Beyond Visual CoT: Internalized Visual Thinking for Proactive Video Reasoning**|Xiaoyu Zhu et.al.|[2608.15869](https://arxiv.org/abs/2608.15869)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-15**|**FloodReasonBench: Benchmarking VLM Reasoning Segmentation for Embodied Flood Response at the Edge**|Rajat Bhattacharjya et.al.|[2608.15410](https://arxiv.org/abs/2608.15410)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-15**|**Physiological World Models for Human State Transitions**|Chongyang Zhang et.al.|[2608.15309](https://arxiv.org/abs/2608.15309)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-14**|**Marionette: Predicting World States, Rendering Geometry, Painting Appearance**|Zian Meng et.al.|[2608.14530](https://arxiv.org/abs/2608.14530)|**[link](https://huggingface.co/spaces/hugging-apps/marionette-world-model)**|
|**2026-08-14**|**Rollplex: Cross-Phase GPU Spatial Sharing for Vision Language Model Post-Training**|Hanfeng Lu et.al.|[2608.14498](https://arxiv.org/abs/2608.14498)|**[link](https://github.com/zhixin612/awesome-papers-LMsys)**|
|**2026-08-14**|**Twin: Playing an Unknown Game with a Test-Time Digital Twin**|Alexy Skoutnev et.al.|[2608.14490](https://arxiv.org/abs/2608.14490)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-08-14**|**Ensuring Safe Physical AI in Urban Mobility via Hazard-Informed Synthesized Envelopes**|Alexei Odinokov et.al.|[2608.14481](https://arxiv.org/abs/2608.14481)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-14**|**Effect of Twisted-Yarn Architecture on Pressure and Proximity Sensing Characteristics of Textile Capacitive Sensors for Robotic Skin**|Ishtia Zahir et.al.|[2608.14406](https://arxiv.org/abs/2608.14406)|**[link](https://github.com/Ed1sonChen/DailyArxiv)**|
|**2026-08-14**|**Traj-LeWM: Path-Aware World-Model Planning via Latent Trajectory Cost**|Xiaodi Huang et.al.|[2608.14125](https://arxiv.org/abs/2608.14125)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-08-14**|**AdvDex: Learning Dexterous Manipulation from Human Demonstrations via Joint-Aligned Actions and Adversarial Learning**|Zhiyue Zhao et.al.|[2608.14028](https://arxiv.org/abs/2608.14028)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-08-14**|**ForgeWM: Progressive Causal Training for Few-Step Action-Conditioned Video World Models**|Xinye Li et.al.|[2608.14022](https://arxiv.org/abs/2608.14022)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-08-14**|**Implementing Computational Law in Wolfram Language for the Governance of Artificial Intelligence**|James K. Wiles et.al.|[2608.13958](https://arxiv.org/abs/2608.13958)|**[link](https://github.com/arxivsub/arXivSub_daily_arxiv)**|
|**2026-08-14**|**Ontology-Grounded World Models for Failure Diagnosis and Closed-Loop Repair in Physical AI Systems**|Kailin Wang et.al.|[2608.13901](https://arxiv.org/abs/2608.13901)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-13**|**hint $^2$ : Hierarchical World Models for Inference-Time Temporal Logic Guidance**|Moritz Zoellner et.al.|[2608.13678](https://arxiv.org/abs/2608.13678)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-08-14**|**PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives**|Kaixin Ding et.al.|[2608.13552](https://arxiv.org/abs/2608.13552)|**[link](https://huggingface.co/spaces/jocelynd/PlayWorld-Leaderboard)**|
|**2026-08-13**|**Alaya-EVOKE: From Linear-Scaling Supervision to Endless World**|Yuanyang Yin et.al.|[2608.13546](https://arxiv.org/abs/2608.13546)|**[link](https://huggingface.co/models/AlayaLab/Evoke)**|
|**2026-08-13**|**Intervention-Aware Clinical World Model for Post-Op Outcome Forecasting in Cardiology**|Yunsung Chung et.al.|[2608.13518](https://arxiv.org/abs/2608.13518)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-13**|**AlayaWorld: Interactive Long-Horizon World Modeling - Full Technical Report (v1.1)**| AlayaWorld Team et.al.|[2608.13492](https://arxiv.org/abs/2608.13492)|**[link](https://huggingface.co/models/AlayaLab/AlayaWorld-v1.1-stage2b)**|
|**2026-08-13**|**DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation**| DreamX Team et.al.|[2608.13489](https://arxiv.org/abs/2608.13489)|null|
|**2026-08-13**|**A Unifying Perspective on Causal World Models: From Observations to Representations to Structure**|Avinash Kori et.al.|[2608.13456](https://arxiv.org/abs/2608.13456)|null|
|**2026-08-13**|**UniTexture: Cross-Task Universal Adversarial Textures for Vision-Language-Action Models**|Yukun Dai et.al.|[2608.13453](https://arxiv.org/abs/2608.13453)|null|
|**2026-08-13**|**ContactGuard: Pre-Contact Execution Monitoring with Action-Conditioned Latent World Models**|Gehan Zheng et.al.|[2608.13438](https://arxiv.org/abs/2608.13438)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-08-13**|**Enhancing Virtual Agents through SLMs and Edge-Computing: An Exploratory Evaluation of Think and Memory Processes**|Aimilios Hadjiliasi et.al.|[2608.13420](https://arxiv.org/abs/2608.13420)|null|
|**2026-08-13**|**S2-HWM: Sparse Event-Structured Hierarchical World Model for Long-Horizon Surgical Robot Manipulation**|Shuzhe Zhang et.al.|[2608.13103](https://arxiv.org/abs/2608.13103)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-13**|**Semantic Radiance Fields as Simulators for Spatial Reasoning in Real-World Scenes**|Nico Heider et.al.|[2608.13095](https://arxiv.org/abs/2608.13095)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-13**|**H2R-Bench: Benchmarking Human-to-Robot Manipulation Video Generation in World Models**|Dingyi Rong et.al.|[2608.13049](https://arxiv.org/abs/2608.13049)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-13**|**RGB-D Video Generation for Improving Human-to-Robot Object Handover Prediction**|Tianyu Sun et.al.|[2608.13028](https://arxiv.org/abs/2608.13028)|null|
|**2026-08-13**|**The Objective Is the Bottleneck: Latent World Models Encode What Their Planners Cannot Use**|Joyjeet Singh et.al.|[2608.12959](https://arxiv.org/abs/2608.12959)|**[link](https://huggingface.co/models/Joyjeetsingh/tinylab-tworoom-lewm)**|
|**2026-08-13**|**Diagnosing JEPA World Models with Action-Conditioned Predictive Consistency**|Guo An et.al.|[2608.12939](https://arxiv.org/abs/2608.12939)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-13**|**HounsWorld: A Multimodal World Model for Hidden Patient-State Readout, Reconstruction, and Simulation**|Yunhao Bai et.al.|[2608.12904](https://arxiv.org/abs/2608.12904)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-13**|**BrainWAM: Action-Space Coordination of Semantic Priors and Predictive Dynamics for Autonomous Driving**|Bing Zhan et.al.|[2608.12854](https://arxiv.org/abs/2608.12854)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-13**|**Spatial Memory Agent: Experience-Grounded Procedure Memory for Spatial Intelligence**|Haokai Zhang et.al.|[2608.12743](https://arxiv.org/abs/2608.12743)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-13**|**FUSE: Active Functional Affordance Grounding through Adaptive Semantic-Geometric Evidence Acquisition**|Zhou Chen et.al.|[2608.12683](https://arxiv.org/abs/2608.12683)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-12**|**Scaling Automatic Research Agents via World Models**|Xiyuan Yang et.al.|[2608.12564](https://arxiv.org/abs/2608.12564)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-12**|**DreamFly: Causal Memory and Receding-Horizon Diffusion Planning for Aerial Vision-Language Navigation**|Yan Deng et.al.|[2608.12308](https://arxiv.org/abs/2608.12308)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-08-12**|**Map-Det3D: Metric Feed-Forward 3D Reconstruction Prior for Multi-view 3D Object Detection from Streaming Inputs**|Yung-Hsu Yang et.al.|[2608.12179](https://arxiv.org/abs/2608.12179)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-08-12**|**Better Slots, Better Worlds: Representation Quality & Robustness in Object-Centric World Models**|Shukrullo Nazirjonov et.al.|[2608.12078](https://arxiv.org/abs/2608.12078)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-12**|**G0.5: One Autoregressive Stream for Robot Reasoning and Action**|Yicheng Liu et.al.|[2608.11739](https://arxiv.org/abs/2608.11739)|**[link](https://github.com/OpenGalaxea/GalaxeaVLA)**|
|**2026-08-12**|**StellaVLA: In-Context Structured Demonstration for Generalizable Vision-Language-Action Models**|Siyu Xu et.al.|[2608.11671](https://arxiv.org/abs/2608.11671)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-12**|**How Can Driving World Models Do Counterfactual Prediction?**|Jiaru Zhang et.al.|[2608.11601](https://arxiv.org/abs/2608.11601)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-11**|**Locomotion Variability and User Experience in Smart Wheelchair Human-Robot Interaction**|Sean Kille et.al.|[2608.11417](https://arxiv.org/abs/2608.11417)|**[link](https://github.com/Ed1sonChen/DailyArxiv)**|
|**2026-08-11**|**Self-Evolving Embodied Agents via Skill-Harness Evolution**|Peidong Wang et.al.|[2608.11350](https://arxiv.org/abs/2608.11350)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-08-11**|**Surgical WAM: A World-Action Model for Data-Efficient Surgical Robot Learning**|Wenrui Bao et.al.|[2608.11204](https://arxiv.org/abs/2608.11204)|null|
|**2026-08-12**|**VIScore: Diagnosing Planning-Relevant Quality in Latent World Models**|Haiyu Wu et.al.|[2608.11174](https://arxiv.org/abs/2608.11174)|**[link](https://huggingface.co/models/BooBooWu/viscore)**|
|**2026-08-11**|**HUI360: A 360° Egocentric Dataset and Baselines for Human-Robot Interaction Anticipation**|Raphael Lorenzo-Louis et.al.|[2608.11051](https://arxiv.org/abs/2608.11051)|**[link](https://huggingface.co/datasets/rlorlou/HUI360)**|
|**2026-08-11**|**MAJEPPA: Morphing and Assessing in a Unified Piano Performance Space**|Jinwen Zhou et.al.|[2608.11026](https://arxiv.org/abs/2608.11026)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-11**|**R4DSG: Relative 4D Scene Graph Memory for Object-Centric Question Answering in Long Egocentric Video**|Ke Ma et.al.|[2608.11017](https://arxiv.org/abs/2608.11017)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-12**|**ComBodied Agents: a New Paradigm of Human-Centric Agentic AI**|Qianggang Ding et.al.|[2608.10915](https://arxiv.org/abs/2608.10915)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-11**|**Toward the Cognitive--Physical Limits of Embodied Intelligence through a World-Model-Centric Autonomous Racing Agent**|Zitong Shan et.al.|[2608.10618](https://arxiv.org/abs/2608.10618)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-12**|**PBD-AG: Persistent Baseline-Delta Active Graphs with Uncertainty-Aware Inspection for Long-Horizon Service Robots**|Shuo Bao et.al.|[2608.10449](https://arxiv.org/abs/2608.10449)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-11**|**Stream Forcing: Constructing Unified Training Trajectory for Robust Streaming Video Generation**|Yueting Zhu et.al.|[2608.10439](https://arxiv.org/abs/2608.10439)|**[link](https://github.com/zezhishao/DailyArXiv)**|
|**2026-08-11**|**Dreamer-SAC: Off-Policy Learning in Latent World Models for Sample-Efficient Autonomous Driving**|Jiazhuo Li et.al.|[2608.10386](https://arxiv.org/abs/2608.10386)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-10**|**FACT: Failure-Aware Causal Training for World-Action Models**|Quanquan Peng et.al.|[2608.10232](https://arxiv.org/abs/2608.10232)|**[link](https://huggingface.co/spaces/Bariona/fact-world-action-model)**|
|**2026-08-10**|**A JEPA-Based Field-Layer World Model for Bridging Channel Prediction and Estimation**|Yuzhi Yang et.al.|[2608.10222](https://arxiv.org/abs/2608.10222)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-10**|**The Evaluation Protocol Determines the Result: An Independent Reproduction of LeWorldModel on TwoRoom**|Joyjeet Singh et.al.|[2608.10145](https://arxiv.org/abs/2608.10145)|**[link](https://huggingface.co/models/Joyjeetsingh/tinylab-tworoom-lewm)**|
|**2026-08-10**|**4D-WAM: 4D Consistent World Modeling for Autonomous Driving**|Jiacheng Fu et.al.|[2608.10107](https://arxiv.org/abs/2608.10107)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-08-10**|**Learning How the World Evolves: Extrapolative Video World Models via Latent Dynamics Reasoning**|Haodong Li et.al.|[2608.09926](https://arxiv.org/abs/2608.09926)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-10**|**Energy-Structured Latent World Models with Neural Time Fields for Physically Constistent Open-World Motion Planning**|Yapeng Liu et.al.|[2608.09876](https://arxiv.org/abs/2608.09876)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-10**|**CEAA: A Cognitive Embodied Agents Architecture for Interactive Computing Systems**|Aimilios Hadjiliasi et.al.|[2608.09848](https://arxiv.org/abs/2608.09848)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-10**|**SLIM-0.5B: Learning Action-Grounded Predictive Latents for Robot Manipulation**|Jingkai Wang et.al.|[2608.09771](https://arxiv.org/abs/2608.09771)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-10**|**World Tokens: Enhancing Embodied Policies with Training-Time World Modeling**|Qu Tang et.al.|[2608.09730](https://arxiv.org/abs/2608.09730)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-11**|**Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models**|Kevin Murphy et.al.|[2608.09696](https://arxiv.org/abs/2608.09696)|**[link](https://github.com/xianshang33/llm-paper-daily)**|
|**2026-08-10**|**Removing Infrastructure Barriers in Human-Robot Collaboration Through Wireless Reconfigurable Cells**|Emma Takács et.al.|[2608.09658](https://arxiv.org/abs/2608.09658)|**[link](https://github.com/Jianqiuer/Awesome6DPoseEstimation)**|
|**2026-08-10**|**verdi: retrieval is not transfer for continual world model optimization**|Junyu Wu et.al.|[2608.09537](https://arxiv.org/abs/2608.09537)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-10**|**Sekai2: From World Exploration to Interactive World Modeling**|Kang He et.al.|[2608.09449](https://arxiv.org/abs/2608.09449)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-10**|**JEPA-WAM: Learning Vision-Language-Action Policies with Joint-Embedding World Modeling**|Yihan Lin et.al.|[2608.09381](https://arxiv.org/abs/2608.09381)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-10**|**WorldSimProbe: Diagnosing Simulator Faithfulness in Action-Conditioned World Models for Embodied Manipulation**|Peterson Co et.al.|[2608.09298](https://arxiv.org/abs/2608.09298)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-10**|**Did the Grid Erase the Event? EndoClock for Auditing Medical World-Model Pipelines**|Yarin Udi et.al.|[2608.09266](https://arxiv.org/abs/2608.09266)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-10**|**SAIN: Structure-Aware Interactive Navigation with Active Dialogue Grounding for Mobile Robot**|Yuhao Cao et.al.|[2608.09196](https://arxiv.org/abs/2608.09196)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-10**|**High Fidelity Capture, Reconstruction, and Transfer of Human Demonstrations for Robot-Assisted Bathing**|Arjun S. Lakshmipathy et.al.|[2608.09127](https://arxiv.org/abs/2608.09127)|null|
|**2026-08-10**|**Latent World Models with Monotone Planning Costs for Image-Goal Navigation**|Amirhosein Chahe et.al.|[2608.09073](https://arxiv.org/abs/2608.09073)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-10**|**Personalized Lower-limb Exoskeleton Assistance via Preference-based Bayesian Optimization**|Xiao-Yin Liu et.al.|[2608.09015](https://arxiv.org/abs/2608.09015)|null|
|**2026-08-10**|**Twin Rollouts: Noise-Coupled Counterfactual Branching in Interactive Video World Models**|Yu Ma et.al.|[2608.08982](https://arxiv.org/abs/2608.08982)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-09**|**360CityArena: A Realistic Virtual Urban Navigation Benchmark for Embodied Agents**|Kenta Watanabe et.al.|[2608.08814](https://arxiv.org/abs/2608.08814)|**[link](https://github.com/OpenEnvision/Awesome-Multimodal-Agent)**|
|**2026-08-09**|**Sensing-Induced Embodied Communication in the Near Field**|Jingreng Lei et.al.|[2608.08731](https://arxiv.org/abs/2608.08731)|**[link](https://github.com/arxivsub/arXivSub_daily_arxiv)**|
|**2026-08-09**|**WA-SpecDec: World-Aware Speculative Decoding for Vision-Language-Action Models**|Zikang Wen et.al.|[2608.08725](https://arxiv.org/abs/2608.08725)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-07**|**Beyond Myopic World Models: Long-Horizon End-to-End Training for Direct Future Prediction**|Xinyi Li et.al.|[2608.07420](https://arxiv.org/abs/2608.07420)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-08-07**|**UniJEPA: A Unified Joint-Embedding Predictive Architecture for Task-Agnostic Visual World Modeling**|An Lanji et.al.|[2608.07409](https://arxiv.org/abs/2608.07409)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-08-07**|**Addressable Memory for Video World Models**|Xindi Wu et.al.|[2608.07408](https://arxiv.org/abs/2608.07408)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-08-07**|**From Optimal Actions to World Models: Identifiability of Transition Kernels in Discounted MDPs**|Neal Batra et.al.|[2608.07301](https://arxiv.org/abs/2608.07301)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-07**|**Metric Non-Collapse in Learned World Models for Control: Approximation Theory, Finite-Sample Geometric Guarantees, and Deterministic Planning Transfer**|Alain Bensoussan et.al.|[2608.07265](https://arxiv.org/abs/2608.07265)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-07**|**MemWM: Memory-Augmented Text-Based World Model**|Yujun Wang et.al.|[2608.07107](https://arxiv.org/abs/2608.07107)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-08-07**|**Transformers Struggle to Use Their Emergent World Models: Revisiting the Tower of Hanoi, and the Illusion of Thinking**|Devin Pereira et.al.|[2608.07077](https://arxiv.org/abs/2608.07077)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-08-07**|**Is Forward Prediction Enough? Physical State Grounding for JEPA World Models**|Haodong Yan et.al.|[2608.06799](https://arxiv.org/abs/2608.06799)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-08-07**|**Surg-UniWorld: A Unified Surgical World Model with Multimodal Control Experts**|Rulin Zhou et.al.|[2608.06770](https://arxiv.org/abs/2608.06770)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-08-07**|**Capek 0.5: An Execution-Centric Vision-Language Model for Embodied Intelligence**|Ying Chen et.al.|[2608.06756](https://arxiv.org/abs/2608.06756)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-07**|**Dueling World Models: Advantage-Style Action Channels for Common-Mode Distractor Rejection**|Jiazhuo Li et.al.|[2608.06706](https://arxiv.org/abs/2608.06706)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-08-07**|**CrossTracer: Cross-Embodiment Navigation via VLA Model Reasoning and Trace Residuals Adapting**|Yao Wang et.al.|[2608.06688](https://arxiv.org/abs/2608.06688)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-06**|**TaskSense: Focusing on What Matters in World Models**|SM Mazharul Islam et.al.|[2608.06544](https://arxiv.org/abs/2608.06544)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-08-06**|**DyPES-VLA: Learning Shared Dynamics Priors and Embodiment-Specific Control for Cross-Embodiment Manipulation**|Junfeng Li et.al.|[2608.06374](https://arxiv.org/abs/2608.06374)|null|
|**2026-08-06**|**GeniWorld: A Generalizable Interactive World Model for Robotic Manipulation via Visual Actions**|Chenghao Gu et.al.|[2608.06332](https://arxiv.org/abs/2608.06332)|null|
|**2026-08-06**|**MASS: Multiplayer World Models with Authoritative Shared State**|Ziqi Cai et.al.|[2608.06257](https://arxiv.org/abs/2608.06257)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-08-06**|**From Passive Mirrors to Active Agents: Holonic Digital Twins for Physical AI over Networks**|Christo Kurisummoottil Thomas et.al.|[2608.06227](https://arxiv.org/abs/2608.06227)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-06**|**Robot Learning from Human Demonstrations: Handwritten Alphabet Trajectories and Human-Likeness Evaluation**|Alperen Kenan et.al.|[2608.06221](https://arxiv.org/abs/2608.06221)|**[link](https://github.com/zezhishao/DailyArXiv)**|
|**2026-08-06**|**EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning**|Zishan Xu et.al.|[2608.06197](https://arxiv.org/abs/2608.06197)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-08-06**|**From Economic Agents to Agentic Economies: A Systems Blueprint for Economic World Models**|Jiale Han et.al.|[2608.06020](https://arxiv.org/abs/2608.06020)|**[link](https://github.com/kyegomez/awesome-multi-agent-papers)**|
|**2026-08-06**|**Adaptive-WAM: Quality-Guided Early-Exit Planning from Intermediate Video-Diffusion Features**|Sining Ang et.al.|[2608.06008](https://arxiv.org/abs/2608.06008)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-08-06**|**Beyond Flat Policies: Hierarchical Post-Training for Embodied Agents in Robotic Manipulation**|He Kong et.al.|[2608.05999](https://arxiv.org/abs/2608.05999)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-06**|**GAUGE: A Measurement-Grounded Benchmark for Physical Fidelity in Simulation Engines and Video World Models**|Shuai Wang et.al.|[2608.05948](https://arxiv.org/abs/2608.05948)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-08-06**|**AppDeltaWorld: Transition-Grounded Delta Code World Model for Mobile GUI Agents**|Weikai Xu et.al.|[2608.05891](https://arxiv.org/abs/2608.05891)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-08-06**|**XEWorld: Can Action-Conditioned World Models Generalize to Unseen Robot Embodiments?**|Yixiang Chen et.al.|[2608.05799](https://arxiv.org/abs/2608.05799)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-08-06**|**When Agentic AI Meets Integrated Sensing and Communication**|Kai Li et.al.|[2608.05792](https://arxiv.org/abs/2608.05792)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-06**|**GST-Bench: Can VLMs Develop Global Spatial Awareness from Video?**|Qifeng Zhang et.al.|[2608.05747](https://arxiv.org/abs/2608.05747)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-08-06**|**PhyLatent: Learning Dynamics-Relevant Representations for JEPA World Models**|Xi Zeng et.al.|[2608.05720](https://arxiv.org/abs/2608.05720)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-08-06**|**LAWM-3D: Learning 3D-Aware Latent Actions from Human Videos for Generalizable Robot World Models**|Jiarui Yang et.al.|[2608.05706](https://arxiv.org/abs/2608.05706)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-08-06**|**DreamGuard: Efficient Runtime Guardrail for LLM Agents via Risk-Aware World Model**|Wenhao Lin et.al.|[2608.05695](https://arxiv.org/abs/2608.05695)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-08-06**|**JoyAI-RA 0.5: Scaling Robot Manipulation Learning via Dual Action Alignment**|JoyAI-RA Team et.al.|[2608.05674](https://arxiv.org/abs/2608.05674)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-06**|**SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries**|Xingyu Tan et.al.|[2608.05604](https://arxiv.org/abs/2608.05604)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-06**|**Uncertainty-Aware World Model for Aerial Image-Goal Navigation**|Deyi Zhu et.al.|[2608.05597](https://arxiv.org/abs/2608.05597)|**[link](https://huggingface.co/spaces/hugging-apps/ua-nwm-aerial-navigation)**|
|**2026-08-05**|**HelloWorld: Enabling Socially Interactive Characters in Video World Models**|Liangyang Ouyang et.al.|[2608.05070](https://arxiv.org/abs/2608.05070)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-08-05**|**DreamWAM: Beyond RGB Future Prediction for World Action Models**|Shanglin Yuan et.al.|[2608.04996](https://arxiv.org/abs/2608.04996)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-08-05**|**WorldCycle: Self-Verifiable Reinforcement Learning for Long-Horizon Video World Models**|Bohai Gu et.al.|[2608.04964](https://arxiv.org/abs/2608.04964)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-08-05**|**Mimir: A Neuro-Symbolic Memory System with Dynamic Grounding for Embodied Agents in Interactive Environments**|Haoming Xu et.al.|[2608.04933](https://arxiv.org/abs/2608.04933)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-08-05**|**RORA: Realistic Object Reconstruction with Articulation**|Hyesung Lee et.al.|[2608.04842](https://arxiv.org/abs/2608.04842)|**[link](https://github.com/longxiang-ai/awesome-gaussians)**|
|**2026-08-05**|**MobileWAM: Bridging World Action Models to Mobile Manipulation with Chain-of-Foresight**|Zehua Fan et.al.|[2608.04657](https://arxiv.org/abs/2608.04657)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-08-05**|**Overcoming Statistical Bias in Action-Controllable World Models**|Yuhong Shi et.al.|[2608.04653](https://arxiv.org/abs/2608.04653)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-08-05**|**muSync-GS: Physics-Synchronized Driving Video Synthesis for Weather and Geometric Road Hazards**|Yang Chen et.al.|[2608.04412](https://arxiv.org/abs/2608.04412)|**[link](https://github.com/longxiang-ai/awesome-gaussians)**|
|**2026-08-05**|**Helping Music Co-Creation Agents 'Listen' Well: Hierarchical Self-Supervised World Models for Understanding and Generation**|Scott H. Hawley et.al.|[2608.04378](https://arxiv.org/abs/2608.04378)|**[link](https://github.com/iszhanjiawei/flow_matching_arxiv_daily)**|
|**2026-08-05**|**Structured LLM Reasoning for Zero-Shot Human--Robot Coordination Under Hidden Goals**|Dong Hae Mangalindan et.al.|[2608.04309](https://arxiv.org/abs/2608.04309)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-08-04**|**SiMDex: Mining Similar Egocentric Videos for Cross-Embodiment Dexterous Manipulation**|Nie Lin et.al.|[2608.04196](https://arxiv.org/abs/2608.04196)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-04**|**Deep Learning for Real-Time Sound Order Recognition in Human-Robot Interaction**|Rezaul Tutul et.al.|[2608.04072](https://arxiv.org/abs/2608.04072)|**[link](https://github.com/Ponkux/DailyArXiv-cp)**|
|**2026-08-04**|**Human Centric Embodied Intelligence for Soft Wearable Robotics**|Rainier Natividad et.al.|[2608.03556](https://arxiv.org/abs/2608.03556)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-04**|**Enactive Artificial Intelligence: A Decision-Centric Architecture for Complex Systems**|Zuojun Max Shen et.al.|[2608.03413](https://arxiv.org/abs/2608.03413)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-04**|**UniNav: A Unified World-Action Diffusion Model for Visual Navigation**|Changqing Zhou et.al.|[2608.03244](https://arxiv.org/abs/2608.03244)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-04**|**CrossScope: A Role-Asymmetric World Model for Joint Dual-Scope Surgical Video Prediction**|Wanhao Liu et.al.|[2608.03211](https://arxiv.org/abs/2608.03211)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-04**|**Accelerating Human-Aware Robot Trajectory Generation via Diffusion and Consistency Distillation**|Byeong-Il Ham et.al.|[2608.03159](https://arxiv.org/abs/2608.03159)|**[link](https://github.com/zezhishao/DailyArXiv)**|
|**2026-08-04**|**DigitCode: Symbolic Tokenization of Hand Motion by Anatomical Units**|Haoyu Gu et.al.|[2608.03127](https://arxiv.org/abs/2608.03127)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-04**|**What Language Does and What the Evidence Supports: A Functional Role Taxonomy and Evidence Audit of Language Grounding in Embodied Agents**|Yifan Guo et.al.|[2608.03099](https://arxiv.org/abs/2608.03099)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-04**|**EmbodiedVAE: Disentangled Video VAE for Efficient and Controllable Embodied Manipulation**|Jiayi Luo et.al.|[2608.02990](https://arxiv.org/abs/2608.02990)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-03**|**RealWeather: Realistic and Scene-Faithful Weather Translation with Driving World Models**|Yuwei Ning et.al.|[2608.02953](https://arxiv.org/abs/2608.02953)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-03**|**Quo Vadis, World Modeling?**|Yu Yang et.al.|[2608.02713](https://arxiv.org/abs/2608.02713)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-03**|**WorldExam: Benchmarking World Models from Apparent Appearance to Inherent Reactivity**|Yuxue Yang et.al.|[2608.02603](https://arxiv.org/abs/2608.02603)|**[link](https://github.com/EasonTuT/Awesome-Interactive-World-Model)**|
|**2026-08-03**|**CoWAM: Coordination Contracts for Selective Policy Intervention with WAMs**|Shuaijun Liu et.al.|[2608.02578](https://arxiv.org/abs/2608.02578)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-03**|**DF $^3$ : World Modeling via Decoder-Free Feature Forecasting in Autonomous Navigation**|Jiaming Chen et.al.|[2608.02428](https://arxiv.org/abs/2608.02428)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-03**|**Faster-WAM: Do World Action Models Need Deep Action Modules?**|Liheng Ma et.al.|[2608.02365](https://arxiv.org/abs/2608.02365)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-04**|**PhyCheck: Fine-Grained Evidence-Grounded Dataset for Physical Law Understanding in Video-LLMs**|Zhongjie Ba et.al.|[2608.02150](https://arxiv.org/abs/2608.02150)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-03**|**MANGO-Grasp: Mahalanobis Fields over Geometry-Oriented 3D Gaussians for Cross-Embodiment Dexterous Grasping**|Heng Zhang et.al.|[2608.02014](https://arxiv.org/abs/2608.02014)|**[link](https://github.com/longxiang-ai/awesome-gaussians)**|
|**2026-08-03**|**Adaptive Human-Robot Collaborative Painting Combining Preference-Based Optimization and Dynamic Motion Primitives**|C. Cella et.al.|[2608.01981](https://arxiv.org/abs/2608.01981)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-03**|**ProWorld: Progress-Aware Hyperbolic World Models for Long-Horizon Visual Goal Reaching**|Zihan Liu et.al.|[2608.01926](https://arxiv.org/abs/2608.01926)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-03**|**Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills**|Gaytri Jena et.al.|[2608.01851](https://arxiv.org/abs/2608.01851)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-03**|**WorldDynCache: Risk-Controlled Latent Dynamics Approximation for Diffusion World Model**|Leyang Chen et.al.|[2608.01845](https://arxiv.org/abs/2608.01845)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-03**|**NeuroWorld: A Latent Brain World Model for Stimulus-Conditioned Human Brain Dynamics**|Zijian Dong et.al.|[2608.01773](https://arxiv.org/abs/2608.01773)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-03**|**Ten Years of Deep Learning for Wireless Communications: From Learned Blocks to Deployable Wireless Intelligence**|Hao Ye et.al.|[2608.01747](https://arxiv.org/abs/2608.01747)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-03**|**TWINS: A Tactile Wearable Isomorphic Arm Networked System for Contact-Rich Manipulation Learning**|Takahide Kitamura et.al.|[2608.01733](https://arxiv.org/abs/2608.01733)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-03**|**FedWorld: Scope-Aware Federation of Agent World Models**|Yuchao Hou et.al.|[2608.01561](https://arxiv.org/abs/2608.01561)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-02**|**Rapid Embodiment Adaptation for Quadrupedal Locomotion**|Dichen Li et.al.|[2608.01506](https://arxiv.org/abs/2608.01506)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-08-02**|**When Replanning Becomes the Bottleneck: Budgeted Replanning for Embodied Agents**|Shuaijun Liu et.al.|[2608.01428](https://arxiv.org/abs/2608.01428)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-08-02**|**SG-WAM: Self-Guided World Modeling in Geometry-Aware Policy Space**|Ruiteng Zhao et.al.|[2608.01397](https://arxiv.org/abs/2608.01397)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-02**|**DreamTrajectory: Trajectory-Guided Action Generation with World Model Alignment for Mobile Manipulation**|Zheng Yang et.al.|[2608.01381](https://arxiv.org/abs/2608.01381)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-02**|**EndoWAM: A Grounded World-Action Model for Generalizable Endoscopic Navigation**|Jinsong Lin et.al.|[2608.01221](https://arxiv.org/abs/2608.01221)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-02**|**Climate-Dyna Deep Hedging for XVAs: Model-Based Reinforcement Learning, Residual Climate HVA, and Hedge-Instrument Discovery**|Xiaozhen Wang et.al.|[2608.01208](https://arxiv.org/abs/2608.01208)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-31**|**WCM: A World Critic Model for Vision-Language-Action Reinforcement Learning**|Senyu Fei et.al.|[2607.29613](https://arxiv.org/abs/2607.29613)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-07-31**|**DreamQAS: Learning a Decision-Useful World Model for VQE-Efficient Quantum Architecture Search**|Jiayang Niu et.al.|[2607.29491](https://arxiv.org/abs/2607.29491)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-31**|**Temporal Policy: History-Initialized Action Generation for Robotic Learning from Demonstration**|Dylan Miller et.al.|[2607.29482](https://arxiv.org/abs/2607.29482)|**[link](https://github.com/iszhanjiawei/flow_matching_arxiv_daily)**|
|**2026-07-31**|**AquaJEPA: Action-Conditioned Multimodal Predictive Representations for Underwater Robot Dynamics**|Alan-Barsag Gazzaev et.al.|[2607.29393](https://arxiv.org/abs/2607.29393)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-07-31**|**BWM: A Low-Cost High-Fidelity World Simulator for Robot Learning**|BWM Team et.al.|[2607.29302](https://arxiv.org/abs/2607.29302)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-07-31**|**Auto-JEPA: A Latent World Model of Continuous Intent for End-to-End Autonomous Driving**|Jiwei Yang et.al.|[2607.29031](https://arxiv.org/abs/2607.29031)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-07-30**|**Mirror Learning**|Yunpeng Liu et.al.|[2607.28737](https://arxiv.org/abs/2607.28737)|**[link](https://github.com/yingchengyang/Reinforcement-Learning-Papers)**|
|**2026-07-30**|**ACE-Data-0: Human-Centric Ambient Capture as Embodied Data Engine**|Yukang Cao et.al.|[2607.28625](https://arxiv.org/abs/2607.28625)|**[link](https://huggingface.co/datasets/ACERobotics/ACE-Data-0)**|
|**2026-07-30**|**PhiZero: A World Model Built Around Physical Language**|Shuyao Shang et.al.|[2607.28624](https://arxiv.org/abs/2607.28624)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-07-30**|**X-NavDP: Generalizing Navigation Diffusion Policy to Novel Behavior and Embodiments with Group Q-score Reweighted Matching**|Tianyu Yang et.al.|[2607.28560](https://arxiv.org/abs/2607.28560)|**[link](https://huggingface.co/models/InternRobotics/X-NavDP)**|
|**2026-07-30**|**AuricularWorld: Hierarchical Action-Guided World Modeling for Fine-Grained Auricular Structure Segmentation from CT Scans**|Jingwen Yang et.al.|[2607.28487](https://arxiv.org/abs/2607.28487)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-30**|**QQWorld: Quantile-Quantile Matching for World Model Regularization**|Zhoushun Yu et.al.|[2607.28415](https://arxiv.org/abs/2607.28415)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-07-30**|**Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfer**|Weiquan Lin et.al.|[2607.28394](https://arxiv.org/abs/2607.28394)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-30**|**SemAnCorr: Semantic Anchored Correspondence for Zero-Shot Manipulation Skill Transfer**|Xiaoxiang Dong et.al.|[2607.28382](https://arxiv.org/abs/2607.28382)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-30**|**ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow**|Jin Cao et.al.|[2607.28362](https://arxiv.org/abs/2607.28362)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-07-30**|**Tycho: Active Abstraction with Programmatic World Models for ARC-AGI-3**|Jens Lehmann et.al.|[2607.28287](https://arxiv.org/abs/2607.28287)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-07-30**|**Security of World-Model-Based Embodied AI: A Lifecycle of Threats, Defenses, and Evaluation**|Fazhong Liu et.al.|[2607.28226](https://arxiv.org/abs/2607.28226)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-07-30**|**ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow**|Dongxiu Liu et.al.|[2607.27924](https://arxiv.org/abs/2607.27924)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-30**|**Learning to Understand Body Language from Flight through Robust 3D Avatar Placing**|Dragos Costea et.al.|[2607.27865](https://arxiv.org/abs/2607.27865)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-30**|**DexDirect: Direct Kinesthetic Arm Guidance for Efficient Dexterous Demonstration Collection**|Beom Jun Kim et.al.|[2607.27784](https://arxiv.org/abs/2607.27784)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-30**|**SpatialCLI: Learning to Reason With Spatial Tools, Then Without Them**|Yang Zhou et.al.|[2607.27703](https://arxiv.org/abs/2607.27703)|**[link](https://huggingface.co/spaces/hugging-apps/spatialcli-8b-demo)**|
|**2026-07-30**|**Arm2Air: Cross-Embodiment Skeleton Transfer for 3D Relay Formation**|Dohun Lee et.al.|[2607.27627](https://arxiv.org/abs/2607.27627)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-30**|**World Action Planner: Generalizable Decision-Making with Action-Conditioned World Models**|Xiangcheng Zhang et.al.|[2607.27599](https://arxiv.org/abs/2607.27599)|**[link](https://huggingface.co/models/XiangchengZhang/world-action-planner)**|
|**2026-07-30**|**Cross-Embodiment Transfer via Behavior-Aligned Representations**|Ajay Sridhar et.al.|[2607.27549](https://arxiv.org/abs/2607.27549)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-29**|**Failure Detection for Surgical Robot Imitation Policies via Flow-Matching World Modeling**|Zhefeng Huang et.al.|[2607.27511](https://arxiv.org/abs/2607.27511)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-07-29**|**Corrigible Assistance in One Round: Pragmatic-Pedagogic Best Response**|Elle Lazarski et.al.|[2607.27508](https://arxiv.org/abs/2607.27508)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-29**|**Mental World Modeling**|Hao Fei et.al.|[2607.27201](https://arxiv.org/abs/2607.27201)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-07-29**|**Mitigating Compounding Error via Video Representation Regularization**|Taiye Chen et.al.|[2607.27036](https://arxiv.org/abs/2607.27036)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-29**|**What Can Latent World Models Know? Physical Parameter Identifiability in Multimodal Predictive Representations**|Kaizhen Tan et.al.|[2607.27017](https://arxiv.org/abs/2607.27017)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-29**|**SymmGrid: Super-Scaling On-Robot Learning with Parallelized Symmetries and Egocentric-Exocentric Visual Perception**|Gabe Everett et.al.|[2607.26985](https://arxiv.org/abs/2607.26985)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-07-29**|**Temporally Centered SIGReg Improves Multi-Task LeWorldModel Learning: From Analysis to Method**|Chang Liu et.al.|[2607.26924](https://arxiv.org/abs/2607.26924)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-29**|**From Passive Video to Editable Experience: Physically Grounded Experience Synthesis for Embodied Intelligence**|Jia Luo et.al.|[2607.26903](https://arxiv.org/abs/2607.26903)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-07-29**|**Practice Makes Policies: Bootstrapping and Consolidating Robotic Capabilities from Zero Human Demonstrations**|Jialiang Li et.al.|[2607.26809](https://arxiv.org/abs/2607.26809)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-07-29**|**CheckVLA: Execution-Time Verification with Action-Conditioned World Model for Long-Horizon Mobile Manipulation**|Yushan Liu et.al.|[2607.26789](https://arxiv.org/abs/2607.26789)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-29**|**StatePlay: State-Aware Game World Models for Mechanics-Consistent Generation**|Zijun Lin et.al.|[2607.26754](https://arxiv.org/abs/2607.26754)|**[link](https://huggingface.co/spaces/hugging-apps/stateplay-world-model)**|
|**2026-07-29**|**CalTwin: Towards Calibrated, Shift-Robust Medical World Models via Fisher-Information Regularisation**|Behraj Khan et.al.|[2607.26752](https://arxiv.org/abs/2607.26752)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-29**|**ActSWM: Action-Sensitive World Models for Long-Horizon Planning in Open-World Games**|Zhenfeng Gan et.al.|[2607.26712](https://arxiv.org/abs/2607.26712)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-07-29**|**ContactFlow: A video action conditioning that transfers across embodiments**|Sami Azirar et.al.|[2607.26579](https://arxiv.org/abs/2607.26579)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-29**|**Learning Dynamic User Personas from Implicit Interaction Streams via Iterative Refinement**|Haifeng Wu et.al.|[2607.26473](https://arxiv.org/abs/2607.26473)|**[link](https://github.com/NY1024/AgentSafety-Papers)**|
|**2026-07-29**|**CG-World: A Large-Scale World-State Dataset and Protocol for World Models**|Yiming Cai et.al.|[2607.26452](https://arxiv.org/abs/2607.26452)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-29**|**From Micro-Cognition to Self-Construction: A Four-Layer Integrative Review of Psychological Theories in HCI**|Xiaohe Bie et.al.|[2607.26402](https://arxiv.org/abs/2607.26402)|**[link](https://github.com/RLCL-EIT/robotics_arxiv_daily)**|
|**2026-07-28**|**Reeling It In: Flexible Needle Pick Up via Thread Manipulation for Autonomous Suturing**|Emma Huang et.al.|[2607.26337](https://arxiv.org/abs/2607.26337)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-07-28**|**Learning Implicit Causal World Models from Multi-Agent Demonstrations**|Jasorsi Ghosh et.al.|[2607.26336](https://arxiv.org/abs/2607.26336)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-28**|**Embodied Agents Take Control: Minimal-Interface Zero-Shot Agents Rival Industrial-Scale Policies in Vision-and-Language Navigation**|Jian Zhou et.al.|[2607.26148](https://arxiv.org/abs/2607.26148)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-28**|**INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models**|Junhan Sun et.al.|[2607.26056](https://arxiv.org/abs/2607.26056)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-28**|**Reinformed Dreamer: An Asymmetric World Model Efficiently Trained through Latent Guidance**|Gaspard Lambrechts et.al.|[2607.26040](https://arxiv.org/abs/2607.26040)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-28**|**Wonder: Video World Model Done Better**|Jiacong Xu et.al.|[2607.26037](https://arxiv.org/abs/2607.26037)|**[link](https://github.com/WingEdge777/daily-papers)**|
|**2026-07-28**|**DC-WAM: Dynamic-Centric Visual Supervision and Reasoning for World-Action Models**|Haoyuan Ji et.al.|[2607.25918](https://arxiv.org/abs/2607.25918)|**[link](https://github.com/iszhanjiawei/flow_matching_arxiv_daily)**|
|**2026-07-28**|**HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone**|Simple AI et.al.|[2607.25895](https://arxiv.org/abs/2607.25895)|**[link](https://huggingface.co/datasets/simple-world-lab/HiFi-UMI-2K)**|
|**2026-07-28**|**Transformer Transformer: A Unified Model for Motion-Conditioned Robot Co-design**|Huy Ha et.al.|[2607.25798](https://arxiv.org/abs/2607.25798)|**[link](https://github.com/YanjieZe/Paper-List)**|
|**2026-07-28**|**Tri-Manual Visuomotor Imitation Learning of Robot Policies**|James Zhao et.al.|[2607.25731](https://arxiv.org/abs/2607.25731)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-07-28**|**Shared Voxel-Map-Based Cooperative Indoor UAV Guidance with a Multi-Agent Soft Actor-Critic Controller**|Thomas Hickling et.al.|[2607.25728](https://arxiv.org/abs/2607.25728)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-07-28**|**When Does Legacy Data Start to Help? Emergent Transfer in Cross-Configuration Robot Learning**|Tao Wang et.al.|[2607.25593](https://arxiv.org/abs/2607.25593)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-07-28**|**P3: Probabilistic Policy Propagation for Stable VAE-Based Robot Learning**|Liyun Yan et.al.|[2607.25541](https://arxiv.org/abs/2607.25541)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-07-28**|**Temporal-Distance JEPA: Plan-Aware Representation Learning for Latent World Model Predictive Control**|Jiaxin Bai et.al.|[2607.25337](https://arxiv.org/abs/2607.25337)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-07-28**|**Belief-Aware Influence and Trust (BAIT): Shaping Human Belief During Repeated Human-Robot Interaction**|Ye-Ji Mun et.al.|[2607.25327](https://arxiv.org/abs/2607.25327)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-28**|**Medical world models in healthcare: foundations, applications, and challenges for trustworthy clinical translation**|Zhaoyan Chen et.al.|[2607.25242](https://arxiv.org/abs/2607.25242)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-07-28**|**VisualPatchWorld: Code World Models as Latent Structured Representations for Planning**|Jiaxin Bai et.al.|[2607.25236](https://arxiv.org/abs/2607.25236)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-07-27**|**Extended Reality as a Mediation Layer for Situated Human Control in Human-Robot Teaming**|Jens Grubert et.al.|[2607.25047](https://arxiv.org/abs/2607.25047)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-07-27**|**Data Pyramid for Embodied Manipulation**|Yifan Ye et.al.|[2607.24744](https://arxiv.org/abs/2607.24744)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-27**|**The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation**|Tianyi Men et.al.|[2607.24720](https://arxiv.org/abs/2607.24720)|**[link](https://github.com/xianshang33/llm-paper-daily)**|
|**2026-07-27**|**ArmnetBench v0.1: Parallel Real-World Evaluation of Manipulation Policies on a Low-Cost Arm Farm**|Praveen Selvaraj et.al.|[2607.24481](https://arxiv.org/abs/2607.24481)|null|
|**2026-07-27**|**Context Is King: How In-Context Specification Shapes the Geometry of Concepts**|Elad David et.al.|[2607.24425](https://arxiv.org/abs/2607.24425)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-27**|**PAC-DP: PAC-Bayesian Diffusion Policy Learning**|Mohammad Hasan Yeganegi et.al.|[2607.24296](https://arxiv.org/abs/2607.24296)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-27**|**FeelWorld: Visuo-Tactile World Model for Hierarchical Contact Prediction and Planning**|Wenxuan Ma et.al.|[2607.24267](https://arxiv.org/abs/2607.24267)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-27**|**Not Forgotten: Implementation and Evaluation of a Personalized Episodic Memory for the Humanoid Robot Head Kim**|Steve Aschenbrenner et.al.|[2607.24190](https://arxiv.org/abs/2607.24190)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-07-27**|**DeVA: Decoupled Video-Action Model with physical guidance for robot policy learning**|Mengqi Zhang et.al.|[2607.24159](https://arxiv.org/abs/2607.24159)|**[link](https://huggingface.co/models/mengqz9/DeVA)**|
|**2026-07-27**|**Scaling GUI Agents with Visual State Transitions**|Xiangyan Liu et.al.|[2607.24112](https://arxiv.org/abs/2607.24112)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-27**|**LeapBot-WA: World-Anchor Action Models via Predictive Latent Alignments**|Pei Liu et.al.|[2607.23969](https://arxiv.org/abs/2607.23969)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-27**|**WorldDiT: A Unified Diffusion Architecture for World and Action Modeling**|Sen Wang et.al.|[2607.23909](https://arxiv.org/abs/2607.23909)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-27**|**SHARE: Towards Head-Mounted AR with User-Centric SLAM in Shared Human-Robot Workspaces**|Tianyuan Du et.al.|[2607.23901](https://arxiv.org/abs/2607.23901)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-27**|**Embodied GPT-5.1: Evidence of a World Model?**|Roberto Spinelli et.al.|[2607.23899](https://arxiv.org/abs/2607.23899)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-26**|**A Few Words Go a Long Way: Language Guided Robot Policy Synthesis**|Daphne Chen et.al.|[2607.23784](https://arxiv.org/abs/2607.23784)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-26**|**LabRobFail: A Benchmark for Robotic Failure Analysis in Chemical Self-driving Laboratories**|Haobo Wang et.al.|[2607.23704](https://arxiv.org/abs/2607.23704)|**[link](https://github.com/alaliqing/AlphaAD)**|
|**2026-07-26**|**Action from Adjacent Set in Physical Space Outperforms the Best Prediction in World Models**|Liangyu Li et.al.|[2607.23602](https://arxiv.org/abs/2607.23602)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-26**|**Real-Time Human-Centric World Modeling for Upper-Body Human-Object Interaction**|Chaonan Ji et.al.|[2607.23517](https://arxiv.org/abs/2607.23517)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-26**|**PRISM: Polynomial Representations for Interaction-Structured Motor Control**|Seung Hyun Lee et.al.|[2607.23473](https://arxiv.org/abs/2607.23473)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-07-25**|**Towards Dual-Brain Minimal Sufficient Representation for Vision-Language Navigation**|Yihao Wu et.al.|[2607.23181](https://arxiv.org/abs/2607.23181)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-25**|**False Prophets: On the Security of World Models in Agentic Systems**|Erik Imgrund et.al.|[2607.23147](https://arxiv.org/abs/2607.23147)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-24**|**Robot-Factored World Models via Robot Rendering**|Byungjun Kim et.al.|[2607.22535](https://arxiv.org/abs/2607.22535)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-07-24**|**ViTacWorld: Scaling Visuo-Tactile World Models for Contact-Rich Robot Manipulation**|Yunao Huang et.al.|[2607.22530](https://arxiv.org/abs/2607.22530)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-07-24**|**Robot Learning to Communicate through Projected Visual Abstractions**|Danyang Yan et.al.|[2607.22434](https://arxiv.org/abs/2607.22434)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-07-24**|**On the Identifiability of Controlled World Models**|Xiangteng Zhang et.al.|[2607.22430](https://arxiv.org/abs/2607.22430)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-07-24**|**One Hand Watches The Other: Dynamic Multi-Agent Cooperation for Sample-Efficient Bimanual Manipulation in Dynamic Environments**|Jan Ole von Hartz et.al.|[2607.22119](https://arxiv.org/abs/2607.22119)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-07-24**|**Zero-Shot Mission-Level Evaluation for Aerial MLLM Agents**|Suman Navaratnarajah et.al.|[2607.22014](https://arxiv.org/abs/2607.22014)|**[link](https://github.com/xianshang33/llm-paper-daily)**|
|**2026-07-24**|**Music-JEPA: Learning a World Model of Sound from Action**|Ziyu Wang et.al.|[2607.22000](https://arxiv.org/abs/2607.22000)|**[link](https://github.com/AI-in-Transportation-Lab/awesome-jepa)**|
|**2026-07-24**|**ACME: A Multi-Cultural, Multi-Embodiment Social-Navigation Dataset**|Shashank Rao Marpally et.al.|[2607.21964](https://arxiv.org/abs/2607.21964)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-07-24**|**Action-Conditioned World Model for Goal Plane Probe Guidance in Robotic Ultrasound**|Siqi Fan et.al.|[2607.21918](https://arxiv.org/abs/2607.21918)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-07-24**|**TRW: TRACE-RealWorld---An Auditable Consistency Contract for World Models as Materialized Views**|Edward Y. Chang et.al.|[2607.21910](https://arxiv.org/abs/2607.21910)|**[link](https://github.com/yanghlll/ArxivDaily-Haolin)**|
|**2026-07-23**|**StARS: Socially Appropriate Robot Actions via a Recommender System-Driven Approach**|Erencem Ozbey et.al.|[2607.21802](https://arxiv.org/abs/2607.21802)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-23**|**Persistent Computational State: A Session-Centric Runtime for Generative World Models**|Zhen Lin et.al.|[2607.21686](https://arxiv.org/abs/2607.21686)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-07-22**|**Progress Reward Modeling for Robotic Learning: A Comprehensive Survey**|Jianshu Zhang et.al.|[2607.21655](https://arxiv.org/abs/2607.21655)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-07-23**|**Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers**|Sicheng Mo et.al.|[2607.21594](https://arxiv.org/abs/2607.21594)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-07-23**|**AXIS: A Growable Community-Driven Data Engine for Scalable Robot Manipulation**|Mengfei Zhao et.al.|[2607.21588](https://arxiv.org/abs/2607.21588)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-23**|**VoLN: Vision-Only Long-Horizon Navigation---Paradigm, Benchmark, and Method**|Jiabin Lou et.al.|[2607.21400](https://arxiv.org/abs/2607.21400)|**[link](https://huggingface.co/datasets/Louj/VoLN-UAV-dataset)**|
|**2026-07-23**|**Factorized Spatio-Temporal Convolutions for Human Pose Estimation from Planar Lidar**|Simone Arreghini et.al.|[2607.21309](https://arxiv.org/abs/2607.21309)|**[link](https://github.com/Jianqiuer/Awesome6DPoseEstimation)**|
|**2026-07-23**|**HyWorldVLA: A Vision-Language-Action Model with Hybrid World Modeling for Autonomous Driving**|Quanfu Yu et.al.|[2607.20988](https://arxiv.org/abs/2607.20988)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-07-22**|**Emergent Compositional Skills in Mixture-of-Experts VLAs**|Shlok Shah et.al.|[2607.20771](https://arxiv.org/abs/2607.20771)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-22**|**PhysCoRe: Physics-Corrected Residual World Models for Material-Aware Deformable Dynamics**|Haocheng Yin et.al.|[2607.20653](https://arxiv.org/abs/2607.20653)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-07-22**|**Courteous Anticipation: Improving Long-Lived Task Planning in Persistent Shared Environments**|Md Ridwan Hossain Talukder et.al.|[2607.20289](https://arxiv.org/abs/2607.20289)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-22**|**Active Inference as a Convex Markov Decision Process**|Nikola Milosevic et.al.|[2607.20152](https://arxiv.org/abs/2607.20152)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-22**|**Odin: Primitive-Level Synchronization for Distributed Point-Based Neural Rendering**|Zhenxiang Ma et.al.|[2607.19893](https://arxiv.org/abs/2607.19893)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-22**|**LAVIFT: Latent-Action-Guided Vision Fine-Tuning for Surgical Interaction Recognition**|Jiajun Cheng et.al.|[2607.19889](https://arxiv.org/abs/2607.19889)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-22**|**EA-Nav: Learning Safe Visual Navigation Policies with Embodiment Awareness**|Jialu Zhang et.al.|[2607.19880](https://arxiv.org/abs/2607.19880)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-22**|**KineBench: Benchmarking Embodied World Models via IDM-Free Kinematic Grounding**|Zeyu Liu et.al.|[2607.19876](https://arxiv.org/abs/2607.19876)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-07-22**|**Dreamer-CPC: Message Learning with World Models for Decentralized Multi-agent Reinforcement Learning**|Taisuke Takayama et.al.|[2607.19809](https://arxiv.org/abs/2607.19809)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-22**|**The World Model Remembers, the Actor Forgets: Dream Rehearsal for Continual Model-Based RL**|Gurp Nijjer et.al.|[2607.19749](https://arxiv.org/abs/2607.19749)|**[link](https://huggingface.co/models/gurpnijjer/dream-rehearsal)**|
|**2026-07-22**|**Koopman Dreamer: Spectrally Constrained Latent Dynamics for Stable World-Model Imagination**|Jiaqi Li et.al.|[2607.19719](https://arxiv.org/abs/2607.19719)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-07-21**|**Learning Personalized Safety Interventions for Haptic Human-Robot Shared Control**|Dawei Zhang et.al.|[2607.19534](https://arxiv.org/abs/2607.19534)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-21**|**Masked Visual Actions for Unified World Modeling**|Hadi Alzayer et.al.|[2607.19343](https://arxiv.org/abs/2607.19343)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-07-21**|**ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU**|Fan Jiang et.al.|[2607.19191](https://arxiv.org/abs/2607.19191)|**[link](https://huggingface.co/spaces/acvlab/abot-world-interactive)**|
|**2026-07-22**|**Agentic Real2Sim: Physics-based World Modeling with Vision-Language Agents**|Guanxiong Chen et.al.|[2607.19190](https://arxiv.org/abs/2607.19190)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-21**|**FilmWorld: Agentic Novel-to-Film Generation through Dynamic Cinematic World Modeling**|Jialong Zuo et.al.|[2607.19038](https://arxiv.org/abs/2607.19038)|**[link](https://github.com/greasebig/daily-video-papers)**|
|**2026-07-21**|**Athena-Brain Technical Report: An Efficient Robot Brain for General Intelligence and Embodied Interactio**|Jialian Li et.al.|[2607.18985](https://arxiv.org/abs/2607.18985)|**[link](https://github.com/NickDee96/ASR-TTS-paper-daily)**|
|**2026-07-21**|**NaviAIS: A Scenario-Level Vessel Trajectory Prediction Dataset withVectorized Lane Priors and the NaviLane Forecasting Framework**|Yuan Gui et.al.|[2607.18887](https://arxiv.org/abs/2607.18887)|**[link](https://github.com/zezhishao/DailyArXiv)**|
|**2026-07-21**|**WorldScape Policy 2.0: Empowering Steerable World Action Modeling with Reasoning-Augmented Memory**|Haisheng Su et.al.|[2607.18840](https://arxiv.org/abs/2607.18840)|**[link](https://github.com/manifoldai-research/WorldScape-Policy)**|
|**2026-07-21**|**Motion Primitive Discovery in a Humanoid Robot via Self-Organising Maps for Phase Recognition**|Radovan Gregor et.al.|[2607.18737](https://arxiv.org/abs/2607.18737)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-21**|**DWM: Separating World Effects from Actions in Latent World Models**|Yi-Ge Zhang et.al.|[2607.18715](https://arxiv.org/abs/2607.18715)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-07-21**|**RoboInter1.5: A Holistic Intermediate Representation Suite for Embodied World Modeling and Robotic Manipulation**|Ziqin Wang et.al.|[2607.18709](https://arxiv.org/abs/2607.18709)|**[link](https://github.com/ttylerzh/robotics_paper_daily)**|
|**2026-07-21**|**Generative World Renderer at the Speed of Play**|Guixu Lin et.al.|[2607.18703](https://arxiv.org/abs/2607.18703)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-21**|**Do AI-Native Biotechs Need Departments? Benchmarking Company World Models for AI-Driven Drug Development**|Yinan Wang et.al.|[2607.18696](https://arxiv.org/abs/2607.18696)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-20**|**Planning as Emergent Behavior in Reinforcement Learning with Relational Hidden States**|Armin Sommer et.al.|[2607.18589](https://arxiv.org/abs/2607.18589)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-20**|**Integrity-Gated Eco-CACC: Epistemic Admissibility for Cooperative Driving at Signalized Intersections**|Lyes Saad Saoud et.al.|[2607.18565](https://arxiv.org/abs/2607.18565)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-20**|**Evaluation-Recording Contamination in Learned Nano-Quadrotor Dynamics: A Fresh-Seed Audit**|David Shulman et.al.|[2607.18482](https://arxiv.org/abs/2607.18482)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-20**|**AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report**|AlayaWorld Team et.al.|[2607.18367](https://arxiv.org/abs/2607.18367)|**[link](https://github.com/greasebig/daily-video-papers)**|
|**2026-07-20**|**Patch Policy: Efficient Embodied Control via Dense Visual Representations**|Gaoyue Zhou et.al.|[2607.18236](https://arxiv.org/abs/2607.18236)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-20**|**Imitation of Arm Gestures by the Semi-Humanoid Robot NICO**|Anastasiya Ihnatovich et.al.|[2607.18197](https://arxiv.org/abs/2607.18197)|**[link](https://github.com/Jianqiuer/Awesome6DPoseEstimation)**|
|**2026-07-20**|**FlashRT: Agent Harness for Guiding Agents to Deploy Real-Time Multimodal Applications**|Krish Agarwal et.al.|[2607.18171](https://arxiv.org/abs/2607.18171)|**[link](https://github.com/xianshang33/llm-paper-daily)**|
|**2026-07-20**|**World Translation: Minimizing Sim-to-Real Gap with Backward Dynamics Extraction and Unpaired Domain Translation**|Xinchen Yao et.al.|[2607.18154](https://arxiv.org/abs/2607.18154)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-20**|**RoboHarness: Memory-Driven Orchestration of Heterogeneous Robot Policies for Long-Horizon Planning**|Jinbang Huang et.al.|[2607.18060](https://arxiv.org/abs/2607.18060)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-20**|**RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model**|Kehan Li et.al.|[2607.17977](https://arxiv.org/abs/2607.17977)|**[link](https://github.com/alibaba-damo-academy/RynnBrain)**|
|**2026-07-20**|**SAGE: Subgoal-Conditioned Action Generation for Latent World Model Planning**|Letian Cheng et.al.|[2607.17973](https://arxiv.org/abs/2607.17973)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-07-20**|**PGN: Design and Implementation of a Vision-Language Navigation System Based on Pangu Multimodal Foundation Model**|Li Xian et.al.|[2607.17806](https://arxiv.org/abs/2607.17806)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-20**|**Mobile Network Control with a World Model**|Maxime Bouton et.al.|[2607.17747](https://arxiv.org/abs/2607.17747)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-07-20**|**Planning with Transformers: Chain of Computation and Structured Context Windows**|Ehsan Futuhi et.al.|[2607.17710](https://arxiv.org/abs/2607.17710)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-20**|**Attention from Above: A Multimodal Model for Drone-Based Object Localization**|Hyun-Ki Jung et.al.|[2607.17669](https://arxiv.org/abs/2607.17669)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-20**|**Reinforcement Learning: From Algorithms To Foundation Models**|Zihan Ding et.al.|[2607.17560](https://arxiv.org/abs/2607.17560)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-20**|**Thinking in Video: Can Video Generators Really Reason About the Real World?**|Yongheng Zhang et.al.|[2607.17523](https://arxiv.org/abs/2607.17523)|**[link](https://huggingface.co/datasets/BRZ911/Thinking-in-Video-Data)**|
|**2026-07-20**|**GeoWorldAD: Geometry World Action Model for Autonomous Driving**|Songyan Zhang et.al.|[2607.17521](https://arxiv.org/abs/2607.17521)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-07-19**|**STAR: Skeletal Token Alignment and Rearrangement for Interaction Recognition**|Yuhang Wen et.al.|[2607.17342](https://arxiv.org/abs/2607.17342)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-19**|**An Explicit World Model Based on Data-First Ontology: DaoQL Multimodal Storage Validation and Counterfactual Reasoning Evaluation**|Zhanbo Li et.al.|[2607.17269](https://arxiv.org/abs/2607.17269)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-19**|**EvolvingWorld: An Open-Schema Framework for Co-Evolving Role-Play Agents and World Model in Interactive Literary World**|Qing Zong et.al.|[2607.17250](https://arxiv.org/abs/2607.17250)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-19**|**Articulated Humanoid Head for a Robot Receptionist Capable of Natural Human Interaction**|Tharusha Fonseka et.al.|[2607.17042](https://arxiv.org/abs/2607.17042)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-18**|**User-Driven Learning from Demonstration: A Trajectory and Impedance Learning Method**|Zi-Qi Yang et.al.|[2607.16998](https://arxiv.org/abs/2607.16998)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-18**|**Environment-free Synthetic Data Generation for API-Calling Agents**|Seanie Lee et.al.|[2607.16900](https://arxiv.org/abs/2607.16900)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-17**|**Handroid: Bridging Dexterous Hand and Humanoid**|Ruogu Li et.al.|[2607.16187](https://arxiv.org/abs/2607.16187)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-17**|**DSWorld: A Data Science World Model for Efficient Autonomous Agents**|Zherui Yang et.al.|[2607.15901](https://arxiv.org/abs/2607.15901)|**[link](https://github.com/xianshang33/llm-paper-daily)**|
|**2026-07-17**|**Orbis 2: A Hierarchical World Model for Driving**|Sudhanshu Mittal et.al.|[2607.15898](https://arxiv.org/abs/2607.15898)|**[link](https://huggingface.co/models/sud0301/orbis2)**|
|**2026-07-17**|**Exo2EgoPose: Leveraging Exocentric Demonstrations for Vision-Language guided Egocentric 3D Hand Pose Forecasting**|Zhaofeng Shi et.al.|[2607.15890](https://arxiv.org/abs/2607.15890)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-17**|**In the Driver's Seat: A Multi-Company Study on the Reality of Autonomous Driving System Testing**|Qunying Song et.al.|[2607.15820](https://arxiv.org/abs/2607.15820)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-17**|**ToolVerse: Unlocking Massive Environments and Long-Horizon Tasks for Agentic Reinforcement Learning**|Shuaiyu Zhou et.al.|[2607.15660](https://arxiv.org/abs/2607.15660)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-17**|**IMBench: A Benchmark for Intuitive Robotic Manipulation**|Anurag Maurya et.al.|[2607.15641](https://arxiv.org/abs/2607.15641)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-17**|**AEGIS: Assay-Aware Protocol Validation and Runtime Monitoring for Open-Source Liquid Handling Robots**|Priyanka V. Setty et.al.|[2607.15620](https://arxiv.org/abs/2607.15620)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-17**|**PACE: Persona Adaptation through Conversational Elicitation in Human-Robot Interaction**|Peizhen Li et.al.|[2607.15579](https://arxiv.org/abs/2607.15579)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-17**|**SeerGuard: A Safety Framework for Mobile GUI Agents via World Model Prediction**|Xue Yu et.al.|[2607.15550](https://arxiv.org/abs/2607.15550)|**[link](https://huggingface.co/spaces/hugging-apps/seerguard-sawm)**|
|**2026-07-17**|**E3DGS: Unified Geometric-Photometric Equivariance for 3D Gaussian Splatting via Color-as-Geometry Embedding**|Chankyo Kim et.al.|[2607.15536](https://arxiv.org/abs/2607.15536)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-16**|**Risk-Aware Preference Learning for Stochastic Outcomes**|Yi-Shiuan Tung et.al.|[2607.15483](https://arxiv.org/abs/2607.15483)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-16**|**Do Coding Agents Need Executable World Models, Simplification, and Verification to Solve ARC-AGI-3?**|Sergey Rodionov et.al.|[2607.15439](https://arxiv.org/abs/2607.15439)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-16**|**Hierarchical Denoising For Multi-Step Visual Reasoning**|Zezhong Qian et.al.|[2607.15278](https://arxiv.org/abs/2607.15278)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-16**|**RoboTTT: Context Scaling for Robot Policies**|Yunfan Jiang et.al.|[2607.15275](https://arxiv.org/abs/2607.15275)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-16**|**When Words Are Safe But Actions Kill: Probing Physical Danger Beyond Text Safety in Hidden-State Risk Space**|Weimeng Wang et.al.|[2607.15218](https://arxiv.org/abs/2607.15218)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-16**|**Scaling Behavior Foundation Model for Humanoid Robots**|Weishuai Zeng et.al.|[2607.15163](https://arxiv.org/abs/2607.15163)|**[link](https://github.com/Foruck/Awesome-Human-Motion)**|
|**2026-07-16**|**Concept-Guided Spatial Regularization for World Models in Atari Pong**|Yukuan Lu et.al.|[2607.15142](https://arxiv.org/abs/2607.15142)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-07-16**|**Catch, Throw, Repeat: Planning for Human-Robot Partner Juggling**|Jonathan Rainer Lippert et.al.|[2607.15129](https://arxiv.org/abs/2607.15129)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-16**|**DriftWorld: Fast World Modeling through Drifting**|Susie Lu et.al.|[2607.15065](https://arxiv.org/abs/2607.15065)|**[link](https://github.com/knightnemo/Awesome-World-Models)**|
|**2026-07-16**|**Human-Robot Interaction in GenAI Architectures via the Agent-Client Protocol**|Jesus Moncada-Ramirez et.al.|[2607.14919](https://arxiv.org/abs/2607.14919)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-16**|**An Intelligent-Cloud Edge Multimodal Interaction System for Robots**|Zihan Guo et.al.|[2607.14675](https://arxiv.org/abs/2607.14675)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-16**|**Knowing You at First Glance: Inferring Apparent Personality from Faces**|Shuhuan Chen et.al.|[2607.14631](https://arxiv.org/abs/2607.14631)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-16**|**World-Model-Aware Responsibility Allocation in Heterogeneous Logistics Systems**|Artan Markaj et.al.|[2607.14550](https://arxiv.org/abs/2607.14550)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-16**|**SafeRelBench: A Spatial-Relation-Aware Benchmark for Process-Level Safety in VLM-Driven Embodied Agents**|Huaigang Yang et.al.|[2607.14543](https://arxiv.org/abs/2607.14543)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-16**|**VTM-Nav: Hierarchical Visual-Topological Memory for Cross-Episode Object-Goal Navigation**|Xiaoran Xu et.al.|[2607.14514](https://arxiv.org/abs/2607.14514)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-16**|**Active Real-World Factor-Based Evaluation for Generalist Robot Policies**|Andrew Liao et.al.|[2607.14439](https://arxiv.org/abs/2607.14439)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-15**|**ConFlow: Constraints-Guided Learning with Flow Matching for Motion Generation**|Nutan Chen et.al.|[2607.14424](https://arxiv.org/abs/2607.14424)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-15**|**An offline approach to fNIRS-guided reinforcement learning for robot behavior**|Julia Santaniello et.al.|[2607.14393](https://arxiv.org/abs/2607.14393)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-15**|**From Pixels to States: Rethinking Interactive World Models as Game Engines**|Zhen Li et.al.|[2607.14076](https://arxiv.org/abs/2607.14076)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-07-16**|**Zero2Skill: Bootstrapping Robot Skills through Autonomous Data Collection, Training, and Deployment**|Boyuan Wang et.al.|[2607.14047](https://arxiv.org/abs/2607.14047)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-15**|**M $^\text{4}$ World: A Multi-view Multimodal Driving World Model for Interactive Object Manipulation and Minute-long Streaming**|Ke Cheng et.al.|[2607.14005](https://arxiv.org/abs/2607.14005)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-07-16**|**GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch**|GigaWorld Team et.al.|[2607.13960](https://arxiv.org/abs/2607.13960)|**[link](https://huggingface.co/models/open-gigaai/Giga-World-Policy-0.5)**|
|**2026-07-15**|**Anatomy of Uncertainty: Expressive Descriptors of Robotic Manipulator Motion for Non-verbal Communication in Human-Robot Collaboration**|Ridhima Bector et.al.|[2607.13696](https://arxiv.org/abs/2607.13696)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-15**|**Towards Spatial Supersensing in the Wild**|Tianjun Gu et.al.|[2607.13681](https://arxiv.org/abs/2607.13681)|**[link](https://huggingface.co/datasets/THUSI-Lab/VSI-Super-Wild)**|
|**2026-07-15**|**Equilibrium Information Aggregation under Machine Learning**|Andrew Ellis et.al.|[2607.13670](https://arxiv.org/abs/2607.13670)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-15**|**Exploratory, Communicative, and Deployable: Vision-Driven Embodied Agents for Open-World Mobile Manipulation**|Boyu Mi et.al.|[2607.13653](https://arxiv.org/abs/2607.13653)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-15**|**From Surface Forecasting to Observability Forecasting: A Latent World Model for Cloud-Aware EO Monitoring**|Mohanad Albughdadi et.al.|[2607.13651](https://arxiv.org/abs/2607.13651)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-15**|**From Language to Navigation Goals: A Vision-Language Approach for Semantic Navigation of Mobile Robots Using RGB-D Perception**|Jose Martínez-Fajardo et.al.|[2607.13624](https://arxiv.org/abs/2607.13624)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-15**|**UESF-Bench: Benchmarking and Probing for Unified Embodied Seeking and Following**|Kun Yu et.al.|[2607.13621](https://arxiv.org/abs/2607.13621)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-15**|**The SIGReg Objective as Variational Free Energy: A Theoretical Active-Inference Account of JEPA World Models**|Fabio Arnez et.al.|[2607.13612](https://arxiv.org/abs/2607.13612)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-15**|**Active Trust Management for Successful Human-Robot Teaming: Moving from a Trust Repair to a Trust Satisficing Perspective**|Nicola Webb et.al.|[2607.13595](https://arxiv.org/abs/2607.13595)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-15**|**Grounded world models in biological organisms and future embodied AI**|Giovanni Pezzulo et.al.|[2607.13560](https://arxiv.org/abs/2607.13560)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-15**|**Joint On-and-Off Policy Learning for Vision-and-Language Navigation**|Qingrong He et.al.|[2607.13461](https://arxiv.org/abs/2607.13461)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-15**|**Ego-Dynamics-Augmented World Model for Autonomous Driving with Zero-Shot Cross-Chassis Adaptation**|Zhidong Wang et.al.|[2607.13410](https://arxiv.org/abs/2607.13410)|**[link](https://github.com/EasonTuT/Awesome-Interactive-World-Model)**|
|**2026-07-15**|**Where Should RL Post-Training Compute Go? Model Size, Search, Learning, and Feedback**|Patrick Wilhelm et.al.|[2607.13389](https://arxiv.org/abs/2607.13389)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-14**|**Just-In-Time Scene Graph Growth: Combating Perceptual Saturation in Long-Horizon Robotics**|Yue Chang et.al.|[2607.13245](https://arxiv.org/abs/2607.13245)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-14**|**Learning Safe Agent Behaviour from Human Preferences and Justifications via World Models**|Ilias Kazantzidis et.al.|[2607.13172](https://arxiv.org/abs/2607.13172)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-14**|**Worlds in One Demo: A Synthetic Data Engine for Learning Open-World Mobile Manipulation**|Lingxiao Guo et.al.|[2607.13154](https://arxiv.org/abs/2607.13154)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-14**|**DenseReward: Dense Reward Learning via Failure Synthesis for Robotic Manipulation**|Yu Fang et.al.|[2607.13033](https://arxiv.org/abs/2607.13033)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-14**|**FlowWAM: Optical Flow as a Unified Action Representation for World Action Models**|Yixiang Chen et.al.|[2607.13017](https://arxiv.org/abs/2607.13017)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-14**|**Hy-Embodied-VLM-1.0: Efficient Physical-World Agents**|Ziyi Wang et.al.|[2607.12894](https://arxiv.org/abs/2607.12894)|**[link](https://huggingface.co/models/tencent/Hy-Embodied-VLM-1.0)**|
|**2026-07-14**|**UR-VC: Unsupervised Robotic Value Correction for Time-Derived Progress Proxies**|Lirui Zhao et.al.|[2607.12892](https://arxiv.org/abs/2607.12892)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-07-14**|**Instance-Enriched Semantic Maps for Visual Language Navigation**|Jiho Hong et.al.|[2607.12630](https://arxiv.org/abs/2607.12630)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-07-14**|**TrustVLA: Mechanism-Guided Inference-Time Defense Against Vision-Language-Action Backdoors**|Pinhan Fu et.al.|[2607.12571](https://arxiv.org/abs/2607.12571)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-14**|**TRACE: An Operational Reasoning Schema for Auditable Agentic Commitments**|Edward Y. Chang et.al.|[2607.12480](https://arxiv.org/abs/2607.12480)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-14**|**From Observation to Insight: Mechanistic World Models and the Quest for Autonomous Discovery**|Ingmar Posner et.al.|[2607.12474](https://arxiv.org/abs/2607.12474)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-14**|**Deployable Human Preference Alignment in Robotics: Learning Representative Rewards from Diverse Human Preferences**|Taehyung Kim et.al.|[2607.12466](https://arxiv.org/abs/2607.12466)|**[link](https://github.com/pstAmbition/DailyArXiv_Multimodal)**|
|**2026-07-14**|**The GEST-Engine: From Event Graphs to Synthetic Video. A Full Technical Report**|Nicolae Cudlenco et.al.|[2607.12231](https://arxiv.org/abs/2607.12231)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-13**|**Analysis of Mutual and Referential Human and Robot Gazes in a Collaborative Word Association Game**|Jens V. Rüppel et.al.|[2607.12181](https://arxiv.org/abs/2607.12181)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-07-13**|**Cycle-World: Mitigating Error Accumulation in Long-term Video World Models via Reverse-Prediction Cycle Consistency**|Zihan Su et.al.|[2607.11836](https://arxiv.org/abs/2607.11836)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-07-13**|**Casting Everything to Online API Services? A Survey of Integrating Localized Speech Recognition Models in Robotic Systems**|Sheng Li et.al.|[2607.11792](https://arxiv.org/abs/2607.11792)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-13**|**Requirement-Driven Design of Whole-Body Social Tactile Sensing via Virtual Human-Robot Interaction**|Dakarai Crowder et.al.|[2607.11690](https://arxiv.org/abs/2607.11690)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-13**|**From World Action Models to Embodied Brains: A Roadmap for Open-World Physical Intelligence**|Yuanzhi Liang et.al.|[2607.11689](https://arxiv.org/abs/2607.11689)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-14**|**ABot-3DWorld 0: A Universal World Model to Explore Any 3D Space**|Mingchao Sun et.al.|[2607.11673](https://arxiv.org/abs/2607.11673)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-07-13**|**Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model**|Xinghang Li et.al.|[2607.11643](https://arxiv.org/abs/2607.11643)|**[link](https://huggingface.co/models/XiaomiRobotics/Xiaomi-Robotics-U0)**|
|**2026-07-13**|**ERR@HRI 3.0 Challenge: Multimodal Detection of Errors and Anticipation in Human-Robot Interactions**|Maria Teresa Parreira et.al.|[2607.11570](https://arxiv.org/abs/2607.11570)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-13**|**WALA Learning Executable Latent Actions from Action-Labeled Demonstrations and Action-Free Videos**|Jiahao Liu et.al.|[2607.11397](https://arxiv.org/abs/2607.11397)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-13**|**A Glimpse into Long-term Physical Coexistence with Intelligent Robots**|Weiqi Jin et.al.|[2607.11377](https://arxiv.org/abs/2607.11377)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-13**|**Towards Predictive, Aligned, and Scalable Robot Learning**|Peijun Tang et.al.|[2607.11270](https://arxiv.org/abs/2607.11270)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-13**|**VIA: Visual Interface Agent for Robot Control**|Hengyuan Hu et.al.|[2607.11119](https://arxiv.org/abs/2607.11119)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-13**|**Whole-Body Semantic-to-Actuation Grounding of Elephant-Inspired Soft-Trunk Motion via Lightweight Flow Matching**|Tingcong Liu et.al.|[2607.11018](https://arxiv.org/abs/2607.11018)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-12**|**Distributed Agent System: Fault-Tolerant Collaboration Among Embodied Agents**|Kai Yu et.al.|[2607.10811](https://arxiv.org/abs/2607.10811)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-12**|**Compositional Context Fine-Tuning Vision-Language Model for Complex Assembly Action Understanding from Videos**|Hao Zheng et.al.|[2607.10797](https://arxiv.org/abs/2607.10797)|**[link](https://github.com/DoongLi/ICRA2026-Paper-List)**|
|**2026-07-12**|**Is Energy Guidance All You Need? Training-Free Norm Injection for Driving World Models**|Xiyan Su et.al.|[2607.10781](https://arxiv.org/abs/2607.10781)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-07-12**|**Traj-VLN: Learning Pixel-Space Interaction via Autoregressive Trajectory Generation**|Changfei Fu et.al.|[2607.10744](https://arxiv.org/abs/2607.10744)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-12**|**Action Map Policy: Learning 3D Closed-loop Manipulation via Pixel Classification**|Haojie Huang et.al.|[2607.10706](https://arxiv.org/abs/2607.10706)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-07-12**|**Artificial Foveated Perception for Mitigating Shortcut Learning in Robotic Foundation Models**|Xiatao Sun et.al.|[2607.10655](https://arxiv.org/abs/2607.10655)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-12**|**World Models as Adversaries: Multi-Agent Self-Play Fine-Tuning for Robust Motion Planning**|Tong Nie et.al.|[2607.10630](https://arxiv.org/abs/2607.10630)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-07-11**|**Stateful Worlds, Stateless Elasticity: Exact-State Serving for Interactive World Models**|Jin Li et.al.|[2607.10389](https://arxiv.org/abs/2607.10389)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-10**|**PanoWorld: Real-World Panoramic Generation**|Haoyuan Li et.al.|[2607.09661](https://arxiv.org/abs/2607.09661)|**[link](https://huggingface.co/models/Insta360-Research/PanoWorld)**|
|**2026-07-10**|**PAC-ACT: Post-training Actor-Critic for Action Chunking Transformers**|Yujie Pang et.al.|[2607.09590](https://arxiv.org/abs/2607.09590)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-10**|**Communication-Efficient Digital-Twin Coordination for Heterogeneous LLM Embodied Agents over Computing Power Networks**|Nuocheng Yang et.al.|[2607.09330](https://arxiv.org/abs/2607.09330)|**[link](https://github.com/xianshang33/llm-paper-daily)**|
|**2026-07-10**|**Validating Virtual Reality for Studying Multimodal Human-Robot Interaction in Socially Aware Robot Navigation**|Hariharan Arunachalam et.al.|[2607.09261](https://arxiv.org/abs/2607.09261)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-07-10**|**Causally Debiased Latent Action Model for Embodied Action Conditioned World Models**|Yufan Wei et.al.|[2607.09185](https://arxiv.org/abs/2607.09185)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-10**|**Toward Active Object Detection for UAVs in the Wild: A Large-Scale Dataset, Benchmark and Method**|Tianpeng Liu et.al.|[2607.09078](https://arxiv.org/abs/2607.09078)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-09**|**SplatCtrl: Perception-Action Coupling via Gaussian Scene Representations and Reactive Robot Control**|Siddarth Jain et.al.|[2607.08948](https://arxiv.org/abs/2607.08948)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-09**|**GATS: Graph-Augmented Tree Search with Layered World Models for Efficient Agent Planning**|Maureese Williams et.al.|[2607.08894](https://arxiv.org/abs/2607.08894)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-09**|**FlowDAgger: Human-in-the-Loop Adaptation of Generative Robot Policies in Latent Space**|Michael Murray et.al.|[2607.08877](https://arxiv.org/abs/2607.08877)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-09**|**AgenticFocus: Object-Preserving Mixed Reality Synthesis from Human FPV Video for Dexterous Humanoid Learning**|Iaroslav Kolomiets et.al.|[2607.08857](https://arxiv.org/abs/2607.08857)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-09**|**DexVerse: A Modular Benchmark for Multi-Task, Multi-Embodiment Dexterous Manipulation**|Yunchao Yao et.al.|[2607.08751](https://arxiv.org/abs/2607.08751)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-09**|**A New Human-Likeness and Comfort Index for Robot Movements Along Prescribed Paths**|Rosanna Coccaro et.al.|[2607.08620](https://arxiv.org/abs/2607.08620)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-09**|**Early to Share, Late to Save: Synchronisation-Driven Communication Gating in Bandwidth-Constrained Cooperative VLN**|Arav Gupta et.al.|[2607.08504](https://arxiv.org/abs/2607.08504)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-08**|**EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Data**|Baoyu Li et.al.|[2607.08436](https://arxiv.org/abs/2607.08436)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-09**|**WCog-VLA: A Dual-Level World-Cognitive Vision-Language-Action Model for End-to-End Autonomous Driving**|Xuerun Yan et.al.|[2607.08375](https://arxiv.org/abs/2607.08375)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-09**|**Write-Protected Discrete Bottlenecks for Language-Grounded World Models: A Structural Limitation and Sufficient Fix**|Jiayi Fang et.al.|[2607.08312](https://arxiv.org/abs/2607.08312)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-08**|**Soft Robotic Exogloves for Dexterous Mobility -- Towards Personalized Rehabilitation**|Paul Dela Cruz et.al.|[2607.07968](https://arxiv.org/abs/2607.07968)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-08**|**Unlocking Temporal Generalization in Hamiltonian Video Dynamics Models**|Eli Laird et.al.|[2607.07763](https://arxiv.org/abs/2607.07763)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-08**|**Infinite Worlds with Versatile Interactions**|Zelin Gao et.al.|[2607.07534](https://arxiv.org/abs/2607.07534)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-09**|**Behavior Foundations for Quadruped Robots: ABot-C0 Technical Report**|Xufeng Zhao et.al.|[2607.07370](https://arxiv.org/abs/2607.07370)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-08**|**Multimodal Voice Activity Projection for Turn-Taking in Social Robots with Voice-Activity-Related Pretrained Encoders**|Antonio Cano et.al.|[2607.07294](https://arxiv.org/abs/2607.07294)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-09**|**TouchWorld: A Predictive and Reactive Tactile Foundation Model for Dexterous Manipulation**|Jianyi Zhou et.al.|[2607.07287](https://arxiv.org/abs/2607.07287)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-08**|**Validate the Dream Before You Trust Its Verdict: Admissibility for World-Model Simulators**|Christian Oefinger et.al.|[2607.07196](https://arxiv.org/abs/2607.07196)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-08**|**Compositional Motion Generation from Demonstration with Object-Centric Neural Fields**|Ahmet Ercan Tekden et.al.|[2607.07129](https://arxiv.org/abs/2607.07129)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-08**|**Ego-Human Motion Prediction with 3D-Aware LLM**|Yujin Bae et.al.|[2607.07001](https://arxiv.org/abs/2607.07001)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-08**|**WAM-TTT: Steering World-Action Models by Watching Human Play at Test Time**|Yusen Feng et.al.|[2607.06988](https://arxiv.org/abs/2607.06988)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-08**|**Grounding Spatial Relations in a Compact World Model: Instruction Leakage and a Goal-Free Dynamics Fix**|Yufeng Wang et.al.|[2607.06925](https://arxiv.org/abs/2607.06925)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-08**|**GemNav: Discrete-Token Visual Robot Navigation using a Multimodal Large Language Model**|Peter Bohm et.al.|[2607.06882](https://arxiv.org/abs/2607.06882)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-07**|**Vision Language Action (VLA) Models for Unmanned Aerial Robotics and Bimanual Manipulation: A Review**|Inkyu Sa et.al.|[2607.06706](https://arxiv.org/abs/2607.06706)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-07**|**SPEAR: A Simulator for Photorealistic Embodied AI Research**|Mike Roberts et.al.|[2607.06701](https://arxiv.org/abs/2607.06701)|**[link](https://github.com/spear-sim/spear)**|
|**2026-07-07**|**RoboSnap: One-Shot Real-to-Sim Scene Generation for Generalizable Robot Learning and Evaluation**|Shujie Zhang et.al.|[2607.06699](https://arxiv.org/abs/2607.06699)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-07**|**The Rank-One Corner: How Much Value Equivalence Does a Task Need from a World Model?**|Donna Vakalis et.al.|[2607.06640](https://arxiv.org/abs/2607.06640)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-07**|**Embodied Human-Robot Interaction via Acoustics: A MARL Approach with AcoustoBots for Spatial Data Physicalization**|Shiqi Liu et.al.|[2607.06563](https://arxiv.org/abs/2607.06563)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-07**|**RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation**|Haoyu Zhao et.al.|[2607.06559](https://arxiv.org/abs/2607.06559)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-07**|**RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation**|Haoyu Zhao et.al.|[2607.06558](https://arxiv.org/abs/2607.06558)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-07**|**Hypothesis-driven Model Expansion under Uncertainty for Open-World Robot Planning**|Anxing Xiao et.al.|[2607.06501](https://arxiv.org/abs/2607.06501)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-07**|**From Foundation to Application: Improving VLA Models in Practice**|Wei Wu et.al.|[2607.06403](https://arxiv.org/abs/2607.06403)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-07**|**A Definition and Roadmap for World Models**|Xinyuan Chen et.al.|[2607.06401](https://arxiv.org/abs/2607.06401)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-07**|**Responsible Personalisation: The Double-Edged Sword of Personalisation in Human-Robot Interaction**|Antonio Andriella et.al.|[2607.06344](https://arxiv.org/abs/2607.06344)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-07-07**|**OrchardBench: A Physically-Grounded, GPU-Parallel Apple-Orchard Simulation Benchmark for Agricultural Robotics**|Humphrey Munn et.al.|[2607.06337](https://arxiv.org/abs/2607.06337)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-07-07**|**AlayaWorld: Long-Horizon and Playable Video World Generation**|AlayaWorld Team et.al.|[2607.06291](https://arxiv.org/abs/2607.06291)|**[link](https://github.com/liujiuming123/Awesome-Interactive-World-Model)**|
|**2026-07-07**|**MoWorld: A Flash World Model**|Team Moxin et.al.|[2607.06216](https://arxiv.org/abs/2607.06216)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-07**|**EAGOR: Embodied Reasoning in Omni-direction**|Shriram Damodaran et.al.|[2607.06165](https://arxiv.org/abs/2607.06165)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-07-07**|**RoboTALES: Learning Reasoning-Guided Robot Policies via Task-Aligned Simulated Futures**|Hanan Gani et.al.|[2607.06018](https://arxiv.org/abs/2607.06018)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-07-07**|**Imagined Rollouts are Kinematic, Not Dynamic: A Diagnosis of Long-Horizon World-Model Failure**|Finn Rasmus Schäfer et.al.|[2607.05966](https://arxiv.org/abs/2607.05966)|**[link](https://github.com/yanghlll/ArxivDaily-Haolin)**|
|**2026-07-06**|**Narrative World Model: Narratology-Grounded Writer Memory for Long-Form Fiction**|Mohammad Saifullah et.al.|[2607.05577](https://arxiv.org/abs/2607.05577)|**[link](https://github.com/yqhuang722/DailyArxiv)**|
|**2026-07-06**|**TypeGo: An OS Runtime for Embodied Agents**|Guojun Chen et.al.|[2607.05482](https://arxiv.org/abs/2607.05482)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-07-06**|**Deform360: A Massive Multi-view Visuotactile Dataset for Deformable World Models**|Hongyu Li et.al.|[2607.05390](https://arxiv.org/abs/2607.05390)|**[link](https://huggingface.co/datasets/brownu/deform360)**|
|**2026-07-06**|**Cortex: A Bidirectionally Aligned Embodied Agent Framework for Long-horizon Manipulation**|Jiaqi Peng et.al.|[2607.05377](https://arxiv.org/abs/2607.05377)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-07**|**Multiplayer Interactive World Models with Representation Autoencoders**|Anthony Hu et.al.|[2607.05352](https://arxiv.org/abs/2607.05352)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-06**|**MoP-JEPA: Hard-Assigned Predictor Mixtures for Stochastic JEPA World Models**|Zhi Song et.al.|[2607.05238](https://arxiv.org/abs/2607.05238)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-06**|**InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action for Compositional Generalization**|Haoxiang Ma et.al.|[2607.04988](https://arxiv.org/abs/2607.04988)|**[link](https://huggingface.co/spaces/hugging-apps/internvla-a1-5-vla-explorer)**|
|**2026-07-06**|**Designing Touch for Trauma-Informed Social Robots: A Design Space for Direct and Indirect Actuation**|Madeleine Rischer et.al.|[2607.04981](https://arxiv.org/abs/2607.04981)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-06**|**Qantara: Bridge-Flow Training for Multi-Paradigm JEPA Control**|Ruslan Rakhimov et.al.|[2607.04978](https://arxiv.org/abs/2607.04978)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-06**|**DSWAM: A Dual-System World Action Foundation Model for Fine-Grained Robot Manipulation**|Jian Zhu et.al.|[2607.04927](https://arxiv.org/abs/2607.04927)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-06**|**PRISM: Personalized Robotic Dataset Generation via Image-based Scene and Motion Synthesis**|Dogyu Ko et.al.|[2607.04880](https://arxiv.org/abs/2607.04880)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-06**|**Spatial Attention: Adapting Execution Horizons for Diffusion Policies via Observation Sensitivity**|Che-Sang Park et.al.|[2607.04739](https://arxiv.org/abs/2607.04739)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-06**|**KAM-WM: Kinematic Affordance Maps from Latent World Models for Robot Manipulation**|Xinyu Shao et.al.|[2607.04652](https://arxiv.org/abs/2607.04652)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-05**|**Mask2Real-WM: Segmentation Masks as a Sim-to-Real Bridge for Controllable Dexterous World Models**|Riccardo O. Feingold et.al.|[2607.04546](https://arxiv.org/abs/2607.04546)|**[link](https://github.com/EasonTuT/Awesome-Interactive-World-Model)**|
|**2026-07-05**|**CRISP: A Spatiotemporal Camera-Radar Backbone for Driving via Forecasting-Based World-Model Pretraining**|Jingyu Song et.al.|[2607.04541](https://arxiv.org/abs/2607.04541)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-05**|**Geographic Diversity Beats Data Volume for Cross-Domain Generalization in Zero-Label JEPA Driving World Models**|Santosh Jaiswal et.al.|[2607.04500](https://arxiv.org/abs/2607.04500)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-05**|**Operator-on-F complements value-equivalence: a planning-time diagnostic for latent world models**|Donna Vakalis et.al.|[2607.04464](https://arxiv.org/abs/2607.04464)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-05**|**Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling**|Fan Feng et.al.|[2607.04409](https://arxiv.org/abs/2607.04409)|**[link](https://github.com/Songwxuan/Embodied-AI-Paper-TopConf)**|
|**2026-07-05**|**Last-Meter Precision Navigation for UAVs: A Diffusion-Refined Aerial Visual Servoing Approach**|Yaxuan Li et.al.|[2607.04352](https://arxiv.org/abs/2607.04352)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-05**|**DynaVieW: Schema-Guided World Modeling for Understanding Hierarchical Visual Dynamics**|Silin Gao et.al.|[2607.04112](https://arxiv.org/abs/2607.04112)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-04**|**Worldscape-MoE: A Unified Mixture-of-Experts World Model for Scalable Heterogeneous Action Control**|Jianjie Fang et.al.|[2607.03964](https://arxiv.org/abs/2607.03964)|**[link](https://huggingface.co/models/EmbodiedCity/Worldscape-MoE)**|
|**2026-07-04**|**ThermoForce: A Physics-Structured Interventional World Model for Building HVAC Control**|Yifan Wang et.al.|[2607.03942](https://arxiv.org/abs/2607.03942)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-02**|**WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory**|Hanlin Wang et.al.|[2607.02517](https://arxiv.org/abs/2607.02517)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-02**|**WorldSample: Closed-loop Real-robot RL with World Modelling**|Yuquan Xue et.al.|[2607.02431](https://arxiv.org/abs/2607.02431)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-02**|**ACID: Action Consistency via Inverse Dynamics for Planning with World Models**|Gawon Seo et.al.|[2607.02403](https://arxiv.org/abs/2607.02403)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-02**|**DecompRL: Solving Harder Problems by Learning Modular Code Generation**|Juliette Decugis et.al.|[2607.02390](https://arxiv.org/abs/2607.02390)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-02**|**Hardware-Enforced Semantic Coordination for Safety-Critical Real-Time Autonomous Systems**|Uwe M. Borghoff et.al.|[2607.02376](https://arxiv.org/abs/2607.02376)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-02**|**Actuator Reality Shaping for Zero-Shot Sim-to-Real Robot Learning**|Satoshi Yamamori et.al.|[2607.02205](https://arxiv.org/abs/2607.02205)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-02**|**Bridge-WA: Predicting Where and How the World Changes for Robotic Action**|Yongjie Bai et.al.|[2607.02195](https://arxiv.org/abs/2607.02195)|**[link](https://huggingface.co/models/baiyu858/Bridge-WA-VLABench)**|
|**2026-07-02**|**Path-Measure Dynamics of Attention-Driven World Models: A Nonlocal Onsager--Machlup Approach**|Gunn Kim et.al.|[2607.02154](https://arxiv.org/abs/2607.02154)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-02**|**PWM-ArtGen: Part World Model for Articulated Object Generation**|Wentao Zheng et.al.|[2607.02045](https://arxiv.org/abs/2607.02045)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-02**|**Liquid Latent State Dynamics for Interpretable Turbofan Degradation Modeling**|Weizhi Nie et.al.|[2607.01986](https://arxiv.org/abs/2607.01986)|**[link](https://github.com/zezhishao/DailyArXiv)**|
|**2026-07-02**|**PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulation**|Peng Yun et.al.|[2607.01938](https://arxiv.org/abs/2607.01938)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-02**|**SPLC: Social Preference Learning for Crowd Robot Navigation**|Zixuan Chen et.al.|[2607.01925](https://arxiv.org/abs/2607.01925)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-02**|**Repair the Amplifier, Not the Symptom: Stable World-Model Correction for Agent Rollouts**|Xinyuan Song et.al.|[2607.01767](https://arxiv.org/abs/2607.01767)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-02**|**Path-level Hindsight Instructions for Semantic Exploration in Vision-Language Navigation**|Sung June Kim et.al.|[2607.01754](https://arxiv.org/abs/2607.01754)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-02**|**Predicting Closed-Loop Performance of Latent World Models: Offline Checkpoint Selection for MPC and Model-Based RL Under Non-Markovian Rewards in LunarLander**|Nikolai Smolyanskiy et.al.|[2607.01736](https://arxiv.org/abs/2607.01736)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-02**|**Safe and Adaptive Cloud Healing: Verifying LLM-Generated Recovery Plans with a Neural-Symbolic World Model**|Junyan Tan et.al.|[2607.01595](https://arxiv.org/abs/2607.01595)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-01**|**Certified World Models as Sensing Clocks: Drift-Aware Deadlines for Active Perception**|Hongbo Wang et.al.|[2607.01537](https://arxiv.org/abs/2607.01537)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-01**|**OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Exploration**|David Courtis et.al.|[2607.01531](https://arxiv.org/abs/2607.01531)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-01**|**BIFROST: Bridging Invariant Feature Representation for Observation-space Sim2Real Transfer**|Yunfu Deng et.al.|[2607.01410](https://arxiv.org/abs/2607.01410)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-01**|**FAR: Failure-Aware Retry for Test-Time Recovery and Continual Policy Improvement**|Haoran Hao et.al.|[2607.01111](https://arxiv.org/abs/2607.01111)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-01**|**RoboWorld: Fast and Reliable Neural Simulators for Generalist Robot Policy Evaluation**|Byeongguk Jeon et.al.|[2607.01060](https://arxiv.org/abs/2607.01060)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-01**|**Robots Ask the Way: Communication-Enabled Social Navigation**|Valentino Sacco et.al.|[2607.01044](https://arxiv.org/abs/2607.01044)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-07-01**|**Valdi: Value Diffusion World Models**|Christopher Lindenberg et.al.|[2607.00917](https://arxiv.org/abs/2607.00917)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-01**|**DeWorldSG: Depth-Aware 3D Semantic Scene Graph Generation via World-Model Priors**|Seok-Young Kim et.al.|[2607.00889](https://arxiv.org/abs/2607.00889)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-01**|**From World Models to World Action Models: A Concise Tutorial for Robotics**|Xiaoxiong Zhang et.al.|[2607.00836](https://arxiv.org/abs/2607.00836)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-01**|**ABot-M0.5: Unified Mobility-and-Manipulation World Action Model**|Ronghan Chen et.al.|[2607.00678](https://arxiv.org/abs/2607.00678)|**[link](https://github.com/amap-cvlab/ABot-Manipulation)**|
|**2026-07-01**|**Path Planning in Physically Viable World Models**|Su Ann Low et.al.|[2607.00673](https://arxiv.org/abs/2607.00673)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-01**|**AGI Maze as a Benchmark Framework for World-Modeling Agents**|Alexey Potapov et.al.|[2607.00627](https://arxiv.org/abs/2607.00627)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-01**|**B2X Networks: Joint Design of Communication and Control for Embodied Intelligence**|Yuanwei Liu et.al.|[2607.00537](https://arxiv.org/abs/2607.00537)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-01**|**From Technical Metrics to User Perception: A User Study of a Multimodal Human-Robot Interaction System for Object Detection and Grasping**|Jian Song et.al.|[2607.00530](https://arxiv.org/abs/2607.00530)|**[link](https://github.com/liliu-avril/Awesome-Segment-Anything)**|
|**2026-07-01**|**Multi-scale Mixture of World Models for Embodied Agents in Evolving Environments**|Jinwoo Jang et.al.|[2607.00457](https://arxiv.org/abs/2607.00457)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-07-01**|**Evolving Intelligent Complex Systems via Intellicise Networks: Architecture, Technologies, and Pathways**|Ping Zhang et.al.|[2607.00316](https://arxiv.org/abs/2607.00316)|**[link](https://github.com/RLCL-EIT/robotics_arxiv_daily)**|
|**2026-07-01**|**RetailSMV: Exocentric vs. Egocentric Adaptation of Foundation Video World Models in Retail**|Amirreza Rouhi et.al.|[2607.00310](https://arxiv.org/abs/2607.00310)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-30**|**Testing Frontier Large Language Models' Physics Literacy in Parallel Physical Worlds**|Dong Zhang et.al.|[2607.00276](https://arxiv.org/abs/2607.00276)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-30**|**EgoSafetyBench: A Diagnostic Egocentric Video Benchmark for Evaluating Embodied VLMs as Runtime Safety Guards**|Siddhant Panpatil et.al.|[2607.00218](https://arxiv.org/abs/2607.00218)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-30**|**VOCA: Visual Odometry with Codec Awareness**|Nouri Alexander Hilscher et.al.|[2607.00189](https://arxiv.org/abs/2607.00189)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-30**|**3D Point World Models: Point Completion Enables More Accurate Dynamics Learning**|Skand Peri et.al.|[2607.00148](https://arxiv.org/abs/2607.00148)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-30**|**Stop Pretending Social Robots Are Inevitable**|Serge Thill et.al.|[2607.00142](https://arxiv.org/abs/2607.00142)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-30**|**DVG-WM: Disentangled Video Generation Enables Efficient Embodied World Model for Robotic Manipulation**|Ziyu Shan et.al.|[2606.32028](https://arxiv.org/abs/2606.32028)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-30**|**Freeform Preference Learning for Robotic Manipulation**|Marcel Torne et.al.|[2606.32027](https://arxiv.org/abs/2606.32027)|**[link](https://github.com/wonderNefelibata/Awesome-LRM-Safety)**|
|**2026-06-30**|**AdaJEPA: An Adaptive Latent World Model**|Ying Wang et.al.|[2606.32026](https://arxiv.org/abs/2606.32026)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-30**|**MECoBench: A Systematic Study of Multimodal Agent Collaboration in Embodied Environments**|Qingyun Liu et.al.|[2606.31966](https://arxiv.org/abs/2606.31966)|**[link](https://github.com/xianshang33/llm-paper-daily)**|
|**2026-06-30**|**Adapting Generalist Robot Policies with Semantic Reinforcement Learning**|Jagdeep Singh Bhatia et.al.|[2606.31958](https://arxiv.org/abs/2606.31958)|**[link](https://github.com/dhkim-furiosa/daily-ai-robotics-papers)**|
|**2026-06-30**|**MVP-Nav: Multi-layer Value Map Planner Navigator**|Wenyuan Xie et.al.|[2606.31919](https://arxiv.org/abs/2606.31919)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-30**|**RoboTacDex: A Dexterous Visual-Tactile-Action Dataset for Humanoid Manipulation**|Xinyi Wang et.al.|[2606.31836](https://arxiv.org/abs/2606.31836)|**[link](https://github.com/vergilshawn/Awesome-Humanoid-Robot-Learning)**|
|**2026-06-30**|**MemLearner: Learning to Query Context memory for Video World Models**|Jiwen Yu et.al.|[2606.31734](https://arxiv.org/abs/2606.31734)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-30**|**ScratchWorld: Evaluating If World Models Compute Executable Consequences**|Yufeng Lin et.al.|[2606.31689](https://arxiv.org/abs/2606.31689)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-30**|**HABIT: Human-Aware Behavior and Interaction Training Dataset for Robot Manipulation**|Jaehwi Song et.al.|[2606.31682](https://arxiv.org/abs/2606.31682)|**[link](https://huggingface.co/datasets/configint/HABIT)**|
|**2026-06-30**|**WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models**|Ting-Bing Xu et.al.|[2606.31672](https://arxiv.org/abs/2606.31672)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-30**|**Ask the World Before Acting: Budgeted Environment Probing for World-Model Calibration**|Xinyuan Song et.al.|[2606.31422](https://arxiv.org/abs/2606.31422)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-30**|**World-Model Collapse as a Phase Transition**|Xinyuan Song et.al.|[2606.31399](https://arxiv.org/abs/2606.31399)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-30**|**One Video, One World: Turning Monocular Video into Physical 4D Scenes**|Junhao Chen et.al.|[2606.31388](https://arxiv.org/abs/2606.31388)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-30**|**Revisiting Parameter Redundancy in Vision-Language-Action Models: Insights from VLM-to-VLA Adaptation**|Fengnian Zhang et.al.|[2606.31382](https://arxiv.org/abs/2606.31382)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-30**|**Delta-JEPA: Learning Action-Sensitive World Models via Latent Difference Decoding**|Zhenghao Zhang et.al.|[2606.31232](https://arxiv.org/abs/2606.31232)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-30**|**ForgeDrive: Bidirectional Cross-Conditioning for Unified Visual-Action Generation in Autonomous Driving**|Xuchang Zhong et.al.|[2606.31226](https://arxiv.org/abs/2606.31226)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-30**|**Long-term Traffic Simulation via Structured Autoregressive Modeling**|Lingyu Xiao et.al.|[2606.31209](https://arxiv.org/abs/2606.31209)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-30**|**LLM-Powered Interactive Robotic Action Synthesis from Multimodal Speech, Gestures, and Music**|Snehasis Banerjee et.al.|[2606.31158](https://arxiv.org/abs/2606.31158)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-30**|**ELASTIC: Efficiently Learning to Adaptively Scale Test-Time Compute for Generative Control Policies**|Andrew Zou Li et.al.|[2606.31132](https://arxiv.org/abs/2606.31132)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-29**|**Self-Evolving World Models for LLM Agent Planning**|Xuan Zhang et.al.|[2606.30639](https://arxiv.org/abs/2606.30639)|**[link](https://github.com/xianshang33/llm-paper-daily)**|
|**2026-06-29**|**Towards World Model-Empowered Integrated Sensing, Communication, and Decision for Complex Unmanned Systems**|Xue Han et.al.|[2606.30568](https://arxiv.org/abs/2606.30568)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-29**|**Training Vision-Language-Action Models with Dense Embodied Chain-of-Thought Supervision**|Haoyang Li et.al.|[2606.30552](https://arxiv.org/abs/2606.30552)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-29**|**OWMDrive: Causality-Aware End-to-End Autonomous Driving via 4D Occupancy World Model**|Junjie Cheng et.al.|[2606.30421](https://arxiv.org/abs/2606.30421)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-29**|**Chronos: A Physics-Informed Full-History Framework for Non-Markovian Long-Horizon Manipulation**|Yulin Zhou et.al.|[2606.30318](https://arxiv.org/abs/2606.30318)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-29**|**DreamForge-World 0.1 Preview: A Low-Compute Real-Time Controllable World Model**|Daniyel Ayupov et.al.|[2606.30292](https://arxiv.org/abs/2606.30292)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-29**|**X-Morph: Human Motion Priors for Scalable Robot Learning Across Morphologies**|Ritwik Sharma et.al.|[2606.30290](https://arxiv.org/abs/2606.30290)|**[link](https://github.com/Foruck/Awesome-Human-Motion)**|
|**2026-06-29**|**Automating the Design of Embodied AgentArchitectures**|Jian Zhou et.al.|[2606.30111](https://arxiv.org/abs/2606.30111)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-29**|**SIR: Structured Image Representations for Explainable Robot Learning**|Paul Mattes et.al.|[2606.30101](https://arxiv.org/abs/2606.30101)|**[link](https://github.com/Ponkux/DailyArXiv-cp)**|
|**2026-06-29**|**REPAIR-Bench: A Benchmark for Robot Error Perception And Interaction Recovery**|Giuliano Pioldi et.al.|[2606.29937](https://arxiv.org/abs/2606.29937)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-29**|**Pondering the Way: Spatial-perceiving World Action Model for Embodied Navigation**|Hong Chen et.al.|[2606.29908](https://arxiv.org/abs/2606.29908)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-29**|**Critical Interval MSE: Toward Reliable Offline Validation for Robot Manipulation Policies**|Haoxu Huang et.al.|[2606.29898](https://arxiv.org/abs/2606.29898)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-29**|**LWDrive: Layer-Wise World-Model-Guided Vision-Language Model Planning for Autonomous Driving**|Chen Yang et.al.|[2606.29879](https://arxiv.org/abs/2606.29879)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-29**|**STEAM: Self-Supervised Temporal Ensemble Advantage Modeling for Real-World Robot Learning**|Zhihao Liu et.al.|[2606.29834](https://arxiv.org/abs/2606.29834)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-29**|**The CRISTAL Method: Neurosymbolic analysis from AI-synthesized world models**|Rafael Kaufmann et.al.|[2606.29799](https://arxiv.org/abs/2606.29799)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-29**|**HERO: Improving the Reliability and Sensitivity of Generative Model Evaluation Using Historical Data**|Xinrui Ruan et.al.|[2606.29784](https://arxiv.org/abs/2606.29784)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-28**|**CORE: Common Outcome Regularities from Action-Free Visual Demonstrations for Robot Manipulation**|Juyi Sheng et.al.|[2606.29517](https://arxiv.org/abs/2606.29517)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-28**|**Learning Transferable Dynamics Priors from Action to World Modeling**|Ze Huang et.al.|[2606.29501](https://arxiv.org/abs/2606.29501)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-28**|**Cognitive World Models for Process-Level Social Influence Evaluation**|Minghui Ma et.al.|[2606.29495](https://arxiv.org/abs/2606.29495)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-28**|**Prototype Latent World Model Replay for Class-Incremental Learning**|Weizhi Nie et.al.|[2606.29465](https://arxiv.org/abs/2606.29465)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-25**|**World Action Models Enable Continual Imitation Learning with Recurrent Generative Replays**|Manish Kumar Govind et.al.|[2606.27374](https://arxiv.org/abs/2606.27374)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-25**|**PhysiFormer: Learning to Simulate Mechanics in World Space**|Yiming Chen et.al.|[2606.27364](https://arxiv.org/abs/2606.27364)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-25**|**Continual Robot Policy Learning via Variational Neural Dynamics**|Jiaxu Xing et.al.|[2606.27353](https://arxiv.org/abs/2606.27353)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-25**|**Hallucination in World Models is Predictable and Preventable**|Nicklas Hansen et.al.|[2606.27326](https://arxiv.org/abs/2606.27326)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-25**|**Not All Actions Are Equal: Rethinking Conditioning for Dexterous World Model**|Zizhao Yuan et.al.|[2606.27325](https://arxiv.org/abs/2606.27325)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-25**|**EO-WM: A Physically Informed World Model for Probabilistic Earth Observation Forecasting**|Junwei Luo et.al.|[2606.27277](https://arxiv.org/abs/2606.27277)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-25**|**Advancing Omnimodal Embodied Agents from Isolated Skills to Everyday Physical Autonomy**|Junhao Shi et.al.|[2606.27251](https://arxiv.org/abs/2606.27251)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-25**|**A Generalization Theory for JEPA-Based World Models**|Jingyi Cui et.al.|[2606.27014](https://arxiv.org/abs/2606.27014)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-25**|**Einstein World Models**|Munachiso Samuel Nwadike et.al.|[2606.26969](https://arxiv.org/abs/2606.26969)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-25**|**Look-Before-Move: Narrative-Grounded World Visual Attention in Dynamic 3D Story Worlds**|Jiaming Bian et.al.|[2606.26964](https://arxiv.org/abs/2606.26964)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-25**|**Risk-Aware Selective Multimodal Driver Monitoring with Driver-State World Modeling**|Daosheng Qiu et.al.|[2606.26922](https://arxiv.org/abs/2606.26922)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-25**|**SSI-Policy: Learning Structured Scene Interfaces for Vision-Language Robotic Manipulation**|Kaijun Wang et.al.|[2606.26800](https://arxiv.org/abs/2606.26800)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-25**|**LithoDreamer: A Physics-Informed World Model for Multi-Stage Computational Lithography**|Yuqi Jiang et.al.|[2606.26713](https://arxiv.org/abs/2606.26713)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-25**|**PhysEditWorld: A Large-Scale Dataset Toward Physics-Editable World Models**|Bin Hu et.al.|[2606.26694](https://arxiv.org/abs/2606.26694)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-25**|**Inference-Time Robot Behavior Steering through Physically-Aware Reconfiguration of Task-Structure**|Yiyuan Pan et.al.|[2606.26588](https://arxiv.org/abs/2606.26588)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-24**|**Neural Voxel Dynamics: Learning Implicit 3D Physics via Volumetric Feature Advection**|Zican Wang et.al.|[2606.26410](https://arxiv.org/abs/2606.26410)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-24**|**Charting the Growth of Social-Physical HRI (spHRI): A Systematic Review Pipeline Augmented by Small Language Models**|Mayumi Mohan et.al.|[2606.26382](https://arxiv.org/abs/2606.26382)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-24**|**KRVF: A Source-Aware Semantic Voxel World Representation for Edge Mobile Manipulation**|Runfeng Ling et.al.|[2606.26321](https://arxiv.org/abs/2606.26321)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-24**|**NavIsaacLab: Generating Realistic Crowd via Parallel Robot Learning for Benchmarking Human-aware Navigation**|Bingyi Xia et.al.|[2606.26265](https://arxiv.org/abs/2606.26265)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-24**|**Fast LeWorldModel**|Yuntian Gao et.al.|[2606.26217](https://arxiv.org/abs/2606.26217)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-24**|**Learning Action Priors for Cross-embodiment Robot Manipulation**|Dong Jing et.al.|[2606.26095](https://arxiv.org/abs/2606.26095)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-24**|**ForceBand: Learning Forceful Manipulation with sEMG**|Botao He et.al.|[2606.26093](https://arxiv.org/abs/2606.26093)|**[link](https://github.com/InsomaniacElf/sg-tamil-tts-resources-)**|
|**2026-06-24**|**The Unfireable Safety Kernel: Execution-Time AI Alignment for AI Agents and Other Escapable AI Systems**|Seth Dobrin et.al.|[2606.26057](https://arxiv.org/abs/2606.26057)|**[link](https://github.com/Trustworthy-AI-Group/Adversarial_Examples_Papers)**|
|**2026-06-24**|**In-Context World Modeling for Robotic Control**|Siyin Wang et.al.|[2606.26025](https://arxiv.org/abs/2606.26025)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-24**|**USS: Unified Spatial-Semantic Prompts for Embodied Visual Tracking with Latent Dynamics Learning**|Yuchen Xie et.al.|[2606.25880](https://arxiv.org/abs/2606.25880)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-24**|**1000 Rallies: An Event-Camera Dataset and Real-Time Learned Ball-State Estimation for Robotic Table Tennis**|Raphaela Kreiser et.al.|[2606.25620](https://arxiv.org/abs/2606.25620)|**[link](https://github.com/Blake-Jiang/ad-arxiv-daily)**|
|**2026-06-24**|**One Body, Two Minds: Variable Autonomy Approach for a Co-embodied Robotic Hand**|Piotr Koczy et.al.|[2606.25575](https://arxiv.org/abs/2606.25575)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-24**|**Beyond One-Size-Fits-All: Diagnosis-Driven Online Reinforcement Learning with Offline Priors**|Guozheng Ma et.al.|[2606.25527](https://arxiv.org/abs/2606.25527)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-24**|**SAGE-Nav: Leveraging LLM Planning and Alignment Fusion for Hierarchical Scene Graph-Guided Navigation**|Hao Su et.al.|[2606.25497](https://arxiv.org/abs/2606.25497)|**[link](https://github.com/JiaHongZ/embodied_intelligence_paper)**|
|**2026-06-24**|**Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models**|Kaiwen Zheng et.al.|[2606.25473](https://arxiv.org/abs/2606.25473)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-24**|**Beyond Next-Observation Prediction: Agent-Authored World Modeling for Sequential Decision Making**|Guangfeng Cai et.al.|[2606.25421](https://arxiv.org/abs/2606.25421)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-24**|**Hypergraph Normal World Models for Logical Visual Anomaly Detection**|Weizhi Nie et.al.|[2606.25368](https://arxiv.org/abs/2606.25368)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-23**|**ARTOO-DARTU: Studying AR-HRC With AR Obstruction Mitigation During a Warehouse Task**|Christian Fronk et.al.|[2606.25202](https://arxiv.org/abs/2606.25202)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-23**|**Learning Perceptive Platform Adaptive Locomotion Controllers for Quadrupedal Robots**|David Rytz et.al.|[2606.25179](https://arxiv.org/abs/2606.25179)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-23**|**fARfetch: Enabling Collocated AR-HRC in Large Visually Diverse Environments with VLM-Driven AR Content Adaptation**|Christian Fronk et.al.|[2606.25162](https://arxiv.org/abs/2606.25162)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-23**|**Toward Low-Latency Vision-Language Models with Doubly-Correct Predictions in Egocentric Visual Understanding**|Qitong Wang et.al.|[2606.25160](https://arxiv.org/abs/2606.25160)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-23**|**World Models in Pieces: Structural Certification for General Agents**|Yikai Lu et.al.|[2606.24842](https://arxiv.org/abs/2606.24842)|**[link](https://github.com/tmgthb/Autonomous-Agents)**|
|**2026-06-23**|**World Value Models for Robotic Manipulation**|Zhihao Wang et.al.|[2606.24742](https://arxiv.org/abs/2606.24742)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-23**|**Human-Robot Shared Control for Humanized End-Effector Teleoperation**|Batool Ibrahim et.al.|[2606.24629](https://arxiv.org/abs/2606.24629)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-23**|**ArtiTwinSplat: Interactable Digital Twin Reconstruction via Gaussian Splatting from RGB-D videos**|Pranjal Mishra et.al.|[2606.24628](https://arxiv.org/abs/2606.24628)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-23**|**Qwen-AgentWorld: Language World Models for General Agents**|Yuxin Zuo et.al.|[2606.24597](https://arxiv.org/abs/2606.24597)|**[link](https://huggingface.co/models/Qwen/Qwen-AgentWorld-35B-A3B)**|
|**2026-06-23**|**VistaRef: Boosting Visual Spatial Orientation Awareness for Pointing-to-Object Detection**|Ling Li et.al.|[2606.24498](https://arxiv.org/abs/2606.24498)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-23**|**WiWorld-RealData: A Real-World Multi-Modal Dataset for 6G Wireless World Models**|Yinyin Jiao et.al.|[2606.24476](https://arxiv.org/abs/2606.24476)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-23**|**Supervise What Survives: Geometry-Guided VLA Adaptation from Synthetic Robot Videos**|Danze Chen et.al.|[2606.24448](https://arxiv.org/abs/2606.24448)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-23**|**Agentic AI for Bilevel Long-Term Optimization of Policy-Driven Physical Layer Systems**|Bingnan Xiao et.al.|[2606.24416](https://arxiv.org/abs/2606.24416)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-23**|**Trimming the Long-Tail of Visual World Modeling Evaluation**|Bingxuan Li et.al.|[2606.24256](https://arxiv.org/abs/2606.24256)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-23**|**AutoSpec: Safety Rule Evolution for LLM Agents via Inductive Logic Programming**|Pingchuan Ma et.al.|[2606.24245](https://arxiv.org/abs/2606.24245)|**[link](https://github.com/tmgthb/Autonomous-Agents)**|
|**2026-06-23**|**Grounding Generative Policies in Physics: Optimization-Guided Diffusion for Robot Control**|Sabrina Bodmer et.al.|[2606.24208](https://arxiv.org/abs/2606.24208)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-23**|**Autonomous Video Generation with Counterfactual Controllability for Self-Evolving World Models**|Xin Wang et.al.|[2606.24152](https://arxiv.org/abs/2606.24152)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-23**|**NavWM: A Unified Navigation World Model for Foresight-Driven Planning**|Yanghong Mei et.al.|[2606.24101](https://arxiv.org/abs/2606.24101)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-23**|**DynaWM: Dynamics-Aware Distillation with World Model and Momentum Targets for Smooth Locomotion over Continuous Stairs**|Haidong Hou et.al.|[2606.24089](https://arxiv.org/abs/2606.24089)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-23**|**SPACE: Enabling Learning from Cross-Robot Data Toward Generalist Policies**|Haeone Lee et.al.|[2606.24049](https://arxiv.org/abs/2606.24049)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-22**|**Critique of Agent Model**|Eric Xing et.al.|[2606.23991](https://arxiv.org/abs/2606.23991)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-22**|**LaST-HD: Learning Latent Physical Reasoning from Scalable Human Data for Robot Manipulation**|Jiaming Liu et.al.|[2606.23685](https://arxiv.org/abs/2606.23685)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-22**|**RECALL: Recovery Experience Collection for Active Lifelong Learning in Vision-Language-Action Models**|Ulas Berk Karli et.al.|[2606.23617](https://arxiv.org/abs/2606.23617)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-22**|**HoloAgent-0: A Unified Embodied Agent Framework with 3D Spatial Memory**|Xiaolin Zhou et.al.|[2606.23565](https://arxiv.org/abs/2606.23565)|**[link](https://github.com/HorizonRobotics/HoloAgent)**|
|**2026-06-22**|**Equilibrium World Models**|Simon Scheidegger et.al.|[2606.23463](https://arxiv.org/abs/2606.23463)|**[link](https://github.com/CQUwilliam/quant-paper-daily)**|
|**2026-06-22**|**MeGAS: Thermomechanical Dynamic Gaussian Splatting for Thermophysical Scene Editing**|Zesong Yang et.al.|[2606.23455](https://arxiv.org/abs/2606.23455)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-22**|**SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotors**|Pratyaksh Rao et.al.|[2606.23444](https://arxiv.org/abs/2606.23444)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-22**|**TSD: A Physics-Inspired Trajectory Saliency Detector for Efficient Imitation Learning**|Yiming Zhao et.al.|[2606.23371](https://arxiv.org/abs/2606.23371)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-22**|**When Robots Rate Their Own Interactions: Engagement Validity and the Strangeness Failure**|Victor Lockwood et.al.|[2606.23339](https://arxiv.org/abs/2606.23339)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-22**|**From Pixels to Concepts: Growing Rich 3D Semantic Scene Graph Forests utilizing Foundation Models**|David Oberacker et.al.|[2606.23312](https://arxiv.org/abs/2606.23312)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-22**|**IOI: Decoupling Kinematics and Physics for Interactive World Models**|Chengyu Bai et.al.|[2606.23296](https://arxiv.org/abs/2606.23296)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-22**|**Causal Reward World Models: Zero-shot Reward Design for Automated Skill Generation**|Yang Yang et.al.|[2606.23280](https://arxiv.org/abs/2606.23280)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-22**|**Compression and Retrieval: Implicit Memory Retrieval for Video World Models**|Zhan Peng et.al.|[2606.23105](https://arxiv.org/abs/2606.23105)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-22**|**Flow as Flow: Modeling Robot Velocity Fields as Probability Velocity Fields for Flow-Based Object Manipulation**|Koki Seno et.al.|[2606.23090](https://arxiv.org/abs/2606.23090)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-22**|**Foresight: Failure Detection for Long-Horizon Robotic Manipulation with Action-Conditioned World Model Latents**|Haoran Zhang et.al.|[2606.23085](https://arxiv.org/abs/2606.23085)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-22**|**AdaReP:Adaptive Re-Planning under Model Mismatch for Neural World-Model Predictive Control**|Yutian Cheng et.al.|[2606.23079](https://arxiv.org/abs/2606.23079)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-22**|**Attacking the Trusted Imagination: Oracle-Level Integrity Attacks on Imagine-then-Act World Models**|Linghan Chen et.al.|[2606.22966](https://arxiv.org/abs/2606.22966)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-22**|**Each Judge Its Own Yardstick: Discovering Per-VLM Taxonomies for Physical Video Evaluation**|Yu Cao et.al.|[2606.22918](https://arxiv.org/abs/2606.22918)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-22**|**Cloak: Zero-Shot Cross-Embodiment Manipulation by Masking the End-Effector from the VLA**|Michael Piseno et.al.|[2606.22836](https://arxiv.org/abs/2606.22836)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-22**|**Active Inference as the Test-Time Scaling Law for Physical AI Agents**|Omar Hashash et.al.|[2606.22813](https://arxiv.org/abs/2606.22813)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-22**|**Temporal Logic Guidance for Action-Only Diffusion Policies with World Models**|Moritz Zoellner et.al.|[2606.22729](https://arxiv.org/abs/2606.22729)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-18**|**Generating Robot Hands from Human Demonstrations**|Sha Yi et.al.|[2606.20549](https://arxiv.org/abs/2606.20549)|**[link](https://github.com/YanjieZe/Paper-List)**|
|**2026-06-18**|**Current World Models Lack a Persistent State Core**|Jinpeng Lu et.al.|[2606.20545](https://arxiv.org/abs/2606.20545)|**[link](https://huggingface.co/spaces/WRBench/wrbench-leaderboard)**|
|**2026-06-18**|**Execution-State Capsules: Graph-Bound Execution-State Checkpoint and Restore for Low-Latency, Small-Batch, On-Device Physical-AI Serving**|Liang Su et.al.|[2606.20537](https://arxiv.org/abs/2606.20537)|**[link](https://github.com/flashrt-project/FlashRT)**|
|**2026-06-18**|**CoLI: A Reproducible Platform for Continuum Robot Learning via Monolithic 3D Printing and Isomorphic Teleoperation**|Ziyuan Tang et.al.|[2606.20389](https://arxiv.org/abs/2606.20389)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-18**|**Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think**|Gia-Binh Nguyen et.al.|[2606.20246](https://arxiv.org/abs/2606.20246)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-18**|**Robust Assembly State Reasoning from Action Recognition for Human-Robot Collaboration**|James Fant-Male et.al.|[2606.20150](https://arxiv.org/abs/2606.20150)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-18**|**Sensorimotor World Models: Perception for Action via Inverse Dynamics**|Petr Ivashkov et.al.|[2606.20104](https://arxiv.org/abs/2606.20104)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-18**|**Holo-World: Unified Camera, Object and Weather Control for Video World Model**|Xiangchen Yin et.al.|[2606.20083](https://arxiv.org/abs/2606.20083)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-18**|**See-and-Reach: Precise Vision-Language Navigation for UAVs within the Field of View**|Fanfu Xue et.al.|[2606.20045](https://arxiv.org/abs/2606.20045)|**[link](https://github.com/longxiang-ai/awesome-gaussians)**|
|**2026-06-18**|**Reward as An Agent for Embodied World Models**|Pu Li et.al.|[2606.19990](https://arxiv.org/abs/2606.19990)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-18**|**ENPIRE: Agentic Robot Policy Self-Improvement in the Real World**|Wenli Xiao et.al.|[2606.19980](https://arxiv.org/abs/2606.19980)|**[link](https://github.com/YanjieZe/Paper-List)**|
|**2026-06-18**|**Advancing DialNav through Automatic Embodied Dialog Augmentation**|Leekyeung Han et.al.|[2606.19948](https://arxiv.org/abs/2606.19948)|**[link](https://github.com/tmgthb/Autonomous-Agents)**|
|**2026-06-18**|**SWAP: Symmetric Equivariant World-Model for Agile Robot Parkour**|Kaixin Lan et.al.|[2606.19928](https://arxiv.org/abs/2606.19928)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-18**|**Co-policy: Responsive Human-Robot Co-Creation for Musical Performances**|Xuetao Li et.al.|[2606.19914](https://arxiv.org/abs/2606.19914)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-18**|**SurgVista: Long-Horizon Surgical World Modeling with Plausible Instrument-Tissue Dynamics**|Wentao Pan et.al.|[2606.19889](https://arxiv.org/abs/2606.19889)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-18**|**Start Right, Arrive Right: Asynchronous Execution via Initial Noise Selection**|Trong-Bao Ho et.al.|[2606.19774](https://arxiv.org/abs/2606.19774)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-18**|**Data Standards for Humanoid Robotics: The Missing Infrastructure for Physical AI**|Shaoshan Liu et.al.|[2606.19769](https://arxiv.org/abs/2606.19769)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-18**|**Bidirectional Tutoring for Developmental Motor Learning in Robots: Co-Developed Interaction Dynamics Support Stable Learning**|Rui Fukushima et.al.|[2606.19728](https://arxiv.org/abs/2606.19728)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-17**|**One Demo is Worth a Thousand Trajectories: Action-View Augmentation for Visuomotor Policies**|Chuer Pan et.al.|[2606.19586](https://arxiv.org/abs/2606.19586)|**[link](https://github.com/zezhishao/DailyArXiv)**|
|**2026-06-17**|**ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?**|Yuyang Zhang et.al.|[2606.19531](https://arxiv.org/abs/2606.19531)|**[link](https://huggingface.co/models/yuyangalin/ImageWAM-FLUX.2-4B-RoboTwin)**|
|**2026-06-17**|**Seeing Through Occlusion: Deterministic Arm Kinematic Correction for Robot Teleoperation**|Thomas M. Kwok et.al.|[2606.19240](https://arxiv.org/abs/2606.19240)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-17**|**Monocular 3D Occupancy Perception for Robots on Sidewalks via Hybrid 2D-3D Learning**|Yukai Ma et.al.|[2606.19122](https://arxiv.org/abs/2606.19122)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-17**|**Lifecycle-Aware Dynamic Analysis for Secure ML Model Execution**|Gabriele Digregorio et.al.|[2606.19023](https://arxiv.org/abs/2606.19023)|**[link](https://github.com/Trustworthy-AI-Group/Adversarial_Examples_Papers)**|
|**2026-06-17**|**Mem-World: Memory-Augmented Action-Conditioned World Models for Persistent Robot Manipulation**|Zirui Zheng et.al.|[2606.18960](https://arxiv.org/abs/2606.18960)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-17**|**TactSpace: Learning a Physics-enriched Shared Latent Space for Tactile Sim-to-Real Transfer**|Arunim Joarder et.al.|[2606.18959](https://arxiv.org/abs/2606.18959)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-17**|**Motion-Focused Latent Action Enables Cross-Embodiment VLA Training from Human EgoVideos**|Runze Xu et.al.|[2606.18955](https://arxiv.org/abs/2606.18955)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-17**|**Physics-IQ Verified**|Tim Rädsch et.al.|[2606.18943](https://arxiv.org/abs/2606.18943)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-17**|**WorldLines: Benchmarking and Modeling Long-Horizon Stateful Embodied Agents**|Yehang Zhang et.al.|[2606.18847](https://arxiv.org/abs/2606.18847)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-17**|**Improving Human-Robot Teamwork in Urban Search and Rescue Through Episodic Memory of Prior Collaboration**|Taewoon Kim et.al.|[2606.18836](https://arxiv.org/abs/2606.18836)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-17**|**DreamReg: Belief-Driven World Model for 2D-3D Ultrasound Registration**|Luoyao Kang et.al.|[2606.18825](https://arxiv.org/abs/2606.18825)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-17**|**Generating Natural and Expressive Robot Gestures through Iterative Reinforcement Learning with Human Feedback using LLMs**|Chris Lee et.al.|[2606.18747](https://arxiv.org/abs/2606.18747)|**[link](https://github.com/liutaocode/TTS-arxiv-daily)**|
|**2026-06-17**|**Stealthy World Model Manipulation via Data Poisoning**|Yibin Hu et.al.|[2606.18697](https://arxiv.org/abs/2606.18697)|**[link](https://github.com/Trustworthy-AI-Group/Adversarial_Examples_Papers)**|
|**2026-06-17**|**Dual-Channel Grounded World Modeling (DCGWM): Structural Prevention of Objective Interference Collapse via Heterogeneous External Grounding with Inward-Only Gradient Flow**|Akshay Hazare et.al.|[2606.18688](https://arxiv.org/abs/2606.18688)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-17**|**SC3-Eval: Evaluating Robot Foundation Models via Self-Consistent Video Generation**|Wei-Cheng Tseng et.al.|[2606.18610](https://arxiv.org/abs/2606.18610)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-17**|**DREAM-Chunk: Reactive Action Chunking with Latent World Model**|Wenxi Chen et.al.|[2606.18589](https://arxiv.org/abs/2606.18589)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-16**|**Short-Duration Gamma-ray Burst and Afterglow Rates in the Rubin and Roman Era**|Tzvetelina Dimitrova et.al.|[2606.18468](https://arxiv.org/abs/2606.18468)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-16**|**PAIWorld: A 3D-Consistent World Foundation Model for Robotic Manipulation**|Yuhang Huang et.al.|[2606.18375](https://arxiv.org/abs/2606.18375)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-16**|**Guava: An Effective and Universal Harness for Embodied Manipulation**|Haowen Liu et.al.|[2606.18363](https://arxiv.org/abs/2606.18363)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-16**|**Future Dynamic 3D Reconstruction: A 3D World Model with Disentangled Ego-Motion**|Nils Morbitzer et.al.|[2606.18250](https://arxiv.org/abs/2606.18250)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-16**|**Visual Verification Enables Inference-time Steering and Autonomous Policy Improvement**|Mingtong Zhang et.al.|[2606.18247](https://arxiv.org/abs/2606.18247)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-16**|**EvolveNav: Proactive Preflection and Self-Evolving Memory for Zero-Shot Object Goal Navigation**|Qi Chai et.al.|[2606.18235](https://arxiv.org/abs/2606.18235)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-16**|**Looped World Models**|Hongyuan Adam Lu et.al.|[2606.18208](https://arxiv.org/abs/2606.18208)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-06-16**|**EgoCS-400K: An Egocentric Gameplay Dataset for World Models**|Rongjin Guo et.al.|[2606.18180](https://arxiv.org/abs/2606.18180)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-16**|**Memory as a Wasting Asset: Pricing Flash Endurance for Embodied Agents, and the Limits of Doing So**|Josef Liyanjun Chen et.al.|[2606.18144](https://arxiv.org/abs/2606.18144)|**[link](https://huggingface.co/spaces/Kaikaku/erase-cycle-demo)**|
|**2026-06-16**|**PearlVLA: Progressive Embodied Action-Plan Refinement in Latent Space**|Bochen Yang et.al.|[2606.17924](https://arxiv.org/abs/2606.17924)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-16**|**WAM-RL: World-Action Model Reinforcement Learning with Reconstruction Rewards and Online Video SFT**|Zezhong Qian et.al.|[2606.17906](https://arxiv.org/abs/2606.17906)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-16**|**Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models**|Haoqi Yuan et.al.|[2606.17846](https://arxiv.org/abs/2606.17846)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-16**|**From Ad Hoc Pilots to Repeatable Patterns: Structuring Drone Collaboration in Emergency Services with DroneLets**|Dzmitry Katsiuba et.al.|[2606.17839](https://arxiv.org/abs/2606.17839)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-16**|**MaineCoon: Pursuing A Real-Time Audio-Visual Social World Model**|Lichen Bai et.al.|[2606.17800](https://arxiv.org/abs/2606.17800)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-16**|**ActWorld: From Explorable to Interactive World Model via Action-Aware Memory**|Zhexiao Xiong et.al.|[2606.17730](https://arxiv.org/abs/2606.17730)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-16**|**ERQA-Plus: A Diagnostic Benchmark for Reasoning in Embodied AI**|Hong Yang et.al.|[2606.17639](https://arxiv.org/abs/2606.17639)|**[link](https://github.com/tmgthb/Autonomous-Agents)**|
|**2026-06-16**|**OmniDrive: An LLM-Choreographed Multi-Agent World Model with Unified Latent Co-Compression for Multi-View Driving Video Generation**|Zijie Meng et.al.|[2606.17536](https://arxiv.org/abs/2606.17536)|**[link](https://github.com/Thinklab-SJTU/Awesome-LLM4AD)**|
|**2026-06-16**|**GASE: Gaussian Splatting-Based Automated System for Reconstructing Embodied-Simulation Environments**|Jiawei Zhang et.al.|[2606.17520](https://arxiv.org/abs/2606.17520)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-16**|**MagicSim: A Unified Infrastructure for Executable Embodied Interaction**|Haoran Lu et.al.|[2606.17511](https://arxiv.org/abs/2606.17511)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-16**|**When Robots Sleep: Offline Skill Consolidation for Shared-Policy Robot Learning**|Nethmi Jayasinghe et.al.|[2606.17493](https://arxiv.org/abs/2606.17493)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-16**|**DexLink Hand: A Compact, Affordable, 16-DOF Linkage-Driven Hand with Human-Like Dexterity**|Hao Wu et.al.|[2606.17418](https://arxiv.org/abs/2606.17418)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-16**|**Where Should Action Generation Begin? A Learnable Source Prior for Generative Robot Policies**|Meipo Dai et.al.|[2606.17408](https://arxiv.org/abs/2606.17408)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-16**|**NarrativeWorldBench: A Frontier-Saturated Benchmark and a Latent World Model for Long-Horizon Co-Creative Audio Drama**|Logan Mann et.al.|[2606.17391](https://arxiv.org/abs/2606.17391)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-15**|**Geometric Action Model for Robot Policy Learning**|Jisang Han et.al.|[2606.17046](https://arxiv.org/abs/2606.17046)|**[link](https://github.com/DravenALG/awesome-vla-wam)**|
|**2026-06-15**|**Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation**|Jie Zhang et.al.|[2606.17030](https://arxiv.org/abs/2606.17030)|**[link](https://github.com/BradyFU/Awesome-Multimodal-Large-Language-Models)**|
|**2026-06-15**|**ROVE: Unlocking Human Interventions for Humanoid Manipulation via Reinforcement Learning**|Wei Xiao et.al.|[2606.17011](https://arxiv.org/abs/2606.17011)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-15**|**DreamX-World 1.0: A General-Purpose Interactive World Model**|DreamX Team et.al.|[2606.16993](https://arxiv.org/abs/2606.16993)|**[link](https://huggingface.co/models/GD-ML/DreamX-World-5B)**|
|**2026-06-15**|**Unified Motion-Action Modeling for Heterogeneous Robot Learning**|Yunhao Cao et.al.|[2606.16917](https://arxiv.org/abs/2606.16917)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-15**|**Semantic Flip: Synthetic OOD Generation for Robust Refusal in Embodied Question Answering and Spatial Localization**|Dongbin Na et.al.|[2606.16898](https://arxiv.org/abs/2606.16898)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-15**|**ExoTraj: A General Lower-limb Exoskeleton Assistance Policy for Complex Environments**|Xiao-Yin Liu et.al.|[2606.16876](https://arxiv.org/abs/2606.16876)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-15**|**DataLadder: A Simulation-Enabled Interconversion Toolchain for the Embodied Data Pyramid**|Peidong Liu et.al.|[2606.16776](https://arxiv.org/abs/2606.16776)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-15**|**MuVAP: Multimodal Multiparty Voice Activity Projection for Turn-taking Prediction in the Wild**|Haotian Qi et.al.|[2606.16731](https://arxiv.org/abs/2606.16731)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-15**|**Medical world models: representing medical states, modelling clinical dynamics and guiding intervention policies**|Ke Liu et.al.|[2606.16721](https://arxiv.org/abs/2606.16721)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-15**|**VENOM: Versatile Embodied Network for Omni-bodied Motion tracking**|Siddharth Padmanabhan et.al.|[2606.16696](https://arxiv.org/abs/2606.16696)|**[link](https://github.com/Foruck/Awesome-Human-Motion)**|
|**2026-06-15**|**ARB4WM: An Adversarial Robustness Benchmark for World Models in Continuous Control**|Junjian Zhang et.al.|[2606.16605](https://arxiv.org/abs/2606.16605)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-15**|**WaveSync: Constrained Wavefront Optimization for Synchronized Co-Speech Gestures in Humanoid Robots**|Thang Tran Viet et.al.|[2606.16600](https://arxiv.org/abs/2606.16600)|**[link](https://github.com/Foruck/Awesome-Human-Motion)**|
|**2026-06-15**|**Can LLM Agents Infer World Models? Evidence from Agentic Automata Learning**|Reef Menaged et.al.|[2606.16576](https://arxiv.org/abs/2606.16576)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-15**|**Kairos: A Native World Model Stack for Physical AI**|Kairos Team et.al.|[2606.16533](https://arxiv.org/abs/2606.16533)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-15**|**BadWorld: Adversarial Attacks on World Models**|Linghui Shen et.al.|[2606.16519](https://arxiv.org/abs/2606.16519)|**[link](https://github.com/Trustworthy-AI-Group/Adversarial_Examples_Papers)**|
|**2026-06-15**|**Robots that Collaborate: Sequential Asymmetric Imitation for Learning Coupled Robot Policies**|Yincong Chen et.al.|[2606.16490](https://arxiv.org/abs/2606.16490)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-15**|**BRICKS-WM: Building Reusability via Interface Composition Kinetics for Structured World Models**|Shaowei Zhang et.al.|[2606.16489](https://arxiv.org/abs/2606.16489)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-15**|**HOLO-MPPI: Multi-Scenario Motion Planning via Hierarchical Policy Optimization**|Youngjae Min et.al.|[2606.16480](https://arxiv.org/abs/2606.16480)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-15**|**ART-Glove: Articulated Tactile Glove for Contact-Grounded Dexterous Interaction Capture**|Changyi Lin et.al.|[2606.16370](https://arxiv.org/abs/2606.16370)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-12**|**AgentSpec: Understanding Embodied Agent Scaffolds Through Controlled Composition**|Jixuan Chen et.al.|[2606.14674](https://arxiv.org/abs/2606.14674)|**[link](https://github.com/IAAR-Shanghai/Awesome-AI-Memory)**|
|**2026-06-12**|**EgoGuide: Egocentric Guidance for Efficient Robot-Free Demonstration Collection and Learning**|Yue Xu et.al.|[2606.14665](https://arxiv.org/abs/2606.14665)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-12**|**Whole-Body Impedance Model Predictive Control for Safe Physical Human--Robot Interaction on Floating-Base Platforms**|Yongyan Cao et.al.|[2606.14617](https://arxiv.org/abs/2606.14617)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-12**|**Impedance MPC with Disturbance Estimation for Dexterous Hand Control**|Yongyan Cao et.al.|[2606.14606](https://arxiv.org/abs/2606.14606)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-12**|**What Robots Do Matters More Than What They Look Like: Task Context Shapes Trust in Educational HRI**|Anna-Maria Velentza et.al.|[2606.14602](https://arxiv.org/abs/2606.14602)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-12**|**SIMMER: Benchmarking Latent Failures in LLM Executable Planning with a World Model**|Xiaoxin Lu et.al.|[2606.14574](https://arxiv.org/abs/2606.14574)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-12**|**ORCA: A Platform for Open-Source Dexterity Research**|Francesco Capuano et.al.|[2606.14561](https://arxiv.org/abs/2606.14561)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-12**|**Causal Object-Centric Models for Planning with Monte Carlo Tree Search**|Rodion Vakhitov et.al.|[2606.14418](https://arxiv.org/abs/2606.14418)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-12**|**Hy-Embodied-0.5-VLA: From Vision-Language-Action Models to a Real-World Robot Learning Stack**|He Zhang et.al.|[2606.14409](https://arxiv.org/abs/2606.14409)|**[link](https://huggingface.co/models/tencent/Hy-Embodied-0.5-VLA-UMI)**|
|**2026-06-12**|**The N2D Haptic Glove: A Multi-Finger Glove for 2D Directional Force Feedback for Contact Rich Manipulation**|Yao-Ting Huang et.al.|[2606.14083](https://arxiv.org/abs/2606.14083)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-12**|**ReactSim-Bench: Benchmarking Reactive Behavior World Model Simulation in Autonomous Driving**|Zhiyuan Zhang et.al.|[2606.14058](https://arxiv.org/abs/2606.14058)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-11**|**An Attention-based Model for Robust Forecasting with Missing Modality**|Zhitian Zhang et.al.|[2606.13970](https://arxiv.org/abs/2606.13970)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-11**|**ContactWorld: What Matters in Vision-Tactile World Models for Contact-Rich Manipulation**|Zhiyuan Zhang et.al.|[2606.13877](https://arxiv.org/abs/2606.13877)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-11**|**Multi-Agent Embodied Autonomous Driving: From V2X Information Exchange to Shared World Models**|Senkang Hu et.al.|[2606.13840](https://arxiv.org/abs/2606.13840)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-11**|**FlowMo-WM: A World Model with Object Momentum and Hidden Ambient Drift**|Yitao Jiang et.al.|[2606.13817](https://arxiv.org/abs/2606.13817)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-11**|**$μ_0$ : A Scalable 3D Interaction-Trace World Model**|Seungjae Lee et.al.|[2606.13769](https://arxiv.org/abs/2606.13769)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-11**|**RepWAM: World Action Modeling with Representation Visual-Action Tokenizers**|Junke Wang et.al.|[2606.13674](https://arxiv.org/abs/2606.13674)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-11**|**$\texttt{WEAVER}$ , Better, Faster, Longer: An Effective World Model for Robotic Manipulation**|Arnav Kumar Jain et.al.|[2606.13672](https://arxiv.org/abs/2606.13672)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-11**|**Reasoning as Pattern Matching: Shared Mechanisms in Human and LLM Everyday Reasoning**|Zach Studdiford et.al.|[2606.13607](https://arxiv.org/abs/2606.13607)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-11**|**SPARC: Reliable Spatial Annotations from Robot Demonstrations at Scale**|Nils Blank et.al.|[2606.13497](https://arxiv.org/abs/2606.13497)|**[link](https://github.com/wadeKeith/Awesome-Embodied-AI)**|
|**2026-06-11**|**NavWAM: A Navigation World Action Model for Goal-Conditioned Visual Navigation**|Daichi Azuma et.al.|[2606.13494](https://arxiv.org/abs/2606.13494)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-11**|**VISA: VLM-Guided Instance Semantic Auditing for 3D Occupancy World Models**|Ruiqi Xian et.al.|[2606.13460](https://arxiv.org/abs/2606.13460)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-11**|**GIVE: Grounding Human Gestures in Vision-Language-Action Models**|Pengfei Liu et.al.|[2606.13435](https://arxiv.org/abs/2606.13435)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-11**|**MoVerse: Real-Time Video World Modeling with Panoramic Gaussian Scaffold**|Yang Zhou et.al.|[2606.13376](https://arxiv.org/abs/2606.13376)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-11**|**Humor Style Drives Laughter, Topic Shapes Acceptability: Evaluating Bilingual Personal and Political Robot-Delivered AI Jokes**|Anna-Maria Velentza et.al.|[2606.13256](https://arxiv.org/abs/2606.13256)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-11**|**Embedding ISO 10218 Safety Compliance in Robots via Control Barrier Functions for Human-Robot Collaboration**|Federico Parma et.al.|[2606.13203](https://arxiv.org/abs/2606.13203)|**[link](https://github.com/wadeKeith/Awesome-Embodied-AI)**|
|**2026-06-11**|**Multi-Modal Multi-Agent Robotic Cognitive Alignment enabled by Non-Invasive Consumer Brain Computer Interfaces: A Proof of Concept Exploration**|Nataliya Kosmyna et.al.|[2606.13190](https://arxiv.org/abs/2606.13190)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-11**|**FTP-1: A Generalist Foundation Tactile Policy Across Tactile Sensors for Contact-Rich Manipulation**|Chengbo Yuan et.al.|[2606.13102](https://arxiv.org/abs/2606.13102)|**[link](https://github.com/linchangyi1/Awesome-Touch)**|
|**2026-06-11**|**Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents**|Saehun Chun et.al.|[2606.13097](https://arxiv.org/abs/2606.13097)|**[link](https://github.com/wadeKeith/Awesome-Embodied-AI)**|
|**2026-06-11**|**Scale Buys Interpolation, Structure Buys a Horizon: Certified Predictability for Equivariant World Models**|Hongbo Wang et.al.|[2606.13092](https://arxiv.org/abs/2606.13092)|**[link](https://github.com/wadeKeith/Awesome-Embodied-AI)**|
|**2026-06-11**|**EA-WM: Event-Aware World Models with Task-Specification Grounding for Long-Horizon Manipulation**|Kailin Wang et.al.|[2606.13053](https://arxiv.org/abs/2606.13053)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-11**|**Y-BotFrame: An Extensible Embodied Agent Framework for Quadruped Robot Assistants**|Luyao Zhang et.al.|[2606.13049](https://arxiv.org/abs/2606.13049)|**[link](https://github.com/wadeKeith/Awesome-Embodied-AI)**|
|**2026-06-11**|**Diffusion Transformer World-Action Model for AV Scene Prediction**|Ruslan Sharifullin et.al.|[2606.12987](https://arxiv.org/abs/2606.12987)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-11**|**EPM-JEPA: Operator-Side Experience Modulation in JEPA-Family World Models**|Vedant Pandya et.al.|[2606.12979](https://arxiv.org/abs/2606.12979)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-11**|**EmbodiSteer: Steering Embodiment-Agnostic Visuomotor Policies with Joint-Space Guidance for Zero-Shot Cross-Embodiment Deployment**|Shihefeng Wang et.al.|[2606.12965](https://arxiv.org/abs/2606.12965)|**[link](https://github.com/wadeKeith/Awesome-Embodied-AI)**|
|**2026-06-11**|**An Embodied Simulation Platform, Benchmark, and Data-Efficient Augmentation Framework for Wet-Lab Robotics**|Zhe Liu et.al.|[2606.12936](https://arxiv.org/abs/2606.12936)|**[link](https://github.com/wadeKeith/Awesome-Embodied-AI)**|
|**2026-06-10**|**World Pilot: Steering Vision-Language-Action Models with World-Action Priors**|Zefu Lin et.al.|[2606.12403](https://arxiv.org/abs/2606.12403)|**[link](https://huggingface.co/models/Chedan86/WorldPilot-LIBERO)**|
|**2026-06-10**|**DIRECT: When and Where Should You Allocate Test-Time Compute in Embodied Planners?**|Jadelynn Dao et.al.|[2606.12402](https://arxiv.org/abs/2606.12402)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-10**|**Semantically-Aware Diver Activity Recognition Framework for Effective Underwater Multi-Human-Robot Collaboration**|Sadman Sakib Enan et.al.|[2606.12374](https://arxiv.org/abs/2606.12374)|**[link](https://github.com/wonderNefelibata/Awesome-LRM-Safety)**|
|**2026-06-10**|**CHORUS: Decentralized Multi-Embodiment Collaboration with One VLA Policy**|Ria Doshi et.al.|[2606.12352](https://arxiv.org/abs/2606.12352)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-10**|**Fast-SDE: Efficient Single-Microphone Sound Source Distance Estimation in Reverberant Environments**|Jiang Wang et.al.|[2606.12339](https://arxiv.org/abs/2606.12339)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-10**|**Slots, Transitions, Loops: Learning Composable World Models for ARC**|Gege Gao et.al.|[2606.12316](https://arxiv.org/abs/2606.12316)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-10**|**Making Foresight Actionable: Repurposing Representation Alignment in World Action Models**|Lu Qiu et.al.|[2606.12217](https://arxiv.org/abs/2606.12217)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-10**|**World Model Self-Distillation: Training World Models to Solve General Tasks**|Sebastian Stapf et.al.|[2606.12072](https://arxiv.org/abs/2606.12072)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-10**|**VICX: Generalizable Robot Manipulation via Video Generation and In-Context Operator Network**|Song Chen et.al.|[2606.12028](https://arxiv.org/abs/2606.12028)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-10**|**When Does Language Matter? Multilingual Instructions Reveal Step-wise Language Sensitivity in Vision-Language-Action Models**|Xuan Dong et.al.|[2606.11906](https://arxiv.org/abs/2606.11906)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-10**|**Human-Guided Co-Manipulation of Carbon Fiber Plies**|Rami Ojanen et.al.|[2606.11818](https://arxiv.org/abs/2606.11818)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-10**|**TouchThinker: Scaling Tactile Commonsense Reasoning to the Open World with Large-scale Data and Action-aware Representation**|Kailin Lyu et.al.|[2606.11637](https://arxiv.org/abs/2606.11637)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-10**|**LUCID: Learning Embodiment-Agnostic Intent Models from Unstructured Human Videos for Scalable Dexterous Robot Skill Acquisition**|Harsh Gupta et.al.|[2606.11628](https://arxiv.org/abs/2606.11628)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-10**|**Vision-Language-Action Models Meet World Models: Embodied Agentic AI for Low-Altitude Wireless Networks**|Feibo Jiang et.al.|[2606.11618](https://arxiv.org/abs/2606.11618)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-09**|**Building Social World Models with Large Language Models**|Haofei Yu et.al.|[2606.11482](https://arxiv.org/abs/2606.11482)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-09**|**Signed Compression Progress on a Sealed Audit is Goodhart-Resistant**|Ayush Mittal et.al.|[2606.11417](https://arxiv.org/abs/2606.11417)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-09**|**Dynamic Execution Horizon Prediction for Chunk-based Robot Policies**|Yuchi Zhao et.al.|[2606.11408](https://arxiv.org/abs/2606.11408)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-09**|**PLUME: Probabilistic Latent Unified World Modeling and Parameter Estimation for Multi-Finger Manipulation**|Abhinav Kumar et.al.|[2606.11396](https://arxiv.org/abs/2606.11396)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-09**|**Next Forcing: Causal World Modeling with Multi-Chunk Prediction**|Gangwei Xu et.al.|[2606.11187](https://arxiv.org/abs/2606.11187)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-09**|**TacForeSight: Force-Guided Tactile World Model for Contact-Rich Manipulation**|Yujie Zang et.al.|[2606.11184](https://arxiv.org/abs/2606.11184)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-09**|**WorldOlympiad: Can Your World Model Survive a Triathlon?**|Yuke Zhao et.al.|[2606.11129](https://arxiv.org/abs/2606.11129)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-09**|**Monte Carlo Pass Search: Using Trajectory Generation for 3D Counterfactual Pass Evaluation in Football**|Andrew Kang et.al.|[2606.11120](https://arxiv.org/abs/2606.11120)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-09**|**WorldKernel: A World Model is the Coupling Kernel of Admissible Possible Worlds**|Fabio Rovai et.al.|[2606.10934](https://arxiv.org/abs/2606.10934)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-09**|**Task Robustness via Re-Labelling Vision-Action Robot Data**|Artur Kuramshin et.al.|[2606.10918](https://arxiv.org/abs/2606.10918)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-09**|**AgniNav: Configuration-Driven Cross-Embodiment Local Planning for Robot Navigation**|Tianhao Zang et.al.|[2606.10903](https://arxiv.org/abs/2606.10903)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-09**|**MODIP: Efficient Model-Based Optimization for Diffusion Policies**|Zakariae El Asri et.al.|[2606.10825](https://arxiv.org/abs/2606.10825)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-09**|**Hand-centric Human-to-Robot Trajectory Transfer from Video Demonstrations via Open-World Contact Localization**|Yitian Shi et.al.|[2606.10743](https://arxiv.org/abs/2606.10743)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-09**|**UniDexTok: A Unified Dexterous Hand Tokenizer from Real Data**|Dong Fang et.al.|[2606.10683](https://arxiv.org/abs/2606.10683)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-09**|**Can Image Models Imagine Time? ImageTime: A Novel Benchmark for Probing Visual World Modeling Through Spatiotemporal Consistency**|Xinrui Wu et.al.|[2606.10620](https://arxiv.org/abs/2606.10620)|**[link](https://huggingface.co/datasets/Xin-Rui/ImageTime_Benchmark)**|
|**2026-06-09**|**Test-time Adversarial Takeover: A Real-time Hijacking Interface against Robotic Diffusion Policies**|Zi Yin et.al.|[2606.10371](https://arxiv.org/abs/2606.10371)|**[link](https://github.com/wadeKeith/Awesome-Embodied-AI)**|
|**2026-06-09**|**ReflectiChain: Epistemic Grounding in LLM-Driven World Models for Supply Chain Resilience**|Jia Luo et.al.|[2606.10359](https://arxiv.org/abs/2606.10359)|**[link](https://github.com/tmgthb/Autonomous-Agents)**|
|**2026-06-09**|**Hierarchical Policies from Verbal and Egocentric Human Signals for Natural Human-Robot Interaction**|Dongjun Lee et.al.|[2606.10276](https://arxiv.org/abs/2606.10276)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-09**|**What Matters in Orchestrating Robot Policies: A Systematic Study of Hierarchical VLA Agents**|Jiaheng Hu et.al.|[2606.10267](https://arxiv.org/abs/2606.10267)|**[link](https://github.com/tmgthb/Autonomous-Agents)**|
|**2026-06-08**|**BiWM: Advancing Open-Source Interactive Video World Models with Bidirectional Autoregression**|Shaohao Rui et.al.|[2606.10135](https://arxiv.org/abs/2606.10135)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-08**|**Business World Model**|Cecil Pang et.al.|[2606.10044](https://arxiv.org/abs/2606.10044)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-08**|**Latent Spatial Memory for Video World Models**|Weijie Wang et.al.|[2606.09828](https://arxiv.org/abs/2606.09828)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-08**|**MemoryVLA++: Temporal Modeling via Memory and Imagination in Vision-Language-Action Models**|Hao Shi et.al.|[2606.09827](https://arxiv.org/abs/2606.09827)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-08**|**iMaC: Translating Actions into Motion and Contact Images for Embodied World Models**|Zhenyu Wu et.al.|[2606.09813](https://arxiv.org/abs/2606.09813)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-08**|**Echo-Memory: A Controlled Study of Memory in Action World Models**|Wayne King et.al.|[2606.09803](https://arxiv.org/abs/2606.09803)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-08**|**AetheRock: An Arm-Worn Robot Teaching System for Force-Guided Vision-Tactile Learning**|Hong Li et.al.|[2606.09777](https://arxiv.org/abs/2606.09777)|**[link](https://github.com/pstAmbition/DailyArXiv_Multimodal)**|
|**2026-06-08**|**Physics-Aware Sparse Learning and Selective Online Adaptation for Euler-Lagrange Robot Dynamics**|Rishabh Dev Yadav et.al.|[2606.09640](https://arxiv.org/abs/2606.09640)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-08**|**Prisma-World: Camera-Controllable Multi-Agent Video World Model**|Huiqiang Sun et.al.|[2606.09507](https://arxiv.org/abs/2606.09507)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-08**|**Targeting World Models to Compromise Robot Learning Pipelines**|Ethan Rathbun et.al.|[2606.09499](https://arxiv.org/abs/2606.09499)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-08**|**Goal Sets, Not Goal States: Queryable Robot Goals through Goal-Set Hindsight Relabeling**|Carlos Vélez García et.al.|[2606.09476](https://arxiv.org/abs/2606.09476)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-08**|**$ω$ -EVA: Envision, Verify, and Act with Latent Interactive World Models**|Zhenguo Sun et.al.|[2606.09457](https://arxiv.org/abs/2606.09457)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-08**|**ReGIL: Retrieval-Guided Imitation Learning from a Single Demonstration**|Yuying Zhang et.al.|[2606.09381](https://arxiv.org/abs/2606.09381)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-08**|**Toward Compiler World Models: Learning Latent Dynamics for Efficient Tensor Program Search**|Haolin Pan et.al.|[2606.09312](https://arxiv.org/abs/2606.09312)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-08**|**FF-JEPA: Long-Horizon Planning in World Models with Latent Planners**|Sergi Masip et.al.|[2606.09311](https://arxiv.org/abs/2606.09311)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-08**|**MotionWAM: Towards Foundation World Action Models for Real-Time Humanoid Loco-Manipulation**|Jia Zheng et.al.|[2606.09215](https://arxiv.org/abs/2606.09215)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-08**|**Bridging the Agent-World Gap: Text World Models for LLM-based Agents**|Yixia Li et.al.|[2606.09032](https://arxiv.org/abs/2606.09032)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-08**|**ATM: Action-Consistency Transfer Matrix for Diagnosing and Improving Latent World Models**|Jiaheng Chen et.al.|[2606.09028](https://arxiv.org/abs/2606.09028)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-07**|**Video2Sim2Real: Full-Stack Autonomous Dexterous Skill Acquisition from a Single Human Video**|Yunhai Han et.al.|[2606.08828](https://arxiv.org/abs/2606.08828)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-07**|**Unifying Object-Centric World Models and Diffusion Policy: A Hierarchical Framework for Multi-Stage Robotic Tasks**|Raktim Gautam Goswami et.al.|[2606.08775](https://arxiv.org/abs/2606.08775)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-07**|**Safe, Fluent and Acceptable Motion Generation and Execution for Human--Robot Interaction in Manufacturing Environments**|Thibaut Lopez et.al.|[2606.08741](https://arxiv.org/abs/2606.08741)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-07**|**Dream-Tac: A Unified Tactile World Action Model for Contact-Rich Robot Manipulation**|Yunfan Lou et.al.|[2606.08737](https://arxiv.org/abs/2606.08737)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-05**|**Re-imagining ISO 26262 in the Age of Autonomous Vehicles: Enhancing Controllability through Transferability and Predictability**|Chaitanya Shinde et.al.|[2606.07437](https://arxiv.org/abs/2606.07437)|**[link](https://github.com/wonderNefelibata/Awesome-LRM-Safety)**|
|**2026-06-05**|**Spline Policy: A Structured Representation for Robot Policies**|Mengze Tian et.al.|[2606.07386](https://arxiv.org/abs/2606.07386)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-05**|**RhinoVLA Technical Report**|Huixi Intelligence et.al.|[2606.07383](https://arxiv.org/abs/2606.07383)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-05**|**AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization**|Yu Li et.al.|[2606.07326](https://arxiv.org/abs/2606.07326)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-05**|**CAPE: Contrastive Action-conditioned Parallel Encoding for Embodied Planning**|Cong Chen et.al.|[2606.07304](https://arxiv.org/abs/2606.07304)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-05**|**Bootstrap Theory of Representational Emergence: Explanatory Insufficiency as a Driver of Representation Learning and World Models**|Jacques Raynal et.al.|[2606.07303](https://arxiv.org/abs/2606.07303)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-05**|**Does Appearance Help? A Systematic Study of Image-Based Re-Identification in Online 3D Multi-Pedestrian Tracking**|Eduardo Borges et.al.|[2606.07233](https://arxiv.org/abs/2606.07233)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-06-05**|**Robotic Policy Adaptation via Weight-Space Meta-Learning**|Christian Bianchi et.al.|[2606.07217](https://arxiv.org/abs/2606.07217)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-05**|**Learning Explicit Behavioral Models with Adaptive Questions and World-Model Probes**|Hikaru Shindo et.al.|[2606.07127](https://arxiv.org/abs/2606.07127)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-05**|**QuadVerse: An Integrated Framework Aligning Visual-Physical Reality for Quadruped Simulation**|Yuxiang Chen et.al.|[2606.07118](https://arxiv.org/abs/2606.07118)|**[link](https://github.com/longxiang-ai/awesome-gaussians)**|
|**2026-06-05**|**ActionMap: Robot Policy Learning via Voxel Action Heatmap**|Pei Yang et.al.|[2606.06904](https://arxiv.org/abs/2606.06904)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-05**|**Blockchain Infrastructure for Intelligent Cyber--Physical--Social Systems:Post-Quantum Security, Interoperability, and Trustworthy Data Economies in the Era of Embodied AI**|Song Guo et.al.|[2606.06895](https://arxiv.org/abs/2606.06895)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-05**|**STRIPS-WM: Learning Grounded Propositional STRIPS-style World Models from Images**|Abhiroop Ajith et.al.|[2606.06832](https://arxiv.org/abs/2606.06832)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-04**|**Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators**|Chenming Zhu et.al.|[2606.06476](https://arxiv.org/abs/2606.06476)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-04**|**Double Preconditioning (DoPr): Optimization for Test-Time Performance, not Validation Loss**|Thomas T. Zhang et.al.|[2606.06418](https://arxiv.org/abs/2606.06418)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-04**|**VOLT: Vision and Language Trajectory Segmentation for Faster-than-Demonstration Policies**|Robert Ramirez Sanchez et.al.|[2606.06323](https://arxiv.org/abs/2606.06323)|**[link](https://github.com/zezhishao/DailyArXiv)**|
|**2026-06-04**|**MPCoT: Reward-Guided Multi-Path Latent Reasoning for Test-Time Scalable Vision-Language-Action**|Boyang Zhang et.al.|[2606.06245](https://arxiv.org/abs/2606.06245)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-04**|**WorldFly: A World-Model-Based Vision-Language-Action Model for UAV Navigation**|Shengtao Zheng et.al.|[2606.06147](https://arxiv.org/abs/2606.06147)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-04**|**A Conversational Framework for Human-Robot Collaborative Manipulation with Distributed Generative AI models**|Arash Ghasemzadeh Kakroudi et.al.|[2606.06061](https://arxiv.org/abs/2606.06061)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-04**|**RealDexUMI: A Wearable Universal Manipulation Interface for Dexterous Robot Learning**|Chaoyi Xu et.al.|[2606.06033](https://arxiv.org/abs/2606.06033)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-04**|**PLAN-S: Bridging Planning with Latent Style Dynamics for Autonomous Driving World Models**|Xiaoyun Qiu et.al.|[2606.06014](https://arxiv.org/abs/2606.06014)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-04**|**World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesis**|Yi Yang et.al.|[2606.05979](https://arxiv.org/abs/2606.05979)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-04**|**Towards a Data Flywheel for Embodied Intelligence in Logistics**|Anlan Yu et.al.|[2606.05960](https://arxiv.org/abs/2606.05960)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-04**|**Towards World Models in Biomedical Research**|Guangyu Wang et.al.|[2606.05925](https://arxiv.org/abs/2606.05925)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-04**|**PiL-World: A Chunk-Wise World Model for VLA Policy-in-the-Loop Evaluation**|Chong Ma et.al.|[2606.05773](https://arxiv.org/abs/2606.05773)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-04**|**Let It Be Simple: One-Step Action Generation for Vision-Language-Action Models**|Yitong Chen et.al.|[2606.05737](https://arxiv.org/abs/2606.05737)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-04**|**DexFuture: Hierarchical Future-State Visuomotor Targeting for Bimanual Dexterous Tool Use**|Runfa Blark Li et.al.|[2606.05699](https://arxiv.org/abs/2606.05699)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-04**|**Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy Learning**|Ziyang Yao et.al.|[2606.05645](https://arxiv.org/abs/2606.05645)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-04**|**KV-Control: Parameter-Efficient K/V Injection for Trajectory-Controlled Text-to-Motion**|Tengjiao Sun et.al.|[2606.05624](https://arxiv.org/abs/2606.05624)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-04**|**Autoregressive Diffusion World Models for Off-Policy Evaluation of LLM Agents**|Kaixuan Liu et.al.|[2606.05558](https://arxiv.org/abs/2606.05558)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-04**|**Representation Learning Enables Scalable Multitask Deep Reinforcement Learning**|Johan Obando-Ceron et.al.|[2606.05555](https://arxiv.org/abs/2606.05555)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-03**|**VASO: Formally Verifiable Self-Evolving Skills for Physical AI Agents**|Yunhao Yang et.al.|[2606.05395](https://arxiv.org/abs/2606.05395)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-03**|**HORIZON: Recoverability-Governed Curriculum for Physical-Domain Scaling**|Chenhao Bai et.al.|[2606.05143](https://arxiv.org/abs/2606.05143)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-03**|**Generalization of World Models under Environmental Variability for Vision-based Quadrotor Navigation**|Luca Zanatta et.al.|[2606.05015](https://arxiv.org/abs/2606.05015)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-03**|**Explainably Safe Reinforcement Learning**|Sabine Rieder et.al.|[2606.04634](https://arxiv.org/abs/2606.04634)|**[link](https://github.com/Mondrian-He/awesome-nips-2025-artist)**|
|**2026-06-03**|**MIRAGE: Mobile Agents with Implicit Reasoning and Generative World Models**|Zhichao Yang et.al.|[2606.04627](https://arxiv.org/abs/2606.04627)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-03**|**MAD: Mapping-Aware World Models for Agile Quadrotor Flight**|Xinhong Zhang et.al.|[2606.04534](https://arxiv.org/abs/2606.04534)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-03**|**OSCAR: Omni-Embodiment Skeleton-Conditioned World Action Model for Robotics**|Zhuoyuan Wu et.al.|[2606.04463](https://arxiv.org/abs/2606.04463)|**[link](https://huggingface.co/datasets/zywu2115/human_v1_70f)**|
|**2026-06-02**|**A Cookbook of 3D Vision: Data, Learning Paradigms, and Application**|Hongyang Du et.al.|[2606.04291](https://arxiv.org/abs/2606.04291)|**[link](https://github.com/longxiang-ai/awesome-gaussians)**|
|**2026-06-02**|**UniCanvas: A Diffusion-base Unified Model for Text-in-Image Joint Generation**|Zeyuan Yang et.al.|[2606.04264](https://arxiv.org/abs/2606.04264)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-02**|**PerceptTwin: Semantic Scene Reconstruction for Iterative LLM Planning and Verification**|Charlie Gauthier et.al.|[2606.04226](https://arxiv.org/abs/2606.04226)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-02**|**GroupToM-Bench: Benchmarking Group Theory of Mind and Nonlinear Social Emergence in MLLMs**|Weidong Tang et.al.|[2606.04184](https://arxiv.org/abs/2606.04184)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-02**|**CLAW: Learning Continuous Latent Action World Models via Adversarial Latent Regularization**|Tewodros Ayalew et.al.|[2606.04130](https://arxiv.org/abs/2606.04130)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-02**|**Denoising Tells When to Replan: Denoising-Variance Adaptive Chunking for Flow-Based Robot Policies**|Xiangdong Feng et.al.|[2606.03847](https://arxiv.org/abs/2606.03847)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-02**|**Same Weights, Different Robot: A Deployment Safety View of VLA Policies**|Jianwei Tai et.al.|[2606.03724](https://arxiv.org/abs/2606.03724)|**[link](https://github.com/Ponkux/DailyArXiv-cp)**|
|**2026-06-02**|**Face versus Body Tracking for Human-Robot Interaction: An Egocentric Dataset**|Jessica Wenninger et.al.|[2606.03694](https://arxiv.org/abs/2606.03694)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-02**|**A Close Look At World Model Recovery In Supervised Fine-Tuned LLM Planners**|Patrick Emami et.al.|[2606.03685](https://arxiv.org/abs/2606.03685)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-02**|**GN0: Toward a Unified Paradigm for Generation, Evaluation, and Policy Learning in Visual-Language Navigation**|Xinhai Li et.al.|[2606.03682](https://arxiv.org/abs/2606.03682)|**[link](https://huggingface.co/models/TeleEmbodied/GN-BAE)**|
|**2026-06-03**|**A 3D Isovist World Model -- Revealing a City's Unseen Geometry and Its Emergent Cross-City Signature**|Xuhui Lin et.al.|[2606.03609](https://arxiv.org/abs/2606.03609)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-02**|**World Models Meet Language Models: On the Complementarity of Concrete and Abstract Reasoning**|Yucheng Zhou et.al.|[2606.03603](https://arxiv.org/abs/2606.03603)|**[link](https://huggingface.co/datasets/YCZhou/vrqa_bench)**|
|**2026-06-02**|**NVIDIA Isaac Sim: Enabling Scalable, GPU-Accelerated Simulation for Robotics**|Sicong Gao et.al.|[2606.03551](https://arxiv.org/abs/2606.03551)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-02**|**Human2Humanoid: Physics-Aware Cross-Morphology Motion Retargeting for Humanoid Robots**|Tianchen Huang et.al.|[2606.03476](https://arxiv.org/abs/2606.03476)|**[link](https://github.com/Foruck/Awesome-Human-Motion)**|

(<a href=#updated-on-20260823>back to top</a>)

## Robotic Manipulation

|Publish Date|Title|Authors|PDF|Code|
|---|---|---|---|---|
|**2026-08-20**|**DreamHand: Repurposing Video Diffusion Models for Occlusion-Robust Egocentric 3D Hand Motion Recovery**|Yufei Liu et.al.|[2608.20308](https://arxiv.org/abs/2608.20308)|null|
|**2026-08-20**|**Video2DoorTraversal: Push Door Traversal via Simulated Door Twins**|Xincheng Tang et.al.|[2608.20251](https://arxiv.org/abs/2608.20251)|null|
|**2026-08-20**|**RoMAN-Flow: Taming Autoregressive Normalizing Flows for Offline Reinforcement Learning in Robotic Manipulation**|Shaoxuan Wang et.al.|[2608.20208](https://arxiv.org/abs/2608.20208)|null|
|**2026-08-20**|**Wave-Based Bilateral Teleoperation between Nonlinear Manipulators with Direct Contact Force Feedback**|G. Q. Bao Tran et.al.|[2608.20043](https://arxiv.org/abs/2608.20043)|null|
|**2026-08-20**|**EXIMO: VLM Guided Exploration of VLA Policies**|Bhavya Sukhija et.al.|[2608.19891](https://arxiv.org/abs/2608.19891)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-20**|**CoToGrasp: Contact-Topology-Conditioned Dexterous Grasp Synthesis via Canonical Workspace Learning**|Julien Merand et.al.|[2608.19776](https://arxiv.org/abs/2608.19776)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-20**|**GOAG: Generative and Object-Agnostic Grasp Planner for Dexterous Robotic Manipulation**|Julien Merand et.al.|[2608.19759](https://arxiv.org/abs/2608.19759)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-20**|**What Matters for Latent Actions in Robot Learning**|Xizhou Bu et.al.|[2608.19613](https://arxiv.org/abs/2608.19613)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-20**|**HiTac-WAM: A Hierarchical Tactile World Action Model for Contact-Rich Robot Manipulation**|Chao Xue et.al.|[2608.19574](https://arxiv.org/abs/2608.19574)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-08-19**|**When Automata Meet Streams: Temporal Logic Compilation for Stream-Based Robotics Task and Motion Planning**|Sayem Nazmuz Zaman et.al.|[2608.19453](https://arxiv.org/abs/2608.19453)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-19**|**Hybrid Feedback Sampling for Sample-Efficient Model Predictive Control**|Chaoyi Pan et.al.|[2608.19443](https://arxiv.org/abs/2608.19443)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-19**|**PartialBiGrasp: Inferring Hidden Local Geometry for Bimanual Grasping from Partial Views**|Ayush Kaura et.al.|[2608.19188](https://arxiv.org/abs/2608.19188)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-19**|**Beyond Placement and Articulation: Usage-Driven Code Scenes for Embodied Interaction**|Zijian Xiao et.al.|[2608.18840](https://arxiv.org/abs/2608.18840)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-19**|**Dream2Reward: Transition-Alignment Reward Models from Positive Demonstrations for Robotic Manipulation**|Haoyu Zhang et.al.|[2608.18787](https://arxiv.org/abs/2608.18787)|null|
|**2026-08-19**|**Reinforced Planning with Latent World Models**|Armin Sommer et.al.|[2608.18669](https://arxiv.org/abs/2608.18669)|null|
|**2026-08-19**|**Backward Layout Search for Sequence-Constrained Robotic Assembly**|Xi Zhang et.al.|[2608.18454](https://arxiv.org/abs/2608.18454)|null|
|**2026-08-19**|**HarvestPoint-ACT: Explicit Target Selection and Harvest-Point Conditioning for Robotic Fruit Harvesting under Occlusion**|Hanying Hu et.al.|[2608.18446](https://arxiv.org/abs/2608.18446)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-18**|**Revisiting the "Push-T" Robot Manipulation Task with Agentic Robotics**|Shuangyu Xie et.al.|[2608.18227](https://arxiv.org/abs/2608.18227)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-18**|**CompCPZ: Preserving Multi-Modal Intent in Language-Guided Robot Manipulation**|Zhen Zhang et.al.|[2608.17717](https://arxiv.org/abs/2608.17717)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-18**|**Force-Based Offset Estimation for Keyed Peg-in-Hole Assembly Using Local Gaussian Process Regression**|Chandra Yuvesh Aubeeluck et.al.|[2608.17691](https://arxiv.org/abs/2608.17691)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-18**|**Iterative Grasp Pose Refinement: A Deep Reinforcement Learning Approach for 2D Vision**|Amir Arsalan Nematollahi et.al.|[2608.17628](https://arxiv.org/abs/2608.17628)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-18**|**Physics-Informed Sliding-Window Particle Filtering for Tactile-Only In-Hand 6-DoF Object Pose Refinement**|Lingjun Shao et.al.|[2608.17601](https://arxiv.org/abs/2608.17601)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-19**|**EATR-Stereo: Embodiment-Aware Token Routing of Paired Stereo Evidence for Humanoid Vision-Language-Action Control**|Songwei Wu et.al.|[2608.17453](https://arxiv.org/abs/2608.17453)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-18**|**MANIGUARD: A Benchmark and Data Suite for Specification-Grounded Safety Evaluation and Improvement of Robotic Manipulation**|Yiyan Peng et.al.|[2608.17386](https://arxiv.org/abs/2608.17386)|**[link](https://huggingface.co/models/IDEAS-Lab-Northwestern/pi05-real-clutter-60-droid-refined-lora)**|
|**2026-08-18**|**Repetition as Reinforcement: Enhancing Sample Efficiency via Instant Episode Repetition in Reinforcement Learning**|Hoda Yamani et.al.|[2608.17347](https://arxiv.org/abs/2608.17347)|null|
|**2026-08-18**|**ORPA: Online Residual Policy Adaptation for Robot Manipulation Control with Human Feedback**|Muhammad A. Muttaqien et.al.|[2608.17323](https://arxiv.org/abs/2608.17323)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-18**|**Robust Brachiation on a Life-Sized Dual-Arm Robot Using Waypoint-Guided Reinforcement Learning**|Ayumu Iwata et.al.|[2608.17320](https://arxiv.org/abs/2608.17320)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-17**|**PDDL-ART: Autonomous Symbolic Abstraction From Demonstration For Long-Horizon Robotic Manipulation Using Vision-Language Models**|Disha Kamale et.al.|[2608.17146](https://arxiv.org/abs/2608.17146)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-17**|**PROBE: Manipulation-Grounded Visual Question Answering with VLM Agents**|Vineet Bhat et.al.|[2608.17129](https://arxiv.org/abs/2608.17129)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-17**|**FetchMan: Learning Visual Humanoid Loco-Manipulation Policies from Simulated Experiences**|Omar Rayyan et.al.|[2608.17027](https://arxiv.org/abs/2608.17027)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-17**|**VLCP: Vision Language Control Policy Closed-Loop Code Replanning for Robot Manipulation**|Dhia Naouali et.al.|[2608.16978](https://arxiv.org/abs/2608.16978)|**[link](https://github.com/Ed1sonChen/DailyArxiv)**|
|**2026-08-17**|**Don't Drop the BATON: Long-Horizon Robot Manipulation via Agentic Subtask Exploration and Transition-aware Memory**|Bingxin Xu et.al.|[2608.16889](https://arxiv.org/abs/2608.16889)|**[link](https://github.com/xianshang33/llm-paper-daily)**|
|**2026-08-17**|**$τ_0$ -VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation**|Xiaowei Cai et.al.|[2608.16885](https://arxiv.org/abs/2608.16885)|**[link](https://huggingface.co/models/sii-research/tau-0-vla)**|
|**2026-08-17**|**HAF: Adapting Generalist VLAs to Humanoid Whole-Body Loco-manipulation via Hierarchical Action Flow and Spectral Latent RL**|Langzhe Gu et.al.|[2608.16837](https://arxiv.org/abs/2608.16837)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-17**|**When State Becomes an Attack Surface: State-Semantic Injection in LLM-Driven Embodied Agents**|Jiawei Liu et.al.|[2608.16806](https://arxiv.org/abs/2608.16806)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-17**|**Design Optimization for Large High-Force Soft Robot Manipulators Under Gravitational Loads**|Isara Cholaseuk et.al.|[2608.16728](https://arxiv.org/abs/2608.16728)|null|
|**2026-08-17**|**H-PAC Hand: Control-Oriented Modeling and Tendon-Elasticity Compensation for an Underactuated Robotic Hand**|Teng Yan et.al.|[2608.16712](https://arxiv.org/abs/2608.16712)|null|
|**2026-08-17**|**ViHaTeleop: A Low-Cost, Lightweight Visual-Haptic Teleoperation System for Dexterous Manipulation Learning**|Fucai Zhu et.al.|[2608.16572](https://arxiv.org/abs/2608.16572)|null|
|**2026-08-17**|**NebulaVLA: A Dual-Frequency Vision-Language-Action Model With Guide Action for Robotic Manipulation**|Cong Zhao et.al.|[2608.16503](https://arxiv.org/abs/2608.16503)|null|
|**2026-08-17**|**Arm-Aware Guided Dexterous Grasp Generation with Arm-Agnostic Grasp Models**|Yongyi Jia et.al.|[2608.16351](https://arxiv.org/abs/2608.16351)|null|
|**2026-08-17**|**Unified Condition-Action Modeling for Accurate One-Step Action Generation**|Xinyu Zhou et.al.|[2608.16153](https://arxiv.org/abs/2608.16153)|**[link](https://github.com/pstAmbition/DailyArXiv_Multimodal)**|
|**2026-08-16**|**Tabletop Pen Manipulation With a Vision-Guided 4-DoF Arm**|Anirudh Rangarajan et.al.|[2608.15968](https://arxiv.org/abs/2608.15968)|**[link](https://github.com/RLCL-EIT/robotics_arxiv_daily)**|
|**2026-08-16**|**Revisiting Open-Loop Execution in Robotics: Toward Reactive, Higher-Performing Policies**|Michael Zeng et.al.|[2608.15938](https://arxiv.org/abs/2608.15938)|**[link](https://github.com/Ed1sonChen/DailyArxiv)**|
|**2026-08-16**|**GAINS: Leveraging Inconsistent Human Intervention Signals in Reinforcement Learning**|Xinyi Zhang et.al.|[2608.15707](https://arxiv.org/abs/2608.15707)|**[link](https://github.com/Ponkux/DailyArXiv-cp)**|
|**2026-08-16**|**Robo-Dopamine 2.0: History-Conditioned and OOD-Aware Process Reward Modeling for Robotic Manipulation**|Yijie Xu et.al.|[2608.15680](https://arxiv.org/abs/2608.15680)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-16**|**Algorithm-Architecture Co-Design for Efficient VLA Inference via Speculative Inference and Verification**|Chunyu Qi et.al.|[2608.15636](https://arxiv.org/abs/2608.15636)|null|
|**2026-08-16**|**ReForce: Learning Force-aware Retargeting for Dexterous Manipulation**|Yuhang Wu et.al.|[2608.15560](https://arxiv.org/abs/2608.15560)|**[link](https://github.com/RLCL-EIT/robotics_arxiv_daily)**|
|**2026-08-15**|**GUIDER: Evaluating Goal-Free Human Intent Inference for Teleoperated Manipulation on Real-Robot Data**|Nicholas Kenny et.al.|[2608.15446](https://arxiv.org/abs/2608.15446)|**[link](https://github.com/Ed1sonChen/DailyArxiv)**|
|**2026-08-15**|**SOS! : A Streamlined Object-Conditional Transformer for Model-free Segmentation**|Jiaqi Hu et.al.|[2608.15295](https://arxiv.org/abs/2608.15295)|**[link](https://github.com/NY1024/AgentSafety-Papers)**|
|**2026-08-15**|**PhaseLoRA: Control-Regime-Conditioned Low-Rank Adaptation for Continuous-Action Vision-Language-Action Policies**|Yufei Guo et.al.|[2608.15285](https://arxiv.org/abs/2608.15285)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-15**|**StructRL: Structured Action-Space Exploration for Flow-Based VLAs**|Jiarui Yang et.al.|[2608.15139](https://arxiv.org/abs/2608.15139)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-14**|**THRIVE: Therapeutic Humanoid Robot In Virtual Environment**|Jin Xu et.al.|[2608.14462](https://arxiv.org/abs/2608.14462)|**[link](https://github.com/Ed1sonChen/DailyArxiv)**|
|**2026-08-14**|**Reflex: Enabling Fast and Predictive Vision-Language-Action Models for Reaction-Critical Manipulation**|Yuxuan Chen et.al.|[2608.14379](https://arxiv.org/abs/2608.14379)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-14**|**FlatLab: A Unified Methodology Framework and Simulation-Based Benchmark for Robotic Manipulation of Flat Objects**|Xingyu Zhu et.al.|[2608.14049](https://arxiv.org/abs/2608.14049)|**[link](https://github.com/Songwxuan/Embodied-AI-Paper-TopConf)**|
|**2026-08-13**|**DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation**| DreamX Team et.al.|[2608.13489](https://arxiv.org/abs/2608.13489)|**[link](https://github.com/knightnemo/Awesome-World-Models)**|
|**2026-08-13**|**Predictive Relative-Velocity Steering for Safe Robotic Manipulator Teleoperation in Dynamic Environments**|Changhao Hu et.al.|[2608.13284](https://arxiv.org/abs/2608.13284)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-13**|**S2-HWM: Sparse Event-Structured Hierarchical World Model for Long-Horizon Surgical Robot Manipulation**|Shuzhe Zhang et.al.|[2608.13103](https://arxiv.org/abs/2608.13103)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-08-13**|**H2R-Bench: Benchmarking Human-to-Robot Manipulation Video Generation in World Models**|Dingyi Rong et.al.|[2608.13049](https://arxiv.org/abs/2608.13049)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-08-13**|**EgoPHI: Estimating Contact and Force from Egocentric Vision**|Andela Ilic et.al.|[2608.13014](https://arxiv.org/abs/2608.13014)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-08-12**|**RoboSynChallenge: Mastering Real-World Dexterity via Generalizing Synthesized Manipulation Skills**|Runyi Zhao et.al.|[2608.12416](https://arxiv.org/abs/2608.12416)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-12**|**Redistribution-based Cost Inference Improves Sparse Safe Offline RL**|Ebenezer Gelo et.al.|[2608.12306](https://arxiv.org/abs/2608.12306)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-12**|**HandEdit: A Unified Benchmark for Egocentric Human-to-Robot Dexterous Hand Image Editing**|Zhenjie Yang et.al.|[2608.12122](https://arxiv.org/abs/2608.12122)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-12**|**Learning Loco-Manipulation From SMPC Demonstrations With Sparse Offline-to-Online RL**|Martin Schuck et.al.|[2608.12063](https://arxiv.org/abs/2608.12063)|null|
|**2026-08-12**|**ATOM: Geometry-Aware Microgesture towards Object-Agnostic Tangible Interaction**|Yinqiao Wang et.al.|[2608.11871](https://arxiv.org/abs/2608.11871)|null|
|**2026-08-12**|**Motion-as-Prompt: Enhancing Motion Reasoning in Multimodal Large Language Models via Motion-Guided Cross-Frame Visual Prompting**|Xikai Sun et.al.|[2608.11655](https://arxiv.org/abs/2608.11655)|**[link](https://github.com/SunVictor23/MaP)**|
|**2026-08-14**|**StageWAM: Joint-Embedding Stage Prediction for World-Action Models in Robot Manipulation**|Xiao Liu et.al.|[2608.10780](https://arxiv.org/abs/2608.10780)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-08-11**|**FADE: From Passive Verification to Active Discovery in Counterfactual Video Understanding**|Fufangchen Zhao et.al.|[2608.10764](https://arxiv.org/abs/2608.10764)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-11**|**Embodied Multimodal Grounding for Open-Vocabulary Mobile Manipulation via Semantic 3D Gaussian Splatting**|Huosen Ou et.al.|[2608.10756](https://arxiv.org/abs/2608.10756)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-11**|**Precise Top-Layer Fabric Segmentation for Fabric Destacking with Edge- and Shape-Aware Deep Networks**|Wenbo Dong et.al.|[2608.10648](https://arxiv.org/abs/2608.10648)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-13**|**Real-World Cooperative Bimanual Dexterous Grasp of Large Objects from Single-View Observations**|Ziming Li et.al.|[2608.10383](https://arxiv.org/abs/2608.10383)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-10**|**Chain of Spatial Thoughts: Modality-Agnostic Spatial Grounding for Vision Language Models**|Hunter Schofield et.al.|[2608.10278](https://arxiv.org/abs/2608.10278)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-10**|**RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance**|Dongchi Huang et.al.|[2608.09853](https://arxiv.org/abs/2608.09853)|**[link](https://huggingface.co/spaces/hugging-apps/rynn-value-4b)**|
|**2026-08-10**|**RoboSeg: Online Part-Level Semantic Reconstruction for Robotic Manipulation via a Single Eye-in-Hand Camera**|Zhaochen Lan et.al.|[2608.09778](https://arxiv.org/abs/2608.09778)|**[link](https://github.com/liliu-avril/Awesome-Segment-Anything)**|
|**2026-08-10**|**SLIM-0.5B: Learning Action-Grounded Predictive Latents for Robot Manipulation**|Jingkai Wang et.al.|[2608.09771](https://arxiv.org/abs/2608.09771)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-10**|**Efficient Real-World Online Reinforcement Learning for Robot Manipulation via Centralized Training and Critic Decomposition**|Changhao Li et.al.|[2608.09762](https://arxiv.org/abs/2608.09762)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-10**|**Removing Infrastructure Barriers in Human-Robot Collaboration Through Wireless Reconfigurable Cells**|Emma Takács et.al.|[2608.09658](https://arxiv.org/abs/2608.09658)|**[link](https://github.com/Jianqiuer/Awesome6DPoseEstimation)**|
|**2026-08-10**|**Skills in Weights, Memory in Code: Hybrid Learning for Memory-Dependent Robot Manipulation**|Yunhao Zhao et.al.|[2608.09410](https://arxiv.org/abs/2608.09410)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-10**|**SAFE-CHEM: Uncertainty-Aware Policy Switching for Robust Robotic Chemistry**|Laura Jones et.al.|[2608.09303](https://arxiv.org/abs/2608.09303)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-10**|**GRASP: Granularity-Aware Region Alignment and Semantic Prototype Learning for Fine-Grained Cross-Modal Understanding in Drone Views**|Jiahui Cui et.al.|[2608.09270](https://arxiv.org/abs/2608.09270)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-10**|**Ultra-Low-Impedance Robotic Gripper for High-Bandwidth and Transparent Physical Interaction**|Joon Lee et.al.|[2608.09198](https://arxiv.org/abs/2608.09198)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-11**|**SpeedTuning: Speeding Up Policy Execution with Lightweight Reinforcement Learning**|David D. Yuan et.al.|[2608.09138](https://arxiv.org/abs/2608.09138)|**[link](https://github.com/DoongLi/ICRA2025-Paper-List)**|
|**2026-08-10**|**Trajectory Divergence Horizon Decision for Reliable Dual-Arm Surgical Subtask Manipulation**|Mingwu Su et.al.|[2608.09125](https://arxiv.org/abs/2608.09125)|**[link](https://github.com/zezhishao/DailyArXiv)**|
|**2026-08-09**|**SG-WAM: Text-Grounded and Spatial-aware Semantic Guidance for World-Action Models**|Junjie He et.al.|[2608.08839](https://arxiv.org/abs/2608.08839)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-09**|**PEEL: Parallel Extraction for Long-Horizon Disassembly Planning via Scale-Invariant Sampling**|Servet B. Bayraktar et.al.|[2608.08773](https://arxiv.org/abs/2608.08773)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-09**|**OnEvoMemory: Evolving Memory through Online Robot Rollouts for Pretrained Robot Policies**|Zhongxi Chen et.al.|[2608.08749](https://arxiv.org/abs/2608.08749)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-09**|**TomaMMU: A Comprehensive Multimodal Understanding Benchmark for Tomato Leaf Diseases**|Gia-Han Truong et.al.|[2608.08727](https://arxiv.org/abs/2608.08727)|**[link](https://github.com/RLCL-EIT/robotics_arxiv_daily)**|
|**2026-08-09**|**WA-SpecDec: World-Aware Speculative Decoding for Vision-Language-Action Models**|Zikang Wen et.al.|[2608.08725](https://arxiv.org/abs/2608.08725)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-09**|**TrustRoboReward: Preference-Ordered Isotonic Score Editing for Multi-Paradigm Robot Reward Models**|Yidong Wang et.al.|[2608.08491](https://arxiv.org/abs/2608.08491)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-08-08**|**Multi-modal Interactive Control of Robotic Arm based on Offline Large Language Models**|Hanxiao Chen et.al.|[2608.08183](https://arxiv.org/abs/2608.08183)|**[link](https://github.com/Ed1sonChen/DailyArxiv)**|
|**2026-08-08**|**A Mixed-Stiffness Anthropomimetic Fingertip Broadens the Operating Range for Coin Grasping**|Kaigen Go et.al.|[2608.07887](https://arxiv.org/abs/2608.07887)|**[link](https://github.com/TogoLab/mixed-stiffness-fingertip-coin-grasping)**|
|**2026-08-07**|**LUCID: Latent-Skill Unified Control via Imagined Dynamics for Long-Horizon Humanoid Loco-Manipulation**|Cheng Guo et.al.|[2608.07746](https://arxiv.org/abs/2608.07746)|**[link](https://github.com/Ed1sonChen/DailyArxiv)**|
|**2026-08-07**|**Detection and Ranging of Transient Extrinsic Contacts Based on 6D Dynamic Tactile Sensing**|Haowen Zheng et.al.|[2608.07075](https://arxiv.org/abs/2608.07075)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-07**|**C2Dex: Contact-Consistent Reconstruction and Retargeting for Dexterous Manipulation from Monocular Video**|Jie Ren et.al.|[2608.07045](https://arxiv.org/abs/2608.07045)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-07**|**Decoupling Intention from Trajectory: A Representational Deduction Framework for World Action Models**|Xiangkai Ma et.al.|[2608.06994](https://arxiv.org/abs/2608.06994)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-08-06**|**GRASP: Reinforcing Language Model Anonymizers with Group Relative Policy Optimization**|Sajjad Ghiasvand et.al.|[2608.06526](https://arxiv.org/abs/2608.06526)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-06**|**$ω$ -0: A Latent Predictive World Action Model for Concurrent Humanoid Loco-Manipulation**|Zhe Li et.al.|[2608.06375](https://arxiv.org/abs/2608.06375)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-08-06**|**DyPES-VLA: Learning Shared Dynamics Priors and Embodiment-Specific Control for Cross-Embodiment Manipulation**|Junfeng Li et.al.|[2608.06374](https://arxiv.org/abs/2608.06374)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-07**|**A Master-Slave Robot Manipulator for Needle-Based Teleoperation in MRI Chamber**|Omar Curiel et.al.|[2608.06354](https://arxiv.org/abs/2608.06354)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-06**|**GeniWorld: A Generalizable Interactive World Model for Robotic Manipulation via Visual Actions**|Chenghao Gu et.al.|[2608.06332](https://arxiv.org/abs/2608.06332)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-06**|**Design and Evaluation of a Touchscreen-Based Teleoperation Interface for Robotic Manipulators**|Juan José García Cárdenas et.al.|[2608.06219](https://arxiv.org/abs/2608.06219)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-06**|**VIDP: Variable Impedance Diffusion Policy for Compliant Robot Manipulation from Diverse Demonstrations**|Hisham Khalil et.al.|[2608.06210](https://arxiv.org/abs/2608.06210)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-06**|**Beyond Flat Policies: Hierarchical Post-Training for Embodied Agents in Robotic Manipulation**|He Kong et.al.|[2608.05999](https://arxiv.org/abs/2608.05999)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-06**|**SkillMemo: Expert-guided Skill Memory Framework for Compositional Embodied Manipulation**|Changyuan Wang et.al.|[2608.05970](https://arxiv.org/abs/2608.05970)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-06**|**XEWorld: Can Action-Conditioned World Models Generalize to Unseen Robot Embodiments?**|Yixiang Chen et.al.|[2608.05799](https://arxiv.org/abs/2608.05799)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-08-06**|**Equipment-centric workpiece localization in near real-time using deep learning-based vision and event-driven finite state machines**|Dohyeon Kong et.al.|[2608.05744](https://arxiv.org/abs/2608.05744)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-06**|**In-Context VLA: Endowing Vision-Language-Action Models with Language via In-Context Post-Training and Agentic Tool Use**|Jiarui Yang et.al.|[2608.05738](https://arxiv.org/abs/2608.05738)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-06**|**SpaceVLA: Spatially Grounded VLA for Robotic Manipulation with User-Authored Grasp and Place Anchors**|Daniia Zinniatullina et.al.|[2608.05730](https://arxiv.org/abs/2608.05730)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-06**|**JoyAI-RA 0.5: Scaling Robot Manipulation Learning via Dual Action Alignment**|JoyAI-RA Team et.al.|[2608.05674](https://arxiv.org/abs/2608.05674)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-06**|**ARGUS: Aligning Robot Scene Geometry Under Shifting Views with Large 3D Vision Models**|Rishik Sathua et.al.|[2608.05579](https://arxiv.org/abs/2608.05579)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-05**|**World-to-Wrist: Task-Conditioned Future Wrist Modeling for Fine-Grained Robot Manipulation**|Yuhao Pan et.al.|[2608.05369](https://arxiv.org/abs/2608.05369)|**[link](https://huggingface.co/models/yuuu94/W2-VLA)**|
|**2026-08-05**|**VLAff: Vision-Language-Affordance Model for Unified Actionable Affordances**|Jihoon Oh et.al.|[2608.05215](https://arxiv.org/abs/2608.05215)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-05**|**BridgeVLA++: A Data-Efficient, Generalizable, and Memory-Augmented Vision-Language-Action Framework for 3D Manipulation**|Peiyan Li et.al.|[2608.05042](https://arxiv.org/abs/2608.05042)|**[link](https://github.com/BridgeVLA/BridgeVLA)**|
|**2026-08-05**|**Differential 6-DOF Pose Estimation with Provable First-Order Immunity to Camera Calibration Errors**|Yueqiang Zhang et.al.|[2608.04673](https://arxiv.org/abs/2608.04673)|**[link](https://github.com/Jianqiuer/Awesome6DPoseEstimation)**|
|**2026-08-06**|**MobileWAM: Bridging World Action Models to Mobile Manipulation with Chain-of-Foresight**|Zehua Fan et.al.|[2608.04657](https://arxiv.org/abs/2608.04657)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-08-05**|**Faster-WAM: Efficient Inference-Time Future Conditioning for Robust World Action Models**|Weiheng Zhao et.al.|[2608.04404](https://arxiv.org/abs/2608.04404)|**[link](https://huggingface.co/models/hustvl/FasterWAM)**|
|**2026-08-05**|**CofactVLA: Deconfounding Vision-Language-Action Models via Counterfactual Intervention**|Yan Zhang et.al.|[2608.04396](https://arxiv.org/abs/2608.04396)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-08-04**|**SiMDex: Mining Similar Egocentric Videos for Cross-Embodiment Dexterous Manipulation**|Nie Lin et.al.|[2608.04196](https://arxiv.org/abs/2608.04196)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-08-04**|**Kitchen Robotic Manipulation utilizing Foundation Models**|Myung-Hwan Jeon et.al.|[2608.04042](https://arxiv.org/abs/2608.04042)|**[link](https://github.com/Jianqiuer/Awesome6DPoseEstimation)**|
|**2026-08-04**|**When AI Wears Many Hats: The Role of Generative Artificial Intelligence in Marketing Education**|Unnati Narang et.al.|[2608.03973](https://arxiv.org/abs/2608.03973)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-04**|**LiLa-WAM: Lightweight Latent Reasoning World-Action Model for Robotic Manipulation**|Fan Yang et.al.|[2608.03701](https://arxiv.org/abs/2608.03701)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-05**|**RoboReact: Agentic Skill Distillation from Generated Egocentric Videos for Generalizable Whole-Body Manipulation**|Shuliang He et.al.|[2608.03387](https://arxiv.org/abs/2608.03387)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-04**|**GraspMeanFlow: SE(3)-Equivariant MeanFlow for Few-Step 6-DoF Grasp Generation**|Jiyong Kwon et.al.|[2608.03295](https://arxiv.org/abs/2608.03295)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-04**|**Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking**|Jinquan Zhang et.al.|[2608.03231](https://arxiv.org/abs/2608.03231)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-04**|**Accelerating Human-Aware Robot Trajectory Generation via Diffusion and Consistency Distillation**|Byeong-Il Ham et.al.|[2608.03159](https://arxiv.org/abs/2608.03159)|**[link](https://github.com/zezhishao/DailyArXiv)**|
|**2026-08-04**|**A Hierarchical Approach to Imitation Learning for Manipulation Tasks Requiring Time Varying Forces**|Rishabh Shukla et.al.|[2608.03103](https://arxiv.org/abs/2608.03103)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-04**|**A Wearable Stiffness-Rendering Haptic Device with a Honeycomb Jamming Mechanism for Bilateral Teleoperation**|Thomas M. Kwok et.al.|[2608.03002](https://arxiv.org/abs/2608.03002)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-04**|**EmbodiedVAE: Disentangled Video VAE for Efficient and Controllable Embodied Manipulation**|Jiayi Luo et.al.|[2608.02990](https://arxiv.org/abs/2608.02990)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-03**|**Ego2Robot: Scalable Robot Data Synthesis from Egocentric Human Data**|Ye Wang et.al.|[2608.02580](https://arxiv.org/abs/2608.02580)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-03**|**Grounded Semantic Re-Binding for Robust Instruction Generalization in Vision-Language-Action Models**|Zhaokai Yin et.al.|[2608.02497](https://arxiv.org/abs/2608.02497)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-03**|**Look Where It Matters: Adaptive Visual Refinement for Vision-Language-Action Models**|Jin Cui et.al.|[2608.02197](https://arxiv.org/abs/2608.02197)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-03**|**MANGO-Grasp: Mahalanobis Fields over Geometry-Oriented 3D Gaussians for Cross-Embodiment Dexterous Grasping**|Heng Zhang et.al.|[2608.02014](https://arxiv.org/abs/2608.02014)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-03**|**PhotoHOI: Synthesizing 3D Hand-Object Interactions from a Single RGB Photograph**|Zhenhao Zhang et.al.|[2608.01905](https://arxiv.org/abs/2608.01905)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-03**|**Multi-View Unified Camera Fields: Geometry-Shaped Action-Facing Representations for RGB-Only Multi-Camera VLA Policies**|Jiarui Yang et.al.|[2608.01826](https://arxiv.org/abs/2608.01826)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-03**|**AffordTrajDP: Dynamic Affordance-Guided Visuomotor Policy Learning for Robotic Manipulation**|Gaoyuan Wu et.al.|[2608.01603](https://arxiv.org/abs/2608.01603)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-03**|**Uncovering and Mitigating Positional Blind Spots in Vision-Language-Action Models**|Dongdong An et.al.|[2608.01573](https://arxiv.org/abs/2608.01573)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-02**|**Same violence, different answer: how AI responds to coercive control against women across languages**|Lyu Chang et.al.|[2608.01436](https://arxiv.org/abs/2608.01436)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-02**|**Hermite Curves as Trajectory Priors for Vision-Language-Action Models**|Qi Lv et.al.|[2608.01265](https://arxiv.org/abs/2608.01265)|**[link](https://github.com/zezhishao/DailyArXiv)**|
|**2026-08-02**|**Sparse Meets Dense: Correspondence Guided Robotic Manipulation with Rigid-Deformable Interactions**|Ziyu Zhu et.al.|[2608.01083](https://arxiv.org/abs/2608.01083)|**[link](https://github.com/Jianqiuer/Awesome6DPoseEstimation)**|
|**2026-08-02**|**OC-VLA++: Monocular Geometry-Guided Cross-View Consistency for Viewpoint-Robust Robotic Manipulation**|Tianyi Zhang et.al.|[2608.01066](https://arxiv.org/abs/2608.01066)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-08-02**|**GraRe: Grasp Candidate Re-Ranking for Frozen 6-DoF Grasp Detectors**|Jibao Yuan et.al.|[2608.00946](https://arxiv.org/abs/2608.00946)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-08-01**|**Grasp Execution Without a Planner: Configuration-Space Grasp Distance Fields with Certified Safety & Guaranteed Quality**|Clinton Enwerem et.al.|[2608.00600](https://arxiv.org/abs/2608.00600)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-08-01**|**SpatialAfford: Teaching Compact VLMs Where to Look and Where to Ground for Affordance**|Yufei Zhang et.al.|[2608.00502](https://arxiv.org/abs/2608.00502)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-31**|**Compliant Sphere Lattice Contact: Distributed Contact Modeling for Sphere-Based Robot Representations**|Nataliya Nechyporenko et.al.|[2608.00263](https://arxiv.org/abs/2608.00263)|**[link](https://github.com/Ponkux/DailyArXiv-cp)**|
|**2026-07-31**|**Developing Combined Manipulation and Locomotion Skills with Interaction Representation and Skill Composition**|Fanxing Meng et.al.|[2608.00208](https://arxiv.org/abs/2608.00208)|**[link](https://github.com/vergilshawn/Awesome-Humanoid-Robot-Learning)**|
|**2026-07-31**|**Diagnosing Compositional Generalization in Sequential Robot Tasks**|Yixiao Wang et.al.|[2607.29687](https://arxiv.org/abs/2607.29687)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-31**|**Balancing of Humanoid with Object Mass: Trade-off Analyses and Lifting Control**|Hyunjong Song et.al.|[2607.29625](https://arxiv.org/abs/2607.29625)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-31**|**WCM: A World Critic Model for Vision-Language-Action Reinforcement Learning**|Senyu Fei et.al.|[2607.29613](https://arxiv.org/abs/2607.29613)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-07-31**|**Safe Vision Language Action Models via Barrier Enhanced Flow Matching**|Kasra Sinaei et.al.|[2607.29569](https://arxiv.org/abs/2607.29569)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-31**|**TransGraspNet: Physically and Geometrically Consistent Manipulation of Transparent Labware**|Hailing Hu et.al.|[2607.29567](https://arxiv.org/abs/2607.29567)|**[link](https://github.com/wonderNefelibata/Awesome-LRM-Safety)**|
|**2026-07-31**|**SAGP: Semantic Affordance-Guided Grasp Planning via Coarse-Zone VLM Reasoning**|Muhayy Ud Din et.al.|[2607.29374](https://arxiv.org/abs/2607.29374)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-31**|**BWM: A Low-Cost High-Fidelity World Simulator for Robot Learning**|BWM Team et.al.|[2607.29302](https://arxiv.org/abs/2607.29302)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-07-31**|**TacPrint: A Wearable Fingertip Tactile Sensor for Human-to-Robot Contact Reproduction**|Yongxi Liu et.al.|[2607.29231](https://arxiv.org/abs/2607.29231)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-31**|**ActFovea: Runtime Safeguarding for VLA Policies via Spatiotemporal Visual-Action Consistency**|Wenda Yu et.al.|[2607.29169](https://arxiv.org/abs/2607.29169)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-30**|**FasTac: A Curved Multispectral Vision-Based Tactile Sensor for High-Speed High-Precision 3D Shape and Force Perception**|Xiaofan Lu et.al.|[2607.28416](https://arxiv.org/abs/2607.28416)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-30**|**QuantWAMs: Calibrating at the Right Granularity for World Action Models**|Jiacheng Zhou et.al.|[2607.28405](https://arxiv.org/abs/2607.28405)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-07-30**|**TacWAM: Anchor-Guided World Action Model with Mechanics-Aware Tactile Prediction**|Lei Jin et.al.|[2607.28391](https://arxiv.org/abs/2607.28391)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-07-30**|**UniCross: Unified Cross-Skill Dexterous Manipulation Synthesis**|Hui Zhang et.al.|[2607.28198](https://arxiv.org/abs/2607.28198)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-30**|**LM-GRASP: Instance-Specific Language Models for Combinatorial Construction via Online Imitation Learning**|Mohand Mezmaz et.al.|[2607.28135](https://arxiv.org/abs/2607.28135)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-30**|**The eROSITA X-ray luminosity function of active galactic nuclei**|W. Roster et.al.|[2607.27887](https://arxiv.org/abs/2607.27887)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-30**|**RoboBRIDGE: A Modular Framework for Bridging Policies to Robust Real-World Robotic Agents**|Sihyung Yoon et.al.|[2607.27881](https://arxiv.org/abs/2607.27881)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-30**|**RedFlow: Redirect Failure into Action-Level Corrections for Flow-matching VLA Policy**|Zhengyang Yan et.al.|[2607.27782](https://arxiv.org/abs/2607.27782)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-30**|**Cross-Embodiment Transfer via Behavior-Aligned Representations**|Ajay Sridhar et.al.|[2607.27549](https://arxiv.org/abs/2607.27549)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-29**|**TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM**|Hengyi Xie et.al.|[2607.27205](https://arxiv.org/abs/2607.27205)|**[link](https://huggingface.co/models/H-EmbodVis/TurboVLA)**|
|**2026-07-29**|**SymmGrid: Super-Scaling On-Robot Learning with Parallelized Symmetries and Egocentric-Exocentric Visual Perception**|Gabe Everett et.al.|[2607.26985](https://arxiv.org/abs/2607.26985)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-29**|**Practice Makes Policies: Bootstrapping and Consolidating Robotic Capabilities from Zero Human Demonstrations**|Jialiang Li et.al.|[2607.26809](https://arxiv.org/abs/2607.26809)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-29**|**Speech2Grasp: Data-Efficient Transfer of Text-Conditioned Grasp Detection to Speech in Humanoid Robots**|Hung Nguyen et.al.|[2607.26567](https://arxiv.org/abs/2607.26567)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-30**|**Fully distributed singularity-free prescribed-time stabilization of the continuous-time generalized adaptive Bellman-Ford algorithm**|Yuanqiu Mo et.al.|[2607.26424](https://arxiv.org/abs/2607.26424)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-28**|**Reeling It In: Flexible Needle Pick Up via Thread Manipulation for Autonomous Suturing**|Emma Huang et.al.|[2607.26337](https://arxiv.org/abs/2607.26337)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-28**|**MoMo: Dial Motion Mode in Robot Manipulation with Spatiotemporal Action Tokenization**|Yuhan Hu et.al.|[2607.26315](https://arxiv.org/abs/2607.26315)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-28**|**Hakka Kitchen: Engagement with Culinary Cultural Heritage Through Immersive Game Play**|Jingle Huang et.al.|[2607.26183](https://arxiv.org/abs/2607.26183)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-28**|**S2A2: Audio-Visual Imitation Learning for Manipulation Tasks Using Acoustic Spatial Information**|Kaneyoshi Hiratsuka et.al.|[2607.26047](https://arxiv.org/abs/2607.26047)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-28**|**SAM3D-Guided Object-Centric Representation Alignment for Vision-Language-Action Models**|Zonghe Liu et.al.|[2607.25912](https://arxiv.org/abs/2607.25912)|**[link](https://github.com/liliu-avril/Awesome-Segment-Anything)**|
|**2026-07-28**|**Transformer Transformer: A Unified Model for Motion-Conditioned Robot Co-design**|Huy Ha et.al.|[2607.25798](https://arxiv.org/abs/2607.25798)|**[link](https://github.com/real-stanford/transformer-transformer)**|
|**2026-07-28**|**When Does Legacy Data Start to Help? Emergent Transfer in Cross-Configuration Robot Learning**|Tao Wang et.al.|[2607.25593](https://arxiv.org/abs/2607.25593)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-28**|**A Causality-aware Infer-diagnose-refine Framework for Test-time Modality Adaptation in VLA Models**|Haoyu Zhang et.al.|[2607.25516](https://arxiv.org/abs/2607.25516)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-28**|**Decompose and Reorganize: Planning with Primitives and Visuomotor Policies Learned from Demonstrations**|Yizhou Chen et.al.|[2607.25397](https://arxiv.org/abs/2607.25397)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-28**|**VisualPatchWorld: Code World Models as Latent Structured Representations for Planning**|Jiaxin Bai et.al.|[2607.25236](https://arxiv.org/abs/2607.25236)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-07-27**|**ObjectEMS: Electrical Muscle Stimulation Without Electrodes on the User**|Yun Ho et.al.|[2607.25084](https://arxiv.org/abs/2607.25084)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-27**|**FIRMGrasp: A Friction-Informed Risk Margin for Robust Grasp Synthesis**|Clinton Enwerem et.al.|[2607.25049](https://arxiv.org/abs/2607.25049)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-27**|**NEO: NeRF It Once, Edit It Many Times for Continuous Object Manipulation**|Mikołaj Zieliński et.al.|[2607.24538](https://arxiv.org/abs/2607.24538)|**[link](https://github.com/wangqiannudt/nerf-arxiv-daily)**|
|**2026-07-27**|**ArmnetBench v0.1: Parallel Real-World Evaluation of Manipulation Policies on a Low-Cost Arm Farm**|Praveen Selvaraj et.al.|[2607.24481](https://arxiv.org/abs/2607.24481)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-27**|**PAC-DP: PAC-Bayesian Diffusion Policy Learning**|Mohammad Hasan Yeganegi et.al.|[2607.24296](https://arxiv.org/abs/2607.24296)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-27**|**FeelWorld: Visuo-Tactile World Model for Hierarchical Contact Prediction and Planning**|Wenxuan Ma et.al.|[2607.24267](https://arxiv.org/abs/2607.24267)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-27**|**DeVA: Decoupled Video-Action Model with physical guidance for robot policy learning**|Mengqi Zhang et.al.|[2607.24159](https://arxiv.org/abs/2607.24159)|**[link](https://huggingface.co/models/mengqz9/DeVA)**|
|**2026-07-27**|**EEGForceFusion: Joint Tokenised-Continuous Representation Learning for Subject-Independent Grasp Force Decoding**|Sankalp Sunil Turankar et.al.|[2607.24126](https://arxiv.org/abs/2607.24126)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-27**|**Towards simultaneous decoding of kinetic and kinematic movement parameters during grasp and lift task by noninvasive brain imaging**|Parth G. Dangi et.al.|[2607.24081](https://arxiv.org/abs/2607.24081)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-27**|**From Cognitive Architectures to Language Agents: A Mechanism-Level Review of Lineage, Convergence, and Migration Gaps**|Haodi Fan et.al.|[2607.23942](https://arxiv.org/abs/2607.23942)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-26**|**$N_0$ -TWAM: Scaling Tactile-Native World-Action Model for Contact-Rich Manipulation**|NeoteAI Team et.al.|[2607.23783](https://arxiv.org/abs/2607.23783)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-26**|**Real-Time Human-Centric World Modeling for Upper-Body Human-Object Interaction**|Chaonan Ji et.al.|[2607.23517](https://arxiv.org/abs/2607.23517)|**[link](https://github.com/Winn1y/Awesome-Human-Motion-Video-Generation)**|
|**2026-07-25**|**The Curse of Precision: A Data Scaling Law for High-Precision Robotic Manipulation**|Cuijie Xu et.al.|[2607.23108](https://arxiv.org/abs/2607.23108)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-24**|**Robot-Factored World Models via Robot Rendering**|Byungjun Kim et.al.|[2607.22535](https://arxiv.org/abs/2607.22535)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-07-24**|**ViTacWorld: Scaling Visuo-Tactile World Models for Contact-Rich Robot Manipulation**|Yunao Huang et.al.|[2607.22530](https://arxiv.org/abs/2607.22530)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-07-24**|**A Monolithic Hand with Asymmetric Origami Bending and Dual-chamber Actuators**|Nan Huang et.al.|[2607.22320](https://arxiv.org/abs/2607.22320)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-24**|**Design and Human Evaluation of Tactile Withdrawal Reflexes for a Skin-Covered Robot Arm**|Laura Babayeva et.al.|[2607.22249](https://arxiv.org/abs/2607.22249)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-24**|**One Hand Watches The Other: Dynamic Multi-Agent Cooperation for Sample-Efficient Bimanual Manipulation in Dynamic Environments**|Jan Ole von Hartz et.al.|[2607.22119](https://arxiv.org/abs/2607.22119)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-23**|**From Grasping to Speaking: Generative AI-Based Environment-Grounded VR Communication Training for Autistic Individuals**|Ziming Li et.al.|[2607.21769](https://arxiv.org/abs/2607.21769)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-23**|**Addressing the Orchestration Gap in Generalist Robots via Physical Agency**|Liane Galanti et.al.|[2607.21725](https://arxiv.org/abs/2607.21725)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-23**|**AXIS: A Growable Community-Driven Data Engine for Scalable Robot Manipulation**|Mengfei Zhao et.al.|[2607.21588](https://arxiv.org/abs/2607.21588)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-23**|**Complexity transition in the Dicke model of light-matter interaction**|Yicheng Zhang et.al.|[2607.21583](https://arxiv.org/abs/2607.21583)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-23**|**Scale Up Strategically: Learning Compositional Generalization via Bias-Aware Evaluation and Data Collection for Robotic Manipulation**|Yu Qi et.al.|[2607.21582](https://arxiv.org/abs/2607.21582)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-23**|**Grasp, Handover, Rotate: Bimanual Object Reorientation via Compositional Diffusion and Energy-Based Optimization**|Wun Lam Yeung et.al.|[2607.21341](https://arxiv.org/abs/2607.21341)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-23**|**TransBiolab: A Real-World Multi-View Dataset of Cluttered Transparent Biomedical Objects**|Ke Ma et.al.|[2607.21071](https://arxiv.org/abs/2607.21071)|**[link](https://github.com/Jianqiuer/Awesome6DPoseEstimation)**|
|**2026-07-24**|**GuidedAttention: Interpretable and Correctable Visual Attention for OOD-Robust Robot Manipulation via Imitation Learning**|Masaki Murooka et.al.|[2607.21049](https://arxiv.org/abs/2607.21049)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-23**|**TableVerse: A Large-scale Tabletop Dataset with Real-world Grounded Layouts for Generalizable Manipulation**|Boyuan Wang et.al.|[2607.21017](https://arxiv.org/abs/2607.21017)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-22**|**PhysCoRe: Physics-Corrected Residual World Models for Material-Aware Deformable Dynamics**|Haocheng Yin et.al.|[2607.20653](https://arxiv.org/abs/2607.20653)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-07-22**|**Towards Miniature Humanoid Tele-Loco-Manipulation Using Virtual Reality and Reinforcement Learning**|Nicolas Kosanovic et.al.|[2607.20399](https://arxiv.org/abs/2607.20399)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-22**|**SeededGrasp: Language-Guided Grasping in Complex Scenes with Multiple Embodiments**|Yang Xu et.al.|[2607.20207](https://arxiv.org/abs/2607.20207)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-22**|**V2F: Vision-Informed Grasp Force Prediction for Damage-Aware Robotic Handling of Date Fruits**|Shahd Shami et.al.|[2607.19804](https://arxiv.org/abs/2607.19804)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-22**|**LENS: LLM-guided Environment Simplification for Planning and Control in Clutter**|Aileen Liao et.al.|[2607.19633](https://arxiv.org/abs/2607.19633)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-21**|**Design and stability analysis of an underactuated hand with passively rotating fingers**|Léonie Plancoulaine et.al.|[2607.18950](https://arxiv.org/abs/2607.18950)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-21**|**WorldScape Policy 2.0: Empowering Steerable World Action Modeling with Reasoning-Augmented Memory**|Haisheng Su et.al.|[2607.18840](https://arxiv.org/abs/2607.18840)|**[link](https://huggingface.co/models/manifoldai-research/WorldScape-Policy-2)**|
|**2026-07-22**|**RoboInter1.5: A Holistic Intermediate Representation Suite for Embodied World Modeling and Robotic Manipulation**|Ziqin Wang et.al.|[2607.18709](https://arxiv.org/abs/2607.18709)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-07-20**|**FARO: Feasibility-Aware Robot Motion Optimization**|Michal Ciebielski et.al.|[2607.18362](https://arxiv.org/abs/2607.18362)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-20**|**FM-VLA: Force-based Memory for Vision-Language-Action Models in Contact-Rich Manipulation**|Ruicheng Li et.al.|[2607.18231](https://arxiv.org/abs/2607.18231)|**[link](https://github.com/zezhishao/DailyArXiv)**|
|**2026-07-20**|**Optimization of sim-to-real transfer in the humanoid robot NICO**|Juraj Gavura et.al.|[2607.18210](https://arxiv.org/abs/2607.18210)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-20**|**Closing the Loop in Humanoid VLA: Persistent 3D Object Tokens for Verifiable Loco-Manipulation**|Peng Ren et.al.|[2607.18016](https://arxiv.org/abs/2607.18016)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-20**|**RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model**|Kehan Li et.al.|[2607.17977](https://arxiv.org/abs/2607.17977)|**[link](https://huggingface.co/spaces/hugging-apps/rynnbrain1-1-2b-demo)**|
|**2026-07-20**|**ConceptTree: Bringing Semantic Transparency to Black-Box Decision Making for Robotic Manipulation**|Yongyan Wen et.al.|[2607.17861](https://arxiv.org/abs/2607.17861)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-20**|**A Compact 3D-Printed Soft Finger with Cyclic Hydraulic Actuation**|Zefang Mao et.al.|[2607.17840](https://arxiv.org/abs/2607.17840)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-20**|**Receiver-Centered Robot-to-Human Handover with Grasp-Aware Object Orientation**|Federico Biagi et.al.|[2607.17839](https://arxiv.org/abs/2607.17839)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-20**|**Seg2Grasp: A Robust Modular Suction Grasping in Bin Picking**|Hye-Jung Yoon et.al.|[2607.17757](https://arxiv.org/abs/2607.17757)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-20**|**DA-Fusion: Deformable Attention-Based RGB-D Fusion Transformer for Unseen Object Instance Segmentation**|Yesol Park et.al.|[2607.17754](https://arxiv.org/abs/2607.17754)|**[link](https://github.com/DoongLi/ICRA2025-Paper-List)**|
|**2026-07-20**|**HCPG-Flow:Hierarchical Contact-Progress Guidance for Flow-Policy Robot Manipulation**|Guanghu Xie et.al.|[2607.17651](https://arxiv.org/abs/2607.17651)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-20**|**On Optimal Event-Triggered Distributed Control for Stochastic Multi-Agent Systems via Reinforcement Learning**|Ziming Wang et.al.|[2607.17635](https://arxiv.org/abs/2607.17635)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-20**|**Predicting Grasping Compliance in Robotic Hands through Analytical-Model-Informed Neural Networks**|Qianwen Zhao et.al.|[2607.17541](https://arxiv.org/abs/2607.17541)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-19**|**From Perception to Assistance: Open-Vocabulary Shared Autonomy for Robotic Manipulation**|Murilo Vinicius da Silva et.al.|[2607.17323](https://arxiv.org/abs/2607.17323)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-18**|**Scene-SAM3D: Multi-View Scene Asset Generation Without Fine-Tuning**|Yuqi Zhang et.al.|[2607.16805](https://arxiv.org/abs/2607.16805)|**[link](https://github.com/liliu-avril/Awesome-Segment-Anything)**|
|**2026-07-17**|**Foresight Residual RL for Long-Horizon Robot Manipulation with Vision-Language-Action Models**|Yuhan Liu et.al.|[2607.16506](https://arxiv.org/abs/2607.16506)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-17**|**Apple- $π$ : Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence**|Runmao Yao et.al.|[2607.16401](https://arxiv.org/abs/2607.16401)|**[link](https://huggingface.co/spaces/yaorunmao/apple-pi-leaderboard)**|
|**2026-07-17**|**Handroid: Bridging Dexterous Hand and Humanoid**|Ruogu Li et.al.|[2607.16187](https://arxiv.org/abs/2607.16187)|**[link](https://github.com/Foruck/Awesome-Human-Motion)**|
|**2026-07-17**|**Dynamic Constraint Reconstruction Based Control Barrier Functions for Safety-Critical Control of High-Dimensional Manipulators**|Bingsheng Zhang et.al.|[2607.15961](https://arxiv.org/abs/2607.15961)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-17**|**Exo2EgoPose: Leveraging Exocentric Demonstrations for Vision-Language guided Egocentric 3D Hand Pose Forecasting**|Zhaofeng Shi et.al.|[2607.15890](https://arxiv.org/abs/2607.15890)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-17**|**Dynamics-Aware Meta-Imitation for Generalization to Unseen Robotic Manipulation**|Zhenduo Shang et.al.|[2607.15880](https://arxiv.org/abs/2607.15880)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-17**|**A Task-Space Receding Horizon Controller for Fast Collision Avoidance**|Mattia Penzotti et.al.|[2607.15733](https://arxiv.org/abs/2607.15733)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-17**|**AC-VLA: Robust Out-of-Distribution Action Execution via Compositional Learning**|Xiaojiang Peng et.al.|[2607.15714](https://arxiv.org/abs/2607.15714)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-17**|**Continuously Stable Structure through Plastic Deformation**|Junlong Xiao et.al.|[2607.15659](https://arxiv.org/abs/2607.15659)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-17**|**IMBench: A Benchmark for Intuitive Robotic Manipulation**|Anurag Maurya et.al.|[2607.15641](https://arxiv.org/abs/2607.15641)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-16**|**VTAP Gripper: Synergizing Fingertip Sensing and a Visuo-Tactile Active Palm for Dexterous In-Hand Manipulation**|Yuhao Zhou et.al.|[2607.15448](https://arxiv.org/abs/2607.15448)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-16**|**NeuroCommitSSM: Decision-Centric Shared Autonomy for Safe Assistive Manipulation via EEG-EMG-ET Commit Readiness**|Tipu Sultan et.al.|[2607.15395](https://arxiv.org/abs/2607.15395)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-16**|**RoboTTT: Context Scaling for Robot Policies**|Yunfan Jiang et.al.|[2607.15275](https://arxiv.org/abs/2607.15275)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-16**|**AHEAD: Anticipatory Hand-Driven Teleoperation via Human Intent Prediction**|Seok Joon Kim et.al.|[2607.15172](https://arxiv.org/abs/2607.15172)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-16**|**DriftWorld: Fast World Modeling through Drifting**|Susie Lu et.al.|[2607.15065](https://arxiv.org/abs/2607.15065)|**[link](https://github.com/knightnemo/Awesome-World-Models)**|
|**2026-07-16**|**Towards Human-like Physical Intelligence: LifelongVision-Language-Action Learning for Robotic Manipulation**|Yao He et.al.|[2607.14852](https://arxiv.org/abs/2607.14852)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-16**|**Hybrid Rigid-Soft Robotic Gripper with Shape Adaptation, Uniform Force Distribution, and Self-Locking Capabilities**|Xi Chen et.al.|[2607.14730](https://arxiv.org/abs/2607.14730)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-16**|**Lights, Camera, Malfunction: When Illumination Robustness Leaves VLA Models Blind to Color**|Marino Watanabe et.al.|[2607.14698](https://arxiv.org/abs/2607.14698)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-16**|**Representation-Aligned Tactile Grounding for Contact-Rich Robotic Manipulation**|Ruilin Chen et.al.|[2607.14609](https://arxiv.org/abs/2607.14609)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-16**|**MIDAS Hand: Modular low-Impedance Direct-drive Anthropomorphic Sensing Hand**|Alvin Zhu et.al.|[2607.14487](https://arxiv.org/abs/2607.14487)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-16**|**Active Real-World Factor-Based Evaluation for Generalist Robot Policies**|Andrew Liao et.al.|[2607.14439](https://arxiv.org/abs/2607.14439)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-15**|**Beyond Visual Grasping: Benchmarking Complex Grasping from Detection to Execution**|Hanyi Zhang et.al.|[2607.14341](https://arxiv.org/abs/2607.14341)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-15**|**DiMaS: Distribution Matching for Steering Vision-Language-Action Models**|Pegah Khayatan et.al.|[2607.14280](https://arxiv.org/abs/2607.14280)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-15**|**Industrial Dexterity Benchmark: A Hardware-Software Benchmarking Platform for Industrial Dexterous Manipulation**|Honglu He et.al.|[2607.14021](https://arxiv.org/abs/2607.14021)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-15**|**Learning Robust Execution in Robotic Manipulation with Agentic Reinforcement Learning**|Xiaopeng Zhang et.al.|[2607.13818](https://arxiv.org/abs/2607.13818)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-15**|**Vision-Based Obstacle Separation for Strawberry Harvesting in Clusters Using Hierarchical Reinforcement Learning**|Teng Li et.al.|[2607.13799](https://arxiv.org/abs/2607.13799)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-15**|**Towards a Modular Bin-picking Framework for Handling Object Pose Uncertainties**|Frederik Hagelskjær et.al.|[2607.13698](https://arxiv.org/abs/2607.13698)|**[link](https://github.com/Jianqiuer/Awesome6DPoseEstimation)**|
|**2026-07-15**|**Anatomy of Uncertainty: Expressive Descriptors of Robotic Manipulator Motion for Non-verbal Communication in Human-Robot Collaboration**|Ridhima Bector et.al.|[2607.13696](https://arxiv.org/abs/2607.13696)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-15**|**Learning Physics-Guided Residual Dynamics for Deformable Object Simulation**|Shivansh Patel et.al.|[2607.13451](https://arxiv.org/abs/2607.13451)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-14**|**DenseReward: Dense Reward Learning via Failure Synthesis for Robotic Manipulation**|Yu Fang et.al.|[2607.13033](https://arxiv.org/abs/2607.13033)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-14**|**ExToken: Structured Exploration for Efficient Vision-Language-Action Reinforcement Fine-tuning**|Yilun Kong et.al.|[2607.12931](https://arxiv.org/abs/2607.12931)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-14**|**UR-VC: Unsupervised Robotic Value Correction for Time-Derived Progress Proxies**|Lirui Zhao et.al.|[2607.12892](https://arxiv.org/abs/2607.12892)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-14**|**Vision-Based Dribbling for Humanoid Soccer via Privileged Representation Learning**|Flavio Maiorana et.al.|[2607.12702](https://arxiv.org/abs/2607.12702)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-14**|**VistaVLA: Geometry- and Semantic-Aware 3D Gaussian-Grounded VLA for Robotic Manipulation**|Mohan Liu et.al.|[2607.12356](https://arxiv.org/abs/2607.12356)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-14**|**Reducing Temporal Redundancy for Efficient Vision-Language-Action Inference**|Yuzhou Wu et.al.|[2607.12287](https://arxiv.org/abs/2607.12287)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-13**|**More than a Manipulator: Planning Propellant-Free Attitude Maneuvers for Free-Floating Spacecraft**|Harsh G. Bhundiya et.al.|[2607.12130](https://arxiv.org/abs/2607.12130)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-13**|**Robust In-Hand Manipulation via Priors in Reinforcement Learning and Mechanical Design**|Yifei Chen et.al.|[2607.12105](https://arxiv.org/abs/2607.12105)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-13**|**Mixture of Frames Policy: Multi-Frame Action Denoising for Bimanual Mobile Manipulation**|Dian Wang et.al.|[2607.11884](https://arxiv.org/abs/2607.11884)|**[link](https://huggingface.co/datasets/dian-wang/mof-datasets)**|
|**2026-07-13**|**Trajectory Planning and Certification for 3-DOF Robot Manipulators Using Real Quantifier Elimination Based on Comprehensive Gröbner Systems**|Yu Nakai et.al.|[2607.11657](https://arxiv.org/abs/2607.11657)|**[link](https://github.com/zezhishao/DailyArXiv)**|
|**2026-07-13**|**Towards Human-level Dexterous Teleoperation**|Puhao Li et.al.|[2607.11481](https://arxiv.org/abs/2607.11481)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-13**|**EDAR: Learning Environment-Dependent Action Representations for Robotic Manipulation**|Yuecheng Xu et.al.|[2607.11427](https://arxiv.org/abs/2607.11427)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-13**|**VIA: Visual Interface Agent for Robot Control**|Hengyuan Hu et.al.|[2607.11119](https://arxiv.org/abs/2607.11119)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-13**|**PAKE: Learning Whole-Body Loco-Manipulation with Partial Kinematic Embeddings**|Zhengmao He et.al.|[2607.11041](https://arxiv.org/abs/2607.11041)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-13**|**GraspGraphNet: Graph-Structured Multi-Embodiment Dexterous Grasp Generation**|Yeonseo Lee et.al.|[2607.11031](https://arxiv.org/abs/2607.11031)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-13**|**SegDiff: Segmented Trajectory Diffusion for Consistent and Adaptive Robot Manipulation**|Haidong Cao et.al.|[2607.11027](https://arxiv.org/abs/2607.11027)|**[link](https://github.com/zezhishao/DailyArXiv)**|
|**2026-07-12**|**A Single Diffusion-Policy Controller for Multi-Task Block Pushing with Zero-Shot Sim-to-Real Transfer**|Haitong Ma et.al.|[2607.10892](https://arxiv.org/abs/2607.10892)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-12**|**Embark Now: User Demand Oriented Framework for Multi-day Urban Travel Itinerary Planning**|Rongbo Qi et.al.|[2607.10651](https://arxiv.org/abs/2607.10651)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-11**|**SUREFlow: State-space Uncertainty-aware REsidual Flow Matching for Robust Robot Manipulation**|Md Tanvir Islam et.al.|[2607.10504](https://arxiv.org/abs/2607.10504)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-11**|**GRASP: GRanularity-Aware Search Policy for Agentic RAG**|Varun Gandhi et.al.|[2607.10463](https://arxiv.org/abs/2607.10463)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-11**|**VINE: Taming Generative Control Policies for Reinforcement Learning**|Rushuai Yang et.al.|[2607.10369](https://arxiv.org/abs/2607.10369)|**[link](https://github.com/iszhanjiawei/flow_matching_arxiv_daily)**|
|**2026-07-11**|**PhysMRV: Physical Memory Retrieval and Verification for Physics Plausibility Reasoning**|Wenyuan Wang et.al.|[2607.10190](https://arxiv.org/abs/2607.10190)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-11**|**On the Efficiency of LoRA Fine-Tuning for Vision-Language-Action Models in Industrial Robotic Manipulation**|Finn Ferchau et.al.|[2607.10172](https://arxiv.org/abs/2607.10172)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-11**|**TAC-LOCO: Unified Whole-Body Control for Quadrupedal TACtile-Informed LOCO-Manipulation**|Muqun Hu et.al.|[2607.10132](https://arxiv.org/abs/2607.10132)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-10**|**PinFT: Miniature 5-Axis Force/Torque Sensor Embeddable to Tweezer-like Tool**|Leo King et.al.|[2607.10000](https://arxiv.org/abs/2607.10000)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-10**|**Robo-ValueRL: Reliable Value Estimation for Offline-to-Online Reinforcement Learning**|Wenke Xia et.al.|[2607.09866](https://arxiv.org/abs/2607.09866)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-07-10**|**B-spline Policy: Accelerating Manipulation Policies via B-spline Action Representations**|Xiaoshen Han et.al.|[2607.09648](https://arxiv.org/abs/2607.09648)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-10**|**DemoBridge: A Simulation-in-the-Loop Toolkit for Single-View Human Demonstration Retargeting**|Zehao Wang et.al.|[2607.09519](https://arxiv.org/abs/2607.09519)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-10**|**One-Shot Multimodal Learning from Demonstration with Force-Constrained Elastic Maps**|Brendan Hertel et.al.|[2607.09515](https://arxiv.org/abs/2607.09515)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-07-10**|**PhysV2A: Reachability-Gated and Semantic-Mask-Constrained Feasibility Completion for Video-to-Robot Manipulation**|Haohui Huang et.al.|[2607.09365](https://arxiv.org/abs/2607.09365)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-10**|**Robot Trajectron V3: A Probabilistic Shared Control Framework for SE(3) Manipulation**|Pinhao Song et.al.|[2607.09315](https://arxiv.org/abs/2607.09315)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-07-10**|**GenVid2Robot: From Video Generation to Robot Manipulation via Rigid-Geometric Consistency**|Haohui Huang et.al.|[2607.09191](https://arxiv.org/abs/2607.09191)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-07-09**|**SplatCtrl: Perception-Action Coupling via Gaussian Scene Representations and Reactive Robot Control**|Siddarth Jain et.al.|[2607.08948](https://arxiv.org/abs/2607.08948)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-09**|**Typicality of Steering for Two-qubit States**|Gerard Anglès Munné et.al.|[2607.08762](https://arxiv.org/abs/2607.08762)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-09**|**DexVerse: A Modular Benchmark for Multi-Task, Multi-Embodiment Dexterous Manipulation**|Yunchao Yao et.al.|[2607.08751](https://arxiv.org/abs/2607.08751)|**[link](https://github.com/BaiShuanghao/Awesome-Robotics-Manipulation)**|
|**2026-07-09**|**Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?**|Masatoshi Tateno et.al.|[2607.08514](https://arxiv.org/abs/2607.08514)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-09**|**Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agents**|Yixian Zhang et.al.|[2607.08448](https://arxiv.org/abs/2607.08448)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-08**|**EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Data**|Baoyu Li et.al.|[2607.08436](https://arxiv.org/abs/2607.08436)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-09**|**SkillPlug: Unsupervised Skill Mining for Few-Shot Adaptation in Robotic Manipulation**|Zi-han Ding et.al.|[2607.08354](https://arxiv.org/abs/2607.08354)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-08**|**Monocular Vision Based Control Framework for Grasping**|Shail Jadav et.al.|[2607.07897](https://arxiv.org/abs/2607.07897)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-08**|**Idiobionics: The Unification of Privacy and Intelligent Robotic Prostheses**|Kwesi Afari Darfoor et.al.|[2607.07775](https://arxiv.org/abs/2607.07775)|**[link](https://github.com/Trustworthy-AI-Group/Adversarial_Examples_Papers)**|
|**2026-07-08**|**Continuous and large-scale: ELEANOR, the soft architected arm inspired by the elephant trunk**|Giovanna A. Naselli et.al.|[2607.07622](https://arxiv.org/abs/2607.07622)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-08**|**Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation**|Hongyu Qu et.al.|[2607.07608](https://arxiv.org/abs/2607.07608)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-08**|**Smooth Operator: A Real-Time Sampling-Based Algorithm for Kinematic Hand Retargeting**|Robert Jomar Malate et.al.|[2607.07491](https://arxiv.org/abs/2607.07491)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-08**|**Initiation Safety: A Missing Dimension in Generalist-Robot Safety**|Zhijin Meng et.al.|[2607.07420](https://arxiv.org/abs/2607.07420)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-09**|**TouchWorld: A Predictive and Reactive Tactile Foundation Model for Dexterous Manipulation**|Jianyi Zhou et.al.|[2607.07287](https://arxiv.org/abs/2607.07287)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-08**|**GeoProp: Grounding Robot State in Vision for Generalist Manipulation**|Guoyang Zhao et.al.|[2607.07101](https://arxiv.org/abs/2607.07101)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-08**|**PriGo: Test-Time Primitive Guidance to Diffusion and Flow Policies for Adaptive Robotic Manipulation**|Zezeng Li et.al.|[2607.07076](https://arxiv.org/abs/2607.07076)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-08**|**A Closed-Loop Multi-Agent Framework for Robust Multi-Robot Manipulation**|Yi-Xiang He et.al.|[2607.06990](https://arxiv.org/abs/2607.06990)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-07**|**A Continual Learning Framework for Adaptive Control of Modular Soft Robots**|Nilay Kushawaha et.al.|[2607.06740](https://arxiv.org/abs/2607.06740)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-07**|**NativeMEM: Native Memory Compression for Long-Horizon Robotic Manipulation**|Ziye Wang et.al.|[2607.06678](https://arxiv.org/abs/2607.06678)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-07**|**Lift3D-VLA: Lifting VLA Models to 3D Geometry and Dynamics-Aware Manipulation**|Jiaming Liu et.al.|[2607.06564](https://arxiv.org/abs/2607.06564)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-07**|**RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation**|Haoyu Zhao et.al.|[2607.06559](https://arxiv.org/abs/2607.06559)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-07**|**WristMimic: Full-Body Humanoid Control with Wrist-Guided Manipulation**|Wongyun Yu et.al.|[2607.06438](https://arxiv.org/abs/2607.06438)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-07**|**Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinement**|Ryuji Oi et.al.|[2607.06370](https://arxiv.org/abs/2607.06370)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-07**|**Diagnosing Semantic Handoff Failures in Agent-Orchestrated Vision-Language-Action Skill Composition**|Ke Rui et.al.|[2607.06256](https://arxiv.org/abs/2607.06256)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-07**|**Calf-Integrated Arms for Bimanual Quadruped Loco-Manipulation**|Yan Pan et.al.|[2607.06186](https://arxiv.org/abs/2607.06186)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-07**|**DexTele: A Dual-Arm Dexterous Teleoperation System Based on Motion Retargeting and Adaptive Force Control**|Yuanchuan Lai et.al.|[2607.05883](https://arxiv.org/abs/2607.05883)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-07**|**GraspIT: A Dataset Bridging the Sim-to-Real gap and back for Validated Grasping SE(3) Pose Generation**|Paul Koch. Adem Karakurt et.al.|[2607.05869](https://arxiv.org/abs/2607.05869)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-06**|**Dynamic Evaluation of Classical and Control-Aware Optimal Trajectory Planning in Robot Manipulators**|Bhanuka Dayawansa et.al.|[2607.05544](https://arxiv.org/abs/2607.05544)|**[link](https://github.com/zezhishao/DailyArXiv)**|
|**2026-07-06**|**Learning 4D Geometric Priors for Inference-Efficient World Action Models**|Jianjun Zhang et.al.|[2607.05468](https://arxiv.org/abs/2607.05468)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-06**|**Deform360: A Massive Multi-view Visuotactile Dataset for Deformable World Models**|Hongyu Li et.al.|[2607.05390](https://arxiv.org/abs/2607.05390)|**[link](https://huggingface.co/datasets/brownu/deform360)**|
|**2026-07-06**|**InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action for Compositional Generalization**|Haoxiang Ma et.al.|[2607.04988](https://arxiv.org/abs/2607.04988)|**[link](https://huggingface.co/spaces/hugging-apps/internvla-a1-5-vla-explorer)**|
|**2026-07-06**|**Closing the Reality Gap: Zero-Shot Sim-to-Real Deployment for Dexterous Force-Based Grasping and Manipulation**|Zhe Zhao et.al.|[2607.04940](https://arxiv.org/abs/2607.04940)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-06**|**DSWAM: A Dual-System World Action Foundation Model for Fine-Grained Robot Manipulation**|Jian Zhu et.al.|[2607.04927](https://arxiv.org/abs/2607.04927)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-06**|**CAC-VLA: Context-Gated Action Conditioning for Vision-Language-Action Models**|Yifu Xiong et.al.|[2607.04816](https://arxiv.org/abs/2607.04816)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-06**|**Geometry-Aware Motion Latents for Learning Robust Manipulation Policies**|Yunchao Zhang et.al.|[2607.04714](https://arxiv.org/abs/2607.04714)|**[link](https://github.com/Songwxuan/Embodied-AI-Paper-TopConf)**|
|**2026-07-06**|**KAM-WM: Kinematic Affordance Maps from Latent World Models for Robot Manipulation**|Xinyu Shao et.al.|[2607.04652](https://arxiv.org/abs/2607.04652)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-06**|**Simple-to-Complex Structured Demonstrations for Vision-Language-Action Learning**|Xinchuan Qiu et.al.|[2607.04591](https://arxiv.org/abs/2607.04591)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-06**|**HUGS: Guiding Unified Dexterous Grasp Synthesis Across Modes and Scales via Learned Human Priors**|Mingrui Yu et.al.|[2607.04554](https://arxiv.org/abs/2607.04554)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-07**|**RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies**|Tianxing Chen et.al.|[2607.04434](https://arxiv.org/abs/2607.04434)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-05**|**Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling**|Fan Feng et.al.|[2607.04409](https://arxiv.org/abs/2607.04409)|**[link](https://github.com/Songwxuan/Embodied-AI-Paper-TopConf)**|
|**2026-07-05**|**HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models**|Angen Ye et.al.|[2607.04265](https://arxiv.org/abs/2607.04265)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-05**|**SoftVTBench: A Safety-Aware Visuo-Tactile Benchmark for Physically Constrained Robotic Manipulation of Deformable Objects**|Bowen Jing et.al.|[2607.04234](https://arxiv.org/abs/2607.04234)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-05**|**XS-VLA: Coupling Coarse-grained Spatial Distillation with Latent Flow Matching for Lightweight Robotic Control**|Lei Iok Tong et.al.|[2607.04171](https://arxiv.org/abs/2607.04171)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-05**|**ACE: Agentic Control for Embodied Manipulation via Zero-shot Workflow Reasoning**|Iok Tong Lei et.al.|[2607.04162](https://arxiv.org/abs/2607.04162)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-04**|**Worldscape-MoE: A Unified Mixture-of-Experts World Model for Scalable Heterogeneous Action Control**|Jianjie Fang et.al.|[2607.03964](https://arxiv.org/abs/2607.03964)|**[link](https://huggingface.co/models/EmbodiedCity/Worldscape-MoE)**|
|**2026-07-04**|**Occluding the Solution Space: Planner-Agnostic Adversarial Attacks on Tolerance-Aware Manipulation**|Keke Tang et.al.|[2607.03758](https://arxiv.org/abs/2607.03758)|**[link](https://github.com/Trustworthy-AI-Group/Adversarial_Examples_Papers)**|
|**2026-07-04**|**GRASP: Graph-Reasoning Aided Survey Planning for High-Fidelity Related Work Generation**|Haoming Li et.al.|[2607.03709](https://arxiv.org/abs/2607.03709)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-04**|**CoRE-VLA: Towards Scalable and Robust Vision-Language-Action Modeling via Conditional Routing of Experts**|Haozhe Zhang et.al.|[2607.03693](https://arxiv.org/abs/2607.03693)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-03**|**ROBOCYCLE: Autonomous Dual-Arm Robotic Manipulation and Coordination for Recycling Applications**|Rubén de J. Hilario-Cruz et.al.|[2607.03616](https://arxiv.org/abs/2607.03616)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-02**|**WorldSample: Closed-loop Real-robot RL with World Modelling**|Yuquan Xue et.al.|[2607.02431](https://arxiv.org/abs/2607.02431)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-02**|**The Moving Eye: Enhancing VLA Spatial Generalization via Hybrid Dynamic Data Collection**|Jincheng Tang et.al.|[2607.02322](https://arxiv.org/abs/2607.02322)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-02**|**Influence of Radial Basis Activation Functions on Intelligent Controller for Robotic Manipulators**|Kimmo Paldanius et.al.|[2607.02167](https://arxiv.org/abs/2607.02167)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-02**|**VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon**|Yi Pan et.al.|[2607.01804](https://arxiv.org/abs/2607.01804)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-02**|**JointHOI: Jointly Generating Contact Maps Enhances Hand Object Interaction Generation**|Mingyeong Song et.al.|[2607.01768](https://arxiv.org/abs/2607.01768)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-02**|**CoRe: Combined Rewards with Vision-Language Model Feedback for Preference-Aligned Reinforcement Learning**|Hexian Ni et.al.|[2607.01721](https://arxiv.org/abs/2607.01721)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-02**|**Imagining the Sense of Touch: Touch-Informed Manipulation via Imagined Tactile Representations**|Zhiyuan Zhang et.al.|[2607.01684](https://arxiv.org/abs/2607.01684)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-02**|**VLAFlow: A Unified Training Framework for Vision-Language-Action Models via Co-training and Future Latent Alignment**|Guoyang Xia et.al.|[2607.01586](https://arxiv.org/abs/2607.01586)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-01**|**Neuro-Symbolic Safety Guidance for Vision-Language-Action Models via Constrained Flow Matching**|William English et.al.|[2607.01378](https://arxiv.org/abs/2607.01378)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-01**|**Human-Centric Transferable Tactile Pre-Training for Dexterous Robotic Manipulation**|Chi Zhang et.al.|[2607.01067](https://arxiv.org/abs/2607.01067)|**[link](https://huggingface.co/models/BeingBeyond/TTP)**|
|**2026-07-01**|**AutoSpeed: Annotation-Free Stage-Adaptive Motion Speed Learning for Robot Manipulation**|Qingda Hu et.al.|[2607.01051](https://arxiv.org/abs/2607.01051)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-01**|**DeWorldSG: Depth-Aware 3D Semantic Scene Graph Generation via World-Model Priors**|Seok-Young Kim et.al.|[2607.00889](https://arxiv.org/abs/2607.00889)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-07-01**|**Task-Relevant Representation Decoupling for Visual Reinforcement Learning Generalization**|Jinwen Wang et.al.|[2607.00796](https://arxiv.org/abs/2607.00796)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-01**|**From Technical Metrics to User Perception: A User Study of a Multimodal Human-Robot Interaction System for Object Detection and Grasping**|Jian Song et.al.|[2607.00530](https://arxiv.org/abs/2607.00530)|**[link](https://github.com/liliu-avril/Awesome-Segment-Anything)**|
|**2026-07-01**|**Robust Operational Space Control with Conformal Disturbance Bounds for Safe Redundant Manipulation**|Wenhua Liu et.al.|[2607.00424](https://arxiv.org/abs/2607.00424)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-01**|**Unleashing More Actions via Action Compositional Training for VLA Models**|Kai Peng et.al.|[2607.00351](https://arxiv.org/abs/2607.00351)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-02**|**DVG-WM: Disentangled Video Generation Enables Efficient Embodied World Model for Robotic Manipulation**|Ziyu Shan et.al.|[2606.32028](https://arxiv.org/abs/2606.32028)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-30**|**Freeform Preference Learning for Robotic Manipulation**|Marcel Torne et.al.|[2606.32027](https://arxiv.org/abs/2606.32027)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-30**|**OopsieVerse: A Safety Benchmark with Damage-Aware Simulation for Robot Manipulation**|Arnav Balaji et.al.|[2606.31993](https://arxiv.org/abs/2606.31993)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-30**|**CoDex: Learning Compositional Dexterous Functional Manipulation without Demonstrations**|Bowen Jiang et.al.|[2606.31909](https://arxiv.org/abs/2606.31909)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-30**|**Z-1: Efficient Reinforcement Learning for Vision-Language-Action Models**|Lang Cao et.al.|[2606.31846](https://arxiv.org/abs/2606.31846)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-30**|**RoboTacDex: A Dexterous Visual-Tactile-Action Dataset for Humanoid Manipulation**|Xinyi Wang et.al.|[2606.31836](https://arxiv.org/abs/2606.31836)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-30**|**UniTacVLA: Unified Tactile Understanding and Prediction in Vision Language Action Models**|Xidong Zhang et.al.|[2606.31723](https://arxiv.org/abs/2606.31723)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-30**|**RCT: A Robot-Collected Touch-Vision-Language Dataset for Tactile Generalization**|Jingbo He et.al.|[2606.31694](https://arxiv.org/abs/2606.31694)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-30**|**HABIT: Human-Aware Behavior and Interaction Training Dataset for Robot Manipulation**|Jaehwi Song et.al.|[2606.31682](https://arxiv.org/abs/2606.31682)|**[link](https://huggingface.co/datasets/configint/HABIT)**|
|**2026-06-30**|**MV-GEL: Language-Driven Multi-View Geometric Entity Localization on Meshes**|Kartik Bali et.al.|[2606.31533](https://arxiv.org/abs/2606.31533)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-30**|**Robustness of Robotic Manipulation: Foundations and Frontiers**|Yifei Dong et.al.|[2606.31494](https://arxiv.org/abs/2606.31494)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-30**|**Stage-Transition Dense Reward Modeling for Reinforcement Learning**|Yang Yang et.al.|[2606.31377](https://arxiv.org/abs/2606.31377)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-01**|**3D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidance**|Dongyoon Hwang et.al.|[2606.31329](https://arxiv.org/abs/2606.31329)|**[link](https://huggingface.co/models/DAVIAN-Robotics/3D_HAMSTER)**|
|**2026-06-30**|**Agentic RAG-VLM: Affordance-Aware Retrieval-Augmented Generation with Self-Reflective Planning for Robotic Grasping**|Tao Chen et.al.|[2606.31200](https://arxiv.org/abs/2606.31200)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-30**|**ELASTIC: Efficiently Learning to Adaptively Scale Test-Time Compute for Generative Control Policies**|Andrew Zou Li et.al.|[2606.31132](https://arxiv.org/abs/2606.31132)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-30**|**Efficient Sim-to-Real Transfer of World-Action Models from Synthetic Priors**|Zixing Wang et.al.|[2606.31101](https://arxiv.org/abs/2606.31101)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-30**|**Dense Structural Priors for Sparse Functional Landmark Localization in Surgical Videos**|Chenyan Jing et.al.|[2606.31007](https://arxiv.org/abs/2606.31007)|**[link](https://github.com/liliu-avril/Awesome-Segment-Anything)**|
|**2026-06-29**|**Multisensory Continual Learning: Adapting Pretrained Visuomotor Policies to Force**|Jaden Clark et.al.|[2606.30988](https://arxiv.org/abs/2606.30988)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-29**|**The Quadruped Soft Tail: Compliant Grasping and Swabbing for Contamination Surveys in Harsh Environments**|Harald Minde Hansen et.al.|[2606.30900](https://arxiv.org/abs/2606.30900)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-29**|**From Grasps to Dexterity: Large-Scale Grasp Pretraining for Dexterous Manipulation**|Ying Yuan et.al.|[2606.30749](https://arxiv.org/abs/2606.30749)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-29**|**VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes**|Yen-Jen Wang et.al.|[2606.30645](https://arxiv.org/abs/2606.30645)|**[link](https://github.com/YanjieZe/Paper-List)**|
|**2026-06-29**|**Sequential Planning via Anchored Robotic Keypoints**|Bryce Grant et.al.|[2606.30613](https://arxiv.org/abs/2606.30613)|**[link](https://github.com/InsomaniacElf/sg-tamil-tts-resources-)**|
|**2026-06-29**|**Grasp-Oriented Non-Prehensile Manipulation via Learning a Graspability Field**|Licheng Zhong et.al.|[2606.30474](https://arxiv.org/abs/2606.30474)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-29**|**A note on the maximal covering location problem with customer preference ordering**|Elisabeth Gaar et.al.|[2606.30379](https://arxiv.org/abs/2606.30379)|**[link](https://github.com/RLCL-EIT/robotics_arxiv_daily)**|
|**2026-06-29**|**X-Morph: Human Motion Priors for Scalable Robot Learning Across Morphologies**|Ritwik Sharma et.al.|[2606.30290](https://arxiv.org/abs/2606.30290)|**[link](https://github.com/Foruck/Awesome-Human-Motion)**|
|**2026-06-29**|**ConCent: Contact-Centric Real-to-Sim-to-Real Learning from One Demonstration**|Heecheol Kim et.al.|[2606.30268](https://arxiv.org/abs/2606.30268)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-29**|**KYON: Semi-Modular Wheel-Legged Quadruped With Agile Bimanual Capability**|Luca Rossini et.al.|[2606.30243](https://arxiv.org/abs/2606.30243)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-29**|**OpenSPM: An Environment-Transferable Robotic Key Spatial Pose Memory and Closed-Loop High-Frequency Flow-Matching Action Generation Model**|Iok Tong Lei et.al.|[2606.29936](https://arxiv.org/abs/2606.29936)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-29**|**DCGrasp: Distance-aware Controllable Grasp Generation**|Hiroyasu Akada et.al.|[2606.29924](https://arxiv.org/abs/2606.29924)|**[link](https://github.com/JiaHongZ/embodied_intelligence_paper)**|
|**2026-06-29**|**Critical Interval MSE: Toward Reliable Offline Validation for Robot Manipulation Policies**|Haoxu Huang et.al.|[2606.29898](https://arxiv.org/abs/2606.29898)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-29**|**AI Training Manager: Bounded Closed-Loop Control of Adaptive Training Recipes**|Anjali Rao et.al.|[2606.29871](https://arxiv.org/abs/2606.29871)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-28**|**CORE: Common Outcome Regularities from Action-Free Visual Demonstrations for Robot Manipulation**|Juyi Sheng et.al.|[2606.29517](https://arxiv.org/abs/2606.29517)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-28**|**Learning Transferable Dynamics Priors from Action to World Modeling**|Ze Huang et.al.|[2606.29501](https://arxiv.org/abs/2606.29501)|**[link](https://github.com/Valiant-Cat/hfpaper)**|
|**2026-06-28**|**Event-VLA: Action-Conditioned Event Fusion for Robust Vision-Language-Action Model**|Jiaxin Liu et.al.|[2606.29384](https://arxiv.org/abs/2606.29384)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-28**|**LAMP: Long-Horizon Adaptive Manipulation Planning for Multi-Robot Collaboration in Cluttered Space**|Shuai Zhou et.al.|[2606.29358](https://arxiv.org/abs/2606.29358)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-28**|**Enhancing Part-Level Point Grounding for Any Open-Source MLLMs**|Jin-Cheng Jhang et.al.|[2606.29267](https://arxiv.org/abs/2606.29267)|**[link](https://github.com/52CV/CVPR-2026-Papers)**|
|**2026-06-28**|**AnyBody: Free-Form Whole-Body Humanoid Control from Arbitrary Keypoint Guidance**|Shuning Li et.al.|[2606.29209](https://arxiv.org/abs/2606.29209)|**[link](https://github.com/Foruck/Awesome-Human-Motion)**|
|**2026-06-27**|**Keypose Exploration: Efficient Automatic Trajectory Labelling and Cross-Embodiment Policy Transfer**|Yupu Lu et.al.|[2606.29028](https://arxiv.org/abs/2606.29028)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-27**|**HJ-SafeDMP: Hamilton-Jacobi Reachability-Guided Dynamic Movement Primitives for Provably Safe Robot Motion**|Siddhanth Ramesh et.al.|[2606.28995](https://arxiv.org/abs/2606.28995)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-27**|**You Only Touch Once: 6-DoF Object Pose Estimation from Single Tactile Contact**|Pengfei Ye et.al.|[2606.28899](https://arxiv.org/abs/2606.28899)|**[link](https://github.com/Jianqiuer/Awesome6DPoseEstimation)**|
|**2026-06-25**|**E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulation**|Wen Ye et.al.|[2606.27268](https://arxiv.org/abs/2606.27268)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-25**|**HumanoidUMI: Bridging Robot-Free Demonstrations and Humanoid Whole-Body Manipulation**|Hongwu Wang et.al.|[2606.27239](https://arxiv.org/abs/2606.27239)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-25**|**PhysReflect-VLA: Physical Feasibility and Self-Reflective Regulation for Reliable Vision-Language-Action Policies**|Jiayu Yang et.al.|[2606.27146](https://arxiv.org/abs/2606.27146)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-25**|**PAMAE: Phase-Aware-MoE Action Experts Towards Reliable Flow-Matching Vision-Language-Action Policies**|Jiayu Yang et.al.|[2606.27144](https://arxiv.org/abs/2606.27144)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-25**|**RelAfford6D: Relational 6D Affordance Graphs for Constraint-Driven Robotic Manipulation**|Guodong Zhang et.al.|[2606.27036](https://arxiv.org/abs/2606.27036)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-25**|**Humanoid-DART: Humanoid Loco-Manipulation using Diffusion-guided Augmentation through Relabeling and Tracking**|Pranav Debbad et.al.|[2606.26855](https://arxiv.org/abs/2606.26855)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-25**|**Improving Vision-Language-Action Model Fine-Tuning with Structured Stage and Keyframe Supervision**|Yuan Xu et.al.|[2606.26801](https://arxiv.org/abs/2606.26801)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-25**|**SSI-Policy: Learning Structured Scene Interfaces for Vision-Language Robotic Manipulation**|Kaijun Wang et.al.|[2606.26800](https://arxiv.org/abs/2606.26800)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-25**|**Learning Motion Feasibility from Point Clouds in Cluttered Environments**|Sajid Ansari et.al.|[2606.26700](https://arxiv.org/abs/2606.26700)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-25**|**Temporally Consistent Label Interpolation for Robust Surgical Multi-Task Learning under Challenging Conditions**|Garam Kim et.al.|[2606.26634](https://arxiv.org/abs/2606.26634)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-24**|**WatchAct: A Benchmark for Behavior-Grounded Robot Manipulation**|Baiqi Li et.al.|[2606.26443](https://arxiv.org/abs/2606.26443)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-24**|**Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly?**|Tyler Ga Wei Lum et.al.|[2606.26428](https://arxiv.org/abs/2606.26428)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-24**|**A System for Fast, Resilient, and Adaptable Loco-Manipulation Behaviors on Humanoid Robots**|Duncan William Calvert et.al.|[2606.26425](https://arxiv.org/abs/2606.26425)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-24**|**KRVF: A Source-Aware Semantic Voxel World Representation for Edge Mobile Manipulation**|Runfeng Ling et.al.|[2606.26321](https://arxiv.org/abs/2606.26321)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-24**|**OmniContact: Chaining Meta-Skills via Contact Flow for Generalizable Humanoid Loco-Manipulation**|Runyi Yu et.al.|[2606.26201](https://arxiv.org/abs/2606.26201)|**[link](https://huggingface.co/datasets/lightcone02/OmniContact-Dataset)**|
|**2026-06-24**|**Morphology-Specific Closed-Loop Control of Logarithmic-Spiral Continuum Arms via Online Jacobian Error Compensation**|Partha Datta et.al.|[2606.26188](https://arxiv.org/abs/2606.26188)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-24**|**Learning Action Priors for Cross-embodiment Robot Manipulation**|Dong Jing et.al.|[2606.26095](https://arxiv.org/abs/2606.26095)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-24**|**ForceBand: Learning Forceful Manipulation with sEMG**|Botao He et.al.|[2606.26093](https://arxiv.org/abs/2606.26093)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-24**|**Action ControlNet: A Lightweight Delay-Aware Adapter for Smooth Asynchronous Control in Vision-Language-Action Models**|Tiecheng Guo et.al.|[2606.25985](https://arxiv.org/abs/2606.25985)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-24**|**DSP-SLAM++: A Unified Framework for Multi-Class, High-Fidelity Object SLAM in the Wild**|Ahmad Kourani et.al.|[2606.25953](https://arxiv.org/abs/2606.25953)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-24**|**ROAD-VLA: Robust Online Adaptation via Self-Distillation for Vision-Language-Action Models**|Kejing Wang et.al.|[2606.25800](https://arxiv.org/abs/2606.25800)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-24**|**WOLF-VLA: Whole-Body Humanoid Optimal Locomotion Framework for Vision-Language-Action Learning**|Melya Boukheddimi et.al.|[2606.25591](https://arxiv.org/abs/2606.25591)|**[link](https://github.com/Foruck/Awesome-Human-Motion)**|
|**2026-06-24**|**One Body, Two Minds: Variable Autonomy Approach for a Co-embodied Robotic Hand**|Piotr Koczy et.al.|[2606.25575](https://arxiv.org/abs/2606.25575)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-24**|**AISPO: Enhancing Depth Reliability for Robotic Manipulation of Non-Lambertian Objects via Affine-Invariant Shape Prior**|Zhiming Chen et.al.|[2606.25503](https://arxiv.org/abs/2606.25503)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-24**|**Decoupling Semantics and Geometric Grounding: Spatial Visual Prompts for Language-Conditioned Imitation Learning**|Yanzhe Tang et.al.|[2606.25360](https://arxiv.org/abs/2606.25360)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-24**|**DynaMOMA: Instantaneous Prediction of Grasp Poses for Mobile Manipulation of Dynamic Objects**|Zhinan Yu et.al.|[2606.25295](https://arxiv.org/abs/2606.25295)|**[link](https://github.com/Blake-Jiang/ad-arxiv-daily)**|
|**2026-06-23**|**GRAFT: Graph-Based Affordance Transfer via Part Correspondence**|Mengying Lin et.al.|[2606.25241](https://arxiv.org/abs/2606.25241)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-23**|**RigPI: Dynamic Parameter Identification of Rigid Body via VLM-Seeded Differentiable Simulation**|Xincheng He et.al.|[2606.25212](https://arxiv.org/abs/2606.25212)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-23**|**World Value Models for Robotic Manipulation**|Zhihao Wang et.al.|[2606.24742](https://arxiv.org/abs/2606.24742)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-23**|**Beyond Monotonic Progress: Retry-Supervised Value Learning for Robot Imitation**|Xinyao Qin et.al.|[2606.24633](https://arxiv.org/abs/2606.24633)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-23**|**Enabling Robust Cloth Manipulation via Inference-Time Simulator-in-the-Loop Refinement**|Xin Liu et.al.|[2606.24552](https://arxiv.org/abs/2606.24552)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-23**|**G $^3$ VLA: Geometric inductive bias for Vision-Language-Action Models**|Yue Peng et.al.|[2606.24472](https://arxiv.org/abs/2606.24472)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-23**|**FT-WBC: Learning Fault-Tolerant Whole-Body Control for Legged Loco-Manipulation**|Yudong Zhong et.al.|[2606.24466](https://arxiv.org/abs/2606.24466)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-23**|**PDS Joint: A Parametric Double-Spiral Joint Tailored for Dexterous Hands**|Haoyang Li et.al.|[2606.24377](https://arxiv.org/abs/2606.24377)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-23**|**Grounding Generative Policies in Physics: Optimization-Guided Diffusion for Robot Control**|Sabrina Bodmer et.al.|[2606.24208](https://arxiv.org/abs/2606.24208)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-22**|**AutoDex: An Automated Real-World System for Dexterous Grasping Data Collection**|Mingi Choi et.al.|[2606.23689](https://arxiv.org/abs/2606.23689)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-22**|**LaST-HD: Learning Latent Physical Reasoning from Scalable Human Data for Robot Manipulation**|Jiaming Liu et.al.|[2606.23685](https://arxiv.org/abs/2606.23685)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-22**|**CoorDex: Coordinating Body and Hand Priors for Continuous Dexterous Humanoid Loco-Manipulation**|Sikai Li et.al.|[2606.23680](https://arxiv.org/abs/2606.23680)|**[link](https://github.com/YanjieZe/Paper-List)**|
|**2026-06-22**|**IMAGIN-4D: Image-Guided Controllable Interaction Generation**|Sai Kumar Dwivedi et.al.|[2606.23675](https://arxiv.org/abs/2606.23675)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-22**|**dVLA-RL: Reinforcement Learning over Denoising Trajectories for Discrete Diffusion Vision-Language-Action Models**|Yuhao Wu et.al.|[2606.23623](https://arxiv.org/abs/2606.23623)|**[link](https://github.com/zezhishao/DailyArXiv)**|
|**2026-06-22**|**KEMO: Event-Driven Keyframe Memory for Long-Horizon Robot Manipulation with VLA Policies**|Yihan Zeng et.al.|[2606.23589](https://arxiv.org/abs/2606.23589)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-22**|**DexTeleop-0: Force-Aware Bimanual Dexterous Teleoperation with Ego-Centric Perception towards Shared Autonomy**|Haichao Liu et.al.|[2606.23431](https://arxiv.org/abs/2606.23431)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-22**|**Flowing With Purpose: Latent Action Guided Flow Matching Policies For Robotic Manipulation**|Bruno Machado et.al.|[2606.23420](https://arxiv.org/abs/2606.23420)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-22**|**TSD: A Physics-Inspired Trajectory Saliency Detector for Efficient Imitation Learning**|Yiming Zhao et.al.|[2606.23371](https://arxiv.org/abs/2606.23371)|**[link](https://github.com/zezhishao/DailyArXiv)**|
|**2026-06-22**|**Flow6D: Discrete-to-Continuous Flow Matching for Efficient and Accurate Category-Level 6D Pose Estimation**|Mingyu Mei et.al.|[2606.23293](https://arxiv.org/abs/2606.23293)|**[link](https://github.com/Jianqiuer/Awesome6DPoseEstimation)**|
|**2026-06-22**|**Bridging Semantics and Kinematics: A Modular Framework for Zero-Shot Robotic Manipulation**|Ali Alabbas et.al.|[2606.23157](https://arxiv.org/abs/2606.23157)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-22**|**Foresight: Failure Detection for Long-Horizon Robotic Manipulation with Action-Conditioned World Model Latents**|Haoran Zhang et.al.|[2606.23085](https://arxiv.org/abs/2606.23085)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-22**|**AdaReP:Adaptive Re-Planning under Model Mismatch for Neural World-Model Predictive Control**|Yutian Cheng et.al.|[2606.23079](https://arxiv.org/abs/2606.23079)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-22**|**Improving Robotic Imitation Learning via Trajectory Standardization**|Licheng Yang et.al.|[2606.22907](https://arxiv.org/abs/2606.22907)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-22**|**HiL-ResRL: A Model-Agnostic Finetuning Adapter via Human-in-the-loop Residual Reinforcement Learning**|Jingyi Liu et.al.|[2606.22860](https://arxiv.org/abs/2606.22860)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-21**|**PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models**|Xianghui Wang et.al.|[2606.22540](https://arxiv.org/abs/2606.22540)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-21**|**ARP: Enhancing Quantized Skill Abstractions via Visual Alignment and Iterative Refinement for Robotic Manipulation**|Yuntian Wang et.al.|[2606.22480](https://arxiv.org/abs/2606.22480)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-21**|**Do Rigid-Body Simulators Dream of Soft Robots? Learning Contact-Rich Manipulation for Tendon-Driven Continuum Robots**|Chengnan Shentu et.al.|[2606.22397](https://arxiv.org/abs/2606.22397)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-21**|**FlowDPG: Deterministic Policy Gradient on Flow Matching Policies for Real-World Manipulation**|Kexin Shi et.al.|[2606.22303](https://arxiv.org/abs/2606.22303)|**[link](https://github.com/iszhanjiawei/flow_matching_arxiv_daily)**|
|**2026-06-21**|**Any-Body Guard: Universal Safeguarding for Manipulation Policies via Action Masking**|Alex Beaudin et.al.|[2606.22278](https://arxiv.org/abs/2606.22278)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-18**|**MemoryWAM: Efficient World Action Modeling with Persistent Memory**|Sizhe Yang et.al.|[2606.20562](https://arxiv.org/abs/2606.20562)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-18**|**TaCauchy: An Extensible FEM Framework for Vision-Based Tactile Simulation**|Hengfei Zhao et.al.|[2606.20426](https://arxiv.org/abs/2606.20426)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-18**|**Co-VLA: Coordination-Aware Structured Action Modeling for Dual-Arm Vision-Language-Action Systems**|Yandong Wang et.al.|[2606.20285](https://arxiv.org/abs/2606.20285)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-18**|**Efficiently Linking Real Scenes with Synthetic Data Generation for AI-based Cognitive Robotics and Computer Vision Applications**|Paul Koch et.al.|[2606.20272](https://arxiv.org/abs/2606.20272)|**[link](https://github.com/Jianqiuer/Awesome6DPoseEstimation)**|
|**2026-06-18**|**Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think**|Gia-Binh Nguyen et.al.|[2606.20246](https://arxiv.org/abs/2606.20246)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-18**|**Applications of quantum annealing to magnetic dipole hyperfine structure constants: First results beyond energies for atoms**|Boni Paul et.al.|[2606.20166](https://arxiv.org/abs/2606.20166)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-18**|**Frequency-Aware Flow Matching for Continuous and Consistent Robotic Action Generation**|Jianing Guo et.al.|[2606.20135](https://arxiv.org/abs/2606.20135)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-18**|**EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies**|Ganlin Yang et.al.|[2606.20092](https://arxiv.org/abs/2606.20092)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-18**|**ENPIRE: Agentic Robot Policy Self-Improvement in the Real World**|Wenli Xiao et.al.|[2606.19980](https://arxiv.org/abs/2606.19980)|**[link](https://github.com/YanjieZe/Paper-List)**|
|**2026-06-18**|**EquiVLA: A General Framework for Rotationally Equivariant Vision-Language-Action Models**|Thien-Loc Ha et.al.|[2606.19784](https://arxiv.org/abs/2606.19784)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-18**|**Temporal Self-Imitation Learning**|Yinsen Jia et.al.|[2606.19752](https://arxiv.org/abs/2606.19752)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-17**|**3D-DLP: Self-Supervised 3D Object-Centric Scene Representation Learning**|Ellina Zhang et.al.|[2606.19451](https://arxiv.org/abs/2606.19451)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-17**|**Zero-Shot Long-Horizon Dexterous Manipulation via Multi-View 3D-Grounded VLM Reasoning**|Jisoo Kim et.al.|[2606.19340](https://arxiv.org/abs/2606.19340)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-17**|**Do as I Do: Dexterous Manipulation Data from Everyday Human Videos**|Bhawna Paliwal et.al.|[2606.19333](https://arxiv.org/abs/2606.19333)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-06-17**|**Invertible Neural Network Adapter for One-Step Flow Matching in Robot Manipulation**|Yu Zhang et.al.|[2606.19194](https://arxiv.org/abs/2606.19194)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-17**|**HT-Bench: Benchmarking and Learning Dexterous Full-Hand Tactile Representations with Egocentric Vision**|Yuzhe Huang et.al.|[2606.19161](https://arxiv.org/abs/2606.19161)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-06-17**|**GCNGrasp-VP: Affordance-Guided View Planning for Efficient Task-Oriented Grasping**|Zanjia Tong et.al.|[2606.19091](https://arxiv.org/abs/2606.19091)|**[link](https://huggingface.co/models/TongZJ/GCNGrasp-v2)**|
|**2026-06-17**|**ART-VS: Adaptive Resolution Tiling for Vision Transformer Visual Servoing**|Alessandro Scherl et.al.|[2606.19089](https://arxiv.org/abs/2606.19089)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-18**|**Mem-World: Memory-Augmented Action-Conditioned World Models for Persistent Robot Manipulation**|Zirui Zheng et.al.|[2606.18960](https://arxiv.org/abs/2606.18960)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-06-17**|**TactSpace: Learning a Physics-enriched Shared Latent Space for Tactile Sim-to-Real Transfer**|Arunim Joarder et.al.|[2606.18959](https://arxiv.org/abs/2606.18959)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-17**|**HALOMI: Learning Humanoid Loco-Manipulation with Active Perception from Human Demonstrations**|Zehui Zhao et.al.|[2606.18772](https://arxiv.org/abs/2606.18772)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-17**|**Selective Unit-Cell Actuation in Lattice Structures for Distributed Morphology in Soft Robots**|Trevor Exley et.al.|[2606.18704](https://arxiv.org/abs/2606.18704)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-17**|**SC3-Eval: Evaluating Robot Foundation Models via Self-Consistent Video Generation**|Wei-Cheng Tseng et.al.|[2606.18610](https://arxiv.org/abs/2606.18610)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-17**|**Benchmarking Action Spaces in Reinforcement Learning for Vision-based Robotic Manipulation**|Seyed Alireza Azimi et.al.|[2606.18594](https://arxiv.org/abs/2606.18594)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-17**|**MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction**|Jianing Zhang et.al.|[2606.18558](https://arxiv.org/abs/2606.18558)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-16**|**PAIWorld: A 3D-Consistent World Foundation Model for Robotic Manipulation**|Yuhang Huang et.al.|[2606.18375](https://arxiv.org/abs/2606.18375)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-16**|**MOCHI: Motion Enhancement of Collaborative Human-object Interactions**|Jiye Lee et.al.|[2606.18243](https://arxiv.org/abs/2606.18243)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-16**|**EAGG: Embodiment-Aligned Grasp Generation via Geometry-Aware Graph Conditioning**|Wanhao Niu et.al.|[2606.18092](https://arxiv.org/abs/2606.18092)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-16**|**A Hybrid Optimization Framework for Grasp Synthesis under Partial Observations**|Wenzheng Zhang et.al.|[2606.18053](https://arxiv.org/abs/2606.18053)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-16**|**Uncertainty Quantification for Flow-Based Vision-Language-Action Models**|Ralf Römer et.al.|[2606.18043](https://arxiv.org/abs/2606.18043)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-16**|**ThinkingVLA: Interleaved Vision and Language Reasoning for Robotic Manipulation**|Tianyi Lu et.al.|[2606.17937](https://arxiv.org/abs/2606.17937)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-17**|**Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models**|Haoqi Yuan et.al.|[2606.17846](https://arxiv.org/abs/2606.17846)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-16**|**A Wearable Multimodal Ultrasound+Inertial System for Real-Time Virtual Reality Interaction**|Giusy Spacone et.al.|[2606.17741](https://arxiv.org/abs/2606.17741)|**[link](https://github.com/Jianqiuer/Awesome6DPoseEstimation)**|
|**2026-06-16**|**MuseVLA: An Adaptive Multimodal Sensing Vision-Language-Action Model for Robotic Manipulation**|Xingyuming Liu et.al.|[2606.17598](https://arxiv.org/abs/2606.17598)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-16**|**WeaveLA: Event Driven Cross-Subtask Latent Memory Weaving for Repetitive Robot Manipulation**|Shoujing Zhu et.al.|[2606.17463](https://arxiv.org/abs/2606.17463)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-16**|**AnnotateAnything: Automatic Annotation of 3D Assets for Robot Manipulation**|Haoran Lu et.al.|[2606.17446](https://arxiv.org/abs/2606.17446)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-16**|**DexLink Hand: A Compact, Affordable, 16-DOF Linkage-Driven Hand with Human-Like Dexterity**|Hao Wu et.al.|[2606.17418](https://arxiv.org/abs/2606.17418)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-16**|**EgoInfinity: A Web-Scale 4D Hand-Object Interaction Data Engine for Any-View Robot Retargeting and Video-to-Action Robot Learning**|Gaotian Wang et.al.|[2606.17385](https://arxiv.org/abs/2606.17385)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-15**|**Contrastive Action-Image Pre-training for Visuomotor Control**|Yuvan Sharma et.al.|[2606.17256](https://arxiv.org/abs/2606.17256)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-15**|**T-Rex: Tactile-Reactive Dexterous Manipulation**|Dantong Niu et.al.|[2606.17055](https://arxiv.org/abs/2606.17055)|**[link](https://huggingface.co/datasets/zekaiwang/trex_dataset)**|
|**2026-06-15**|**Human Universal Grasping**|Kevin Yuanbo Wu et.al.|[2606.17054](https://arxiv.org/abs/2606.17054)|**[link](https://huggingface.co/models/kevinywu/hug)**|
|**2026-06-15**|**Geometric Action Model for Robot Policy Learning**|Jisang Han et.al.|[2606.17046](https://arxiv.org/abs/2606.17046)|**[link](https://github.com/DravenALG/awesome-vla-wam)**|
|**2026-06-16**|**Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation**|Jie Zhang et.al.|[2606.17030](https://arxiv.org/abs/2606.17030)|**[link](https://github.com/BradyFU/Awesome-Multimodal-Large-Language-Models)**|
|**2026-06-15**|**PATCH: Action-Chunk-Conditioned Latent Patch Innovation Monitoring for Robot Manipulation**|Yanan Zhou et.al.|[2606.16690](https://arxiv.org/abs/2606.16690)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-15**|**Robots that Collaborate: Sequential Asymmetric Imitation for Learning Coupled Robot Policies**|Yincong Chen et.al.|[2606.16490](https://arxiv.org/abs/2606.16490)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-15**|**Decoupled Object-Centric Video Understanding for Generating Robotic Manipulation Commands**|Thanh Nguyen Canh et.al.|[2606.16470](https://arxiv.org/abs/2606.16470)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-15**|**Training and Evaluating Diffusion Policies with Long Context Lengths**|Abhinav Agarwal et.al.|[2606.16447](https://arxiv.org/abs/2606.16447)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-14**|**GeoTLM: Geometry-aware Tactile-Language Models for Contact Motion Orientation Reasoning of Dynamic Objects**|Qiutian Li et.al.|[2606.15909](https://arxiv.org/abs/2606.15909)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-14**|**SAPS: Shared Autonomy for Policy Steering by Blending Teleoperation with a Pretrained VLA**|Crystal Zhou et.al.|[2606.15568](https://arxiv.org/abs/2606.15568)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-14**|**Transferring Contact, Not Just Motion: Compliant Grasping Across Dexterous Hands**|Soofiyan Atar et.al.|[2606.15516](https://arxiv.org/abs/2606.15516)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-13**|**SimWeaver: Zero-Shot RGB Sim-to-Real for Deformable Manipulation**|Wenkang Hu et.al.|[2606.15338](https://arxiv.org/abs/2606.15338)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-13**|**Acting While Understanding: Asynchronous Semantic-Action Decoupling for Real-Time Vision-Language-Action Models**|Shenhao Yan et.al.|[2606.15285](https://arxiv.org/abs/2606.15285)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-13**|**Rethinking Implicit Spatial Representation in Visuomotor Policy Learning**|Xiangyu Chen et.al.|[2606.15232](https://arxiv.org/abs/2606.15232)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-13**|**Seam-to-Graph Reconstruction for Garment Configuration Alignment**|Xuzhao Huang et.al.|[2606.15171](https://arxiv.org/abs/2606.15171)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-13**|**MimicIK: Real-Time Generative Inverse Kinematics from Teleoperation with FK Consistency**|Jiahao Yang et.al.|[2606.15148](https://arxiv.org/abs/2606.15148)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-13**|**DragMesh-2: Physically Plausible Dexterous Hand-Object Interaction with Articulated Objects**|Tianshan Zhang et.al.|[2606.15133](https://arxiv.org/abs/2606.15133)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-12**|**GRASP: Gradient-Aligned Sequential Parameter Transfer for Memory-Efficient Multi-Source Learning**|Mary Isabelle Wisell et.al.|[2606.14900](https://arxiv.org/abs/2606.14900)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-12**|**Impedance MPC with Disturbance Estimation for Dexterous Hand Control**|Yongyan Cao et.al.|[2606.14606](https://arxiv.org/abs/2606.14606)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-12**|**ORCA: A Platform for Open-Source Dexterity Research**|Francesco Capuano et.al.|[2606.14561](https://arxiv.org/abs/2606.14561)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-12**|**Elastic Queries Reinforcement Learning: Self-Aware Policy Execution for VLA Models**|Ge Wang et.al.|[2606.14375](https://arxiv.org/abs/2606.14375)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-12**|**More with LESS -- Local Scene Representations for Tactile Imaging**|Zohar Rimon et.al.|[2606.14344](https://arxiv.org/abs/2606.14344)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-12**|**ReactVLA: Fast and Lightweight Reactive Robot Manipulation via Improved Mean Flow Action Generation**|Yanzhao Guo et.al.|[2606.14255](https://arxiv.org/abs/2606.14255)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-12**|**SyLink Hand: A Synergy-Inspired Linkage-Driven Anthropomorphic Hand for Human-Like Dexterity**|Hao Wu et.al.|[2606.14250](https://arxiv.org/abs/2606.14250)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-12**|**Environment-Aware Stable Neural Koopman Dynamics Learning for Input-Driven Systems under Environmental Constraints**|Lin Feng et.al.|[2606.14136](https://arxiv.org/abs/2606.14136)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-12**|**Self-Improving VLA Policies: Selected Diffusion Noise for Spurious-Robust Action Smoothing**|Duc Minh Nguyen et.al.|[2606.14084](https://arxiv.org/abs/2606.14084)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-11**|**An Attention-based Model for Robust Forecasting with Missing Modality**|Zhitian Zhang et.al.|[2606.13970](https://arxiv.org/abs/2606.13970)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-11**|**PhysVLA: Towards Physically-Grounded VLA for Embodied Robotic Manipulation**|Namai Chandra et.al.|[2606.13886](https://arxiv.org/abs/2606.13886)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-11**|**ContactWorld: What Matters in Vision-Tactile World Models for Contact-Rich Manipulation**|Zhiyuan Zhang et.al.|[2606.13877](https://arxiv.org/abs/2606.13877)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-11**|**Mana: Dexterous Manipulation of Articulated Tools**|Zhao-Heng Yin et.al.|[2606.13677](https://arxiv.org/abs/2606.13677)|**[link](https://github.com/wadeKeith/Awesome-Embodied-AI)**|
|**2026-06-11**|**$\texttt{WEAVER}$ , Better, Faster, Longer: An Effective World Model for Robotic Manipulation**|Arnav Kumar Jain et.al.|[2606.13672](https://arxiv.org/abs/2606.13672)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-11**|**MCR-Bionic Hand: Anatomical Structural Priors for Dexterous Manipulation**|Haosen Yang et.al.|[2606.13601](https://arxiv.org/abs/2606.13601)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-11**|**GIVE: Grounding Human Gestures in Vision-Language-Action Models**|Pengfei Liu et.al.|[2606.13435](https://arxiv.org/abs/2606.13435)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-11**|**Low cost, easily manufactured, highly flexible strain and touch sensitive fiber for robotics applications**|Christian Diaz Herrera et.al.|[2606.13352](https://arxiv.org/abs/2606.13352)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-11**|**See Selectively, Act Adaptively: Dual-Level Structural Decomposition for Bimanual Robot Manipulation**|Yoon-Ji Choi et.al.|[2606.13279](https://arxiv.org/abs/2606.13279)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-11**|**WT-UMI: Tactile-based Whole-Body Manipulation via Force-Supervised Contact-Aware Planning**|Jaehwi Jang et.al.|[2606.13232](https://arxiv.org/abs/2606.13232)|**[link](https://github.com/Foruck/Awesome-Human-Motion)**|
|**2026-06-11**|**RoboProcessBench: Benchmarking Process-Aware Understanding in Vision-Language Robotic Manipulation**|Dayu Xia et.al.|[2606.13040](https://arxiv.org/abs/2606.13040)|**[link](https://github.com/wadeKeith/Awesome-Embodied-AI)**|
|**2026-06-11**|**GenHOI: Contact-Aware Humanoid-Object Interaction by Imitating Generated Videos without Task-Specific Training**|Zhihai Bi et.al.|[2606.12995](https://arxiv.org/abs/2606.12995)|**[link](https://github.com/Foruck/Awesome-Human-Motion)**|
|**2026-06-11**|**Towards Reliable Sequential Object Picking in Clutter: The Runner-up Solution to RGMC 2025**|Wei Yu et.al.|[2606.12954](https://arxiv.org/abs/2606.12954)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-11**|**Bounding Boxes as Goals: Language-Conditioned Grasping via Neuro-Symbolic Planning**|Allison Andreyev et.al.|[2606.12910](https://arxiv.org/abs/2606.12910)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-11**|**AIR-VLA+: Decoupling Movement and Manipulation via Cascaded Dual-Action Decoders with Asymmetric MoE for Aerial Robots**|Jianli Sun et.al.|[2606.12859](https://arxiv.org/abs/2606.12859)|**[link](https://github.com/wadeKeith/Awesome-Embodied-AI)**|
|**2026-06-10**|**Sparse2Act: Learning Action-Aligned Sparse 3D Representations for Cross-Domain Robot Manipulation**|Yu Guo et.al.|[2606.12759](https://arxiv.org/abs/2606.12759)|**[link](https://github.com/wadeKeith/Awesome-Embodied-AI)**|
|**2026-06-10**|**EquiDexFlow: Contact-Grounded SE(3)-Equivariant Dexterous Grasp Generative Flows**|Clinton Enwerem et.al.|[2606.12728](https://arxiv.org/abs/2606.12728)|**[link](https://huggingface.co/models/cenwerem/equidexflow-allegro-full)**|
|**2026-06-10**|**Action-Effect Memory Pretraining for Robot Manipulation**|Yijing Zhou et.al.|[2606.12499](https://arxiv.org/abs/2606.12499)|**[link](https://github.com/wadeKeith/Awesome-Embodied-AI)**|
|**2026-06-10**|**UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learning**|Haoyuan Deng et.al.|[2606.12372](https://arxiv.org/abs/2606.12372)|**[link](https://github.com/wadeKeith/Awesome-Embodied-AI)**|
|**2026-06-10**|**Fourier Features Let Agents Learn High Precision Policies with Imitation Learning**|Balázs Gyenes et.al.|[2606.12334](https://arxiv.org/abs/2606.12334)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-10**|**Finding Sparse Subnetworks in One Training Cycle via Progressive Magnitude-Based Pruning**|Romana Qureshi et.al.|[2606.12278](https://arxiv.org/abs/2606.12278)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-10**|**Making Foresight Actionable: Repurposing Representation Alignment in World Action Models**|Lu Qiu et.al.|[2606.12217](https://arxiv.org/abs/2606.12217)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-10**|**Bridging the Morphology Gap: Adapting VLA Models to Dexterous Manipulation via Intent-Conditioned Fine-Tuning**|Chuanke Pang et.al.|[2606.12109](https://arxiv.org/abs/2606.12109)|**[link](https://github.com/wadeKeith/Awesome-Embodied-AI)**|
|**2026-06-10**|**VICX: Generalizable Robot Manipulation via Video Generation and In-Context Operator Network**|Song Chen et.al.|[2606.12028](https://arxiv.org/abs/2606.12028)|**[link](https://github.com/wadeKeith/Awesome-Embodied-AI)**|
|**2026-06-10**|**PAWS: Preference Learning with Advantage-Weighted Segments**|Aleksandar Taranovic et.al.|[2606.11982](https://arxiv.org/abs/2606.11982)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-10**|**Embodied-BenchClaw: An Autonomous Multi-Agent System for Embodied Spatial Intelligence Benchmark Construction**|Baoyang Jiang et.al.|[2606.11909](https://arxiv.org/abs/2606.11909)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-06-10**|**When Does Language Matter? Multilingual Instructions Reveal Step-wise Language Sensitivity in Vision-Language-Action Models**|Xuan Dong et.al.|[2606.11906](https://arxiv.org/abs/2606.11906)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-10**|**Critic Architecture Matters: Dual vs. Unified Critics for Humanoid Loco-Manipulation**|Mehmet Turan Yardımcı et.al.|[2606.11891](https://arxiv.org/abs/2606.11891)|**[link](https://github.com/Foruck/Awesome-Human-Motion)**|
|**2026-06-10**|**Modular Anthropomorphic Hand Design via Multi-Parameter Finger Benchmarking and Selection**|Yu Zhang et.al.|[2606.11826](https://arxiv.org/abs/2606.11826)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-10**|**Blind Dexterous Grasping via Real2Sim2Real Tactile Policy Learning**|Shengcheng Luo et.al.|[2606.11767](https://arxiv.org/abs/2606.11767)|**[link](https://github.com/pstAmbition/DailyArXiv_Multimodal)**|
|**2026-06-10**|**TacCoRL: Integrating Tactile Feedback into VLA via Simulation**|Siyu Ma et.al.|[2606.11743](https://arxiv.org/abs/2606.11743)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-10**|**4DP-QA: Scalable QA for 4D Perception in Vision Language Models**|Seokju Cho et.al.|[2606.11568](https://arxiv.org/abs/2606.11568)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-06-10**|**Learning Object Manipulation from Scratch via Contrastive Interaction**|Tongle Shen et.al.|[2606.11525](https://arxiv.org/abs/2606.11525)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-09**|**HiPi: Reproducible High-Fidelity Piezoresistive Sensors for Robotic Manipulation**|Changyi Lin et.al.|[2606.11372](https://arxiv.org/abs/2606.11372)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-09**|**JOIN: Anchor-Grasp-Conditioned Joining via Opposition, Inference, and Navigation for Bimanual Assistive Manipulation**|Drake Moore et.al.|[2606.11151](https://arxiv.org/abs/2606.11151)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-09**|**Understanding and mitigating the risks of OpenClaw for non-technical users: A practical guide with Skill**|Junchang Zheng et.al.|[2606.11007](https://arxiv.org/abs/2606.11007)|**[link](https://github.com/tmgthb/Autonomous-Agents)**|
|**2026-06-09**|**MV-Actor: Aligning Multi-View Semantics and Spatial Awareness for Bimanual Manipulation**|Yinchen Tian et.al.|[2606.10899](https://arxiv.org/abs/2606.10899)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-09**|**IMPACT: Learning Internal-Model Predictive Control for Forceful Robotic Manipulation**|Jiawei Gao et.al.|[2606.10818](https://arxiv.org/abs/2606.10818)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-09**|**Hand-centric Human-to-Robot Trajectory Transfer from Video Demonstrations via Open-World Contact Localization**|Yitian Shi et.al.|[2606.10743](https://arxiv.org/abs/2606.10743)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-09**|**VeriSpace: Spatially Grounded Action Verification for Vision-Language-Action Models**|Guiyu Zhao et.al.|[2606.10568](https://arxiv.org/abs/2606.10568)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-09**|**UMI-Bench 1.0: An Open and Reproducible Real-World Benchmark for Tabletop Robotic Manipulation with UMI Data**|Shi Jin et.al.|[2606.10382](https://arxiv.org/abs/2606.10382)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-06-09**|**HiMem-WAM: Hierarchical Memory-Gated World Action Models for Robotic Manipulation**|Xiaoquan Sun et.al.|[2606.10363](https://arxiv.org/abs/2606.10363)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-09**|**SARM2: Multi-Task Stage Aware Reward Modeling for Self Improving Robotic Manipulation**|Qianzhong Chen et.al.|[2606.10305](https://arxiv.org/abs/2606.10305)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-09**|**What Matters in Orchestrating Robot Policies: A Systematic Study of Hierarchical VLA Agents**|Jiaheng Hu et.al.|[2606.10267](https://arxiv.org/abs/2606.10267)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-08**|**Robotic Nonprehensile Object Transportation with a Hanging Tray**|Adam Heins et.al.|[2606.10039](https://arxiv.org/abs/2606.10039)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-08**|**GHOST: Hierarchical Sub-Goal Policies for Generalizing Robot Manipulation**|Sriram Krishna et.al.|[2606.10025](https://arxiv.org/abs/2606.10025)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-08**|**MemoryVLA++: Temporal Modeling via Memory and Imagination in Vision-Language-Action Models**|Hao Shi et.al.|[2606.09827](https://arxiv.org/abs/2606.09827)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-08**|**AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing**|Jisong Cai et.al.|[2606.09811](https://arxiv.org/abs/2606.09811)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-08**|**SynManDex: Synthesizing Human-like Dexterous Grasps from Synthetic Human Pre-Grasps**|Yanming Shao et.al.|[2606.09798](https://arxiv.org/abs/2606.09798)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-08**|**Difference-Aware Retrieval Policies for Imitation Learning**|Quinn Pfeifer et.al.|[2606.09758](https://arxiv.org/abs/2606.09758)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-08**|**Your Model Already Knows: Attention-Guided Safety Filter for Vision-Language-Action Models**|Seongbin Park et.al.|[2606.09749](https://arxiv.org/abs/2606.09749)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-08**|**ProbeAct: Probe-Guided Training-Free Failure Recovery in Vision-Language-Action Models**|Fan Zhang et.al.|[2606.09740](https://arxiv.org/abs/2606.09740)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-08**|**CT-VAM: A Cerebello-Thalamic-Inspired Vision-Action Model for Efficient Visuomotor Control**|Jiacheng Li et.al.|[2606.09572](https://arxiv.org/abs/2606.09572)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-08**|**Dense Force Estimation with an Event-based Optical Tactile Sensor**|Agis Politis et.al.|[2606.09451](https://arxiv.org/abs/2606.09451)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-08**|**ReGIL: Retrieval-Guided Imitation Learning from a Single Demonstration**|Yuying Zhang et.al.|[2606.09381](https://arxiv.org/abs/2606.09381)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-08**|**TORL-VLA: Tactile Guided Online Reinforcement Learning for Contact-Rich Manipulation**|Huaihang Zheng et.al.|[2606.09337](https://arxiv.org/abs/2606.09337)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-08**|**KPGrasp: Scalable Keypoint Flow Matching for Dexterous Grasp Generation**|Yuansen Huang et.al.|[2606.09314](https://arxiv.org/abs/2606.09314)|**[link](https://github.com/iszhanjiawei/flow_matching_arxiv_daily)**|
|**2026-06-08**|**EgoTactile: Learning Grasp Pressure for Everyday Objects from Egocentric Video**|Yuan Zeng et.al.|[2606.09243](https://arxiv.org/abs/2606.09243)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-08**|**MotionWAM: Towards Foundation World Action Models for Real-Time Humanoid Loco-Manipulation**|Jia Zheng et.al.|[2606.09215](https://arxiv.org/abs/2606.09215)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-08**|**EPS3D: End-to-End Feed-Forward 3D Panoptic Segmentation**|Runsong Zhu et.al.|[2606.08980](https://arxiv.org/abs/2606.08980)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-07**|**Benchmarking Vision-Language-Action Models on SO-101: Failure and Recovery Analysis**|Yi Yu et.al.|[2606.08881](https://arxiv.org/abs/2606.08881)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-07**|**Unifying Object-Centric World Models and Diffusion Policy: A Hierarchical Framework for Multi-Stage Robotic Tasks**|Raktim Gautam Goswami et.al.|[2606.08775](https://arxiv.org/abs/2606.08775)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-07**|**Dream-Tac: A Unified Tactile World Action Model for Contact-Rich Robot Manipulation**|Yunfan Lou et.al.|[2606.08737](https://arxiv.org/abs/2606.08737)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-07**|**Latent Diffusion Policy: Shaping Latent Spaces for Diffusion-Based Robotic Manipulation**|Zhexuan Zhou et.al.|[2606.08657](https://arxiv.org/abs/2606.08657)|**[link](https://github.com/iszhanjiawei/flow_matching_arxiv_daily)**|
|**2026-06-07**|**Reinforcement Learning for Flow-Matching Policies with Density Transport**|Boshu Lei et.al.|[2606.08602](https://arxiv.org/abs/2606.08602)|**[link](https://github.com/iszhanjiawei/flow_matching_arxiv_daily)**|
|**2026-06-07**|**Real-IKEA: Physical Fidelity is the Prerequisite for Robust Manipulation**|Kunqi Xu et.al.|[2606.08564](https://arxiv.org/abs/2606.08564)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-05**|**Simulation-Driven Imitation Learning for Biosignals-Free Shared-Autonomy Prosthetic Grasping**|Kaijie Shi et.al.|[2606.07389](https://arxiv.org/abs/2606.07389)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-05**|**Spline Policy: A Structured Representation for Robot Policies**|Mengze Tian et.al.|[2606.07386](https://arxiv.org/abs/2606.07386)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-05**|**RhinoVLA Technical Report**|Huixi Intelligence et.al.|[2606.07383](https://arxiv.org/abs/2606.07383)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-05**|**Robotic Policy Adaptation via Weight-Space Meta-Learning**|Christian Bianchi et.al.|[2606.07217](https://arxiv.org/abs/2606.07217)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-05**|**LARA: Latent Action Representation Alignment for Vision-Language-Action Models**|Mengya Liu et.al.|[2606.07100](https://arxiv.org/abs/2606.07100)|**[link](https://github.com/DravenALG/awesome-vla-wam)**|
|**2026-06-05**|**Task Editing for Generalizable 3D Visuomotor Policy Learning**|Jian-Jian Jiang et.al.|[2606.07012](https://arxiv.org/abs/2606.07012)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-05**|**GenPO++: Generative Policy Optimization with Jacobian-free Likelihood Ratios**|Ke Hu et.al.|[2606.06967](https://arxiv.org/abs/2606.06967)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-06-05**|**GRASP: Geometry-aware Residual Alignment for Scalable Pretraining Data Attribution**|Yue Min et.al.|[2606.06892](https://arxiv.org/abs/2606.06892)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-06-05**|**A Cross-view Fusion Framework for Robust 6-DoF Grasp Pose Estimation**|Kangjian Zhu et.al.|[2606.06878](https://arxiv.org/abs/2606.06878)|**[link](https://github.com/Jianqiuer/Awesome6DPoseEstimation)**|
|**2026-06-04**|**AEGIS: A Backup Reflex for Physical AI**|Josef Chen et.al.|[2606.06660](https://arxiv.org/abs/2606.06660)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-04**|**What Matters When Cotraining Robot Manipulation Policies on Everyday Human Videos?**|Richard Li et.al.|[2606.06627](https://arxiv.org/abs/2606.06627)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-04**|**PhyRoGen: Synthetic Generation of Physical Robot Manipulation Puzzles Using Procedural Content Generation**|Lennart Julian Droß et.al.|[2606.06569](https://arxiv.org/abs/2606.06569)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-04**|**TempoVLA: Learning Speed-Controllable Vision-Language-Action Policies**|Dong Jing et.al.|[2606.06491](https://arxiv.org/abs/2606.06491)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-04**|**Synthetic Data Generation and Vision-based Wrinkle and Keypoint Detection for Bimanual Cloth Manipulation**|Ariel Herrera et.al.|[2606.06292](https://arxiv.org/abs/2606.06292)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-04**|**Multi-Resolution Tactile Imitation Learning for Contact-Rich Robotic Manipulation**|Rickmer Krohn et.al.|[2606.06281](https://arxiv.org/abs/2606.06281)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-04**|**AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding**|Qize Yu et.al.|[2606.06155](https://arxiv.org/abs/2606.06155)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-04**|**MotionDisco: Motion Discovery for Extreme Humanoid Loco-Manipulation**|Ilyass Taouil et.al.|[2606.06139](https://arxiv.org/abs/2606.06139)|**[link](https://github.com/YanjieZe/Paper-List)**|
|**2026-06-04**|**L-SDPPO: Policy Optimization of Spiking Diffusion Policy for Intra-vehicular Robotic Manipulation**|Liwen Zhang et.al.|[2606.06049](https://arxiv.org/abs/2606.06049)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-04**|**Sample-efficient Low-level Motion Planning for Robotic Manipulation Tasks via Zero-shot Transfer Learning**|Yuanzhi He et.al.|[2606.06041](https://arxiv.org/abs/2606.06041)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-04**|**Visuotactile and Explicitly Force-Controlled Robotic Ultrasound for Abdominal Volumetric Reconstruction**|Adrian Piedra et.al.|[2606.05848](https://arxiv.org/abs/2606.05848)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-04**|**Safe Embodied AI for Long-horizon Tasks: A Cross-layer Analysis of Robotic Manipulation**|Dabin Kim et.al.|[2606.05660](https://arxiv.org/abs/2606.05660)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-03**|**MoDex: A Diffusion Policy for Sequential Multi-Object Dexterous Grasping**|Haofei Lu et.al.|[2606.05407](https://arxiv.org/abs/2606.05407)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-03**|**Efficient Computation of Distance Functions for Navigation Vector Fields in Lie Groups**|Vinicius M. Gonçalves et.al.|[2606.05372](https://arxiv.org/abs/2606.05372)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-03**|**Inverse Manipulation through Symbolic Planning and Residual Operator Learning**|Yigit Yildirim et.al.|[2606.05248](https://arxiv.org/abs/2606.05248)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-03**|**GRAIL: Generating Humanoid Loco-Manipulation from 3D Assets and Video Priors**|Tianyi Xie et.al.|[2606.05160](https://arxiv.org/abs/2606.05160)|**[link](https://huggingface.co/datasets/nvidia/PhysicalAI-Robotics-Locomanipulation-GRAIL)**|
|**2026-06-03**|**X4Val: Learning Neural Surrogates for Variance-Reduced Policy Evaluation**|Rachel Luo et.al.|[2606.05159](https://arxiv.org/abs/2606.05159)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-03**|**M3imic: Learning a Versatile Whole-Body Controller for Multimodal Motion Mimicking**|Zuxing Lu et.al.|[2606.04829](https://arxiv.org/abs/2606.04829)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-04**|**Dream.exe: Can Video Generation Models Dream Executable Robot Manipulation?**|Rui Zhao et.al.|[2606.04811](https://arxiv.org/abs/2606.04811)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-03**|**A model-free approach to control barrier functions for higher-order systems**|Lukas Lanza et.al.|[2606.04790](https://arxiv.org/abs/2606.04790)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-03**|**SoftPINCH: EMG-Driven Soft Exoskeleton Assistance for Finger Flexion and Grasping**|Nicklas Nikolaj Grønvall et.al.|[2606.04776](https://arxiv.org/abs/2606.04776)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-02**|**What Are We Actually Benchmarking in Robot Manipulation?**|Tianchong Jiang et.al.|[2606.04233](https://arxiv.org/abs/2606.04233)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-02**|**DLO-Lab: Benchmarking Deformable Linear Object Manipulations with Differentiable Physics**|Junyi Cao et.al.|[2606.04206](https://arxiv.org/abs/2606.04206)|**[link](https://github.com/Songwxuan/Embodied-AI-Paper-TopConf)**|
|**2026-06-02**|**Affordance2Action: Task-Conditioned Scene-level Affordance Grounding for Real-Time Manipulation**|Litao Liu et.al.|[2606.04172](https://arxiv.org/abs/2606.04172)|**[link](https://github.com/arc-l/a2a)**|
|**2026-06-02**|**Dive into the Scene: Breaking the Perceptual Bottleneck in Vision-Language Decision Making via Focus Plan Generation**|Boyuan Xiao et.al.|[2606.04046](https://arxiv.org/abs/2606.04046)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-02**|**SimuScene: Simulation-Ready Compositional 3D Scene Reconstruction from a Single Image**|Inhee Lee et.al.|[2606.03994](https://arxiv.org/abs/2606.03994)|**[link](https://github.com/Tavish9/awesome-daily-AI-arxiv)**|
|**2026-06-02**|**Preference-Calibrated Human-in-the-Loop Reinforcement Learning for Robotic Manipulation**|Zeyi Liu et.al.|[2606.03949](https://arxiv.org/abs/2606.03949)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-02**|**PointAction: 3D Points as Universal Action Representations for Robot Control**|Mutian Tong et.al.|[2606.03943](https://arxiv.org/abs/2606.03943)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-02**|**Optimal Design and Analytical Modeling of a Soft Fin-Ray Effect Gripper Finger Using the Finite Rigid Elements Method**|Sara Adeli et.al.|[2606.03798](https://arxiv.org/abs/2606.03798)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-03**|**Revisiting Embodied Chain-of-Thought for Generalizable Robot Manipulation**|Nan Sun et.al.|[2606.03784](https://arxiv.org/abs/2606.03784)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-02**|**The Polymorphic Chiral Anomaly**|Christopher Smith et.al.|[2606.03619](https://arxiv.org/abs/2606.03619)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-03**|**PHASER: Phase-Aware and Semantic Experience Replay for Vision-Language-Action Models**|Ziyang Chen et.al.|[2606.03598](https://arxiv.org/abs/2606.03598)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-02**|**Static and Dynamic Representations for Tactile Contact-Angle Estimation with Event-Based Sensors**|Yanhui Lu et.al.|[2606.03545](https://arxiv.org/abs/2606.03545)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-02**|**Grasp-Then-Plan with Failure Attribution: A Closed Two-Stage Framework for Precise and Generalizable Robotic Manipulation**|Jiahao Xu et.al.|[2606.03385](https://arxiv.org/abs/2606.03385)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-06-02**|**SplitAdapter: Load-Aware Humanoid Loco-Manipulation via Factorized Adaptation**|Jeonguk Kang et.al.|[2606.03297](https://arxiv.org/abs/2606.03297)|**[link](https://github.com/Foruck/Awesome-Human-Motion)**|

(<a href=#updated-on-20260823>back to top</a>)

## Vision Language Action Model

|Publish Date|Title|Authors|PDF|Code|
|---|---|---|---|---|
|**2026-08-20**|**OrthoSkillVLA: Continual Skill Learning via Gradient-Informed Skill Subspace Adaptation**|Jiaqi Wang et.al.|[2608.19589](https://arxiv.org/abs/2608.19589)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-18**|**Plug-and-Play Traffic Element Awareness for End-to-End Autonomous Driving**|Zongzheng Zhang et.al.|[2608.18035](https://arxiv.org/abs/2608.18035)|**[link](https://huggingface.co/datasets/Zzz0918/Traffic_Elements)**|
|**2026-08-18**|**CompCPZ: Preserving Multi-Modal Intent in Language-Guided Robot Manipulation**|Zhen Zhang et.al.|[2608.17717](https://arxiv.org/abs/2608.17717)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-18**|**LIBERO-VIFO: Benchmarking the Capability and Safety of Visual Cue Following in Vision-Language-Action Models**|Zhengyan Qian et.al.|[2608.17600](https://arxiv.org/abs/2608.17600)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-17**|**Q-Learning With World Models**|Perry Dong et.al.|[2608.17163](https://arxiv.org/abs/2608.17163)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-17**|**When State Becomes an Attack Surface: State-Semantic Injection in LLM-Driven Embodied Agents**|Jiawei Liu et.al.|[2608.16806](https://arxiv.org/abs/2608.16806)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-17**|**FabriMAE I Trust Myself? Self-Evaluating VLA Action Generation with Markov Attention Entropy**| Aniri et.al.|[2608.16697](https://arxiv.org/abs/2608.16697)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-17**|**NebulaVLA: A Dual-Frequency Vision-Language-Action Model With Guide Action for Robotic Manipulation**|Cong Zhao et.al.|[2608.16503](https://arxiv.org/abs/2608.16503)|null|
|**2026-08-17**|**US-VLA: An Ultrasound Vision-Language-Action Model for Embodied Abdomina**|Cheng Zhang et.al.|[2608.16074](https://arxiv.org/abs/2608.16074)|null|
|**2026-08-16**|**EcoVLA: Energy-Efficient Device-Edge Co-Inference for Vision-Language-Action Models under Real-Time Constraints**|Ao Zhou et.al.|[2608.15502](https://arxiv.org/abs/2608.15502)|null|
|**2026-08-16**|**Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability**|Yudong Gao et.al.|[2608.15475](https://arxiv.org/abs/2608.15475)|null|
|**2026-08-15**|**ForceU-VLA: A Force-Aware Vision-Language-Action Model for Embodied Ultrasound Scanning**|Xingzheng Wu et.al.|[2608.15009](https://arxiv.org/abs/2608.15009)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-14**|**Imagining Recovery: Inference-Time Counterfactual Realignment for Vision-Language-Action Models**|Yanyan Zhang et.al.|[2608.14822](https://arxiv.org/abs/2608.14822)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-14**|**Reflex: Enabling Fast and Predictive Vision-Language-Action Models for Reaction-Critical Manipulation**|Yuxuan Chen et.al.|[2608.14379](https://arxiv.org/abs/2608.14379)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-14**|**Evolve Vision-Language-Action Model into an Agent with On-the-fly Tool-use**|Yi Ding et.al.|[2608.14047](https://arxiv.org/abs/2608.14047)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-13**|**Decoding Task Progress from VLA Representations**|Atiksh Bhardwaj et.al.|[2608.13474](https://arxiv.org/abs/2608.13474)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-13**|**UniTexture: Cross-Task Universal Adversarial Textures for Vision-Language-Action Models**|Yukun Dai et.al.|[2608.13453](https://arxiv.org/abs/2608.13453)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-13**|**FIRE-VLA: Failure-Informed Self-Evolution for Vision-Language-Action Models in Autonomous Driving**|Hao Dou et.al.|[2608.13395](https://arxiv.org/abs/2608.13395)|**[link](https://github.com/chrisliu298/awesome-on-policy-distillation)**|
|**2026-08-12**|**StellaVLA: In-Context Structured Demonstration for Generalizable Vision-Language-Action Models**|Siyu Xu et.al.|[2608.11671](https://arxiv.org/abs/2608.11671)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-11**|**Neural Introspection Gating for Adaptive KV-Cache Reuse in Vision-Language-Action Models**|Zhijie Wu et.al.|[2608.10824](https://arxiv.org/abs/2608.10824)|**[link](https://github.com/Xnhyacinth/Awesome-LLM-Long-Context-Modeling)**|
|**2026-08-11**|**Lost in Reconstruction: Aligning Action Representations with Language in Vision-Language-Action Models**|Li Wenjie et.al.|[2608.10484](https://arxiv.org/abs/2608.10484)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-11**|**Hidden in Plain Sight: Diffusion-Based Unrestricted Robotic Attacks on Vision-Language-Action Models**|Jiahui Han et.al.|[2608.10393](https://arxiv.org/abs/2608.10393)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-12**|**VANE: Reliable Test-Time Training for Vision-Language-Action Models via Future Visual Representation Prediction**|Hongjin Ji et.al.|[2608.09448](https://arxiv.org/abs/2608.09448)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-14**|**From Recovery to Drop-off: How Action Post-training Reduces a VLM's Late-Layer Depth Decodability**|Alexander Hackett et.al.|[2608.08904](https://arxiv.org/abs/2608.08904)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-08-09**|**WA-SpecDec: World-Aware Speculative Decoding for Vision-Language-Action Models**|Zikang Wen et.al.|[2608.08725](https://arxiv.org/abs/2608.08725)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-07**|**CMU-Drive and V2V-VLA: Cooperative Multi-agent Unified Driving with Reasoning Benchmark and Vehicle-to-Vehicle Vision-Language-Action Models**|Hsu-kuang Chiu et.al.|[2608.07621](https://arxiv.org/abs/2608.07621)|null|
|**2026-08-07**|**Depth-Wise Probing and Pruning of the Planning Token in a Driving Vision-Language-Action Model**|Harisankar Babu et.al.|[2608.07361](https://arxiv.org/abs/2608.07361)|null|
|**2026-08-07**|**TEMPO: Semantic-Action Decoupled RL Post-Training for Vision-Language-Action Models**|Ziheng Liu et.al.|[2608.07314](https://arxiv.org/abs/2608.07314)|null|
|**2026-08-07**|**AtlasVLA: Persistent World-Ego State Modeling for Vision-Language-Action Models**|Guiyu Zhao et.al.|[2608.06729](https://arxiv.org/abs/2608.06729)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-08-06**|**In-Context VLA: Endowing Vision-Language-Action Models with Language via In-Context Post-Training and Agentic Tool Use**|Jiarui Yang et.al.|[2608.05738](https://arxiv.org/abs/2608.05738)|null|
|**2026-08-05**|**Explicit Language Memory for Long-Horizon Planning in Vision-Language-Action Models**|Houze Xu et.al.|[2608.04765](https://arxiv.org/abs/2608.04765)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-05**|**Mind-VLA: Instruction-Aware Spatial Representation Alignment for Vision-Language-Action Models**|Xingyu Ding et.al.|[2608.04633](https://arxiv.org/abs/2608.04633)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-05**|**CofactVLA: Deconfounding Vision-Language-Action Models via Counterfactual Intervention**|Yan Zhang et.al.|[2608.04396](https://arxiv.org/abs/2608.04396)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-04**|**How Should Vision-Language-Action Models Use Proprioceptive State?**|Yiren Zhao et.al.|[2608.03052](https://arxiv.org/abs/2608.03052)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-03**|**Ego2Robot: Scalable Robot Data Synthesis from Egocentric Human Data**|Ye Wang et.al.|[2608.02580](https://arxiv.org/abs/2608.02580)|**[link](https://github.com/zli12321/Vision-Language-Models-Overview)**|
|**2026-08-03**|**Grounded Semantic Re-Binding for Robust Instruction Generalization in Vision-Language-Action Models**|Zhaokai Yin et.al.|[2608.02497](https://arxiv.org/abs/2608.02497)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-03**|**Look Where It Matters: Adaptive Visual Refinement for Vision-Language-Action Models**|Jin Cui et.al.|[2608.02197](https://arxiv.org/abs/2608.02197)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-03**|**ReTouch: Empowering Contact-Rich Dexterous Manipulation with Online-Refined Tactile Prediction**|Shiqi Zhang et.al.|[2608.01824](https://arxiv.org/abs/2608.01824)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-03**|**Uncovering and Mitigating Positional Blind Spots in Vision-Language-Action Models**|Dongdong An et.al.|[2608.01573](https://arxiv.org/abs/2608.01573)|null|
|**2026-08-02**|**Demystifying When and Why VLAs Fail in Contact-Rich Tasks and How to Fix Them**|Carlota Parés-Morlans et.al.|[2608.01402](https://arxiv.org/abs/2608.01402)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-09**|**Hermite Curves as Trajectory Priors for Vision-Language-Action Models**|Qi Lv et.al.|[2608.01265](https://arxiv.org/abs/2608.01265)|**[link](https://github.com/zezhishao/DailyArXiv)**|
|**2026-08-01**|**Latency-Tolerant Cloud-Edge Collaborative Vision-Language-Action Models via Emergent Representational Specialization**|Daojie Peng et.al.|[2608.00569](https://arxiv.org/abs/2608.00569)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-31**|**FibVLA: An Efficient Temporal Vision-Language-Action Model with Fibonacci Sampling**|Li Lin et.al.|[2607.29596](https://arxiv.org/abs/2607.29596)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-31**|**Safe Vision Language Action Models via Barrier Enhanced Flow Matching**|Kasra Sinaei et.al.|[2607.29569](https://arxiv.org/abs/2607.29569)|null|
|**2026-07-30**|**Self-Evolving Learning for Embodied AI with Criticality Model**|Linxuan He et.al.|[2607.28251](https://arxiv.org/abs/2607.28251)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-29**|**TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM**|Hengyi Xie et.al.|[2607.27205](https://arxiv.org/abs/2607.27205)|**[link](https://huggingface.co/models/H-EmbodVis/TurboVLA)**|
|**2026-07-30**|**RL $^2$ -VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models**|Derek Ming Siang Tan et.al.|[2607.26991](https://arxiv.org/abs/2607.26991)|**[link](https://huggingface.co/models/rl2-vla/rl2-vla-qam-bridge)**|
|**2026-07-29**|**Explicit Kinematic Guidance from Analytic Concepts for Vision-Language-Action Models**|Mingyang Sun et.al.|[2607.26513](https://arxiv.org/abs/2607.26513)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-28**|**SAM3D-Guided Object-Centric Representation Alignment for Vision-Language-Action Models**|Zonghe Liu et.al.|[2607.25912](https://arxiv.org/abs/2607.25912)|**[link](https://github.com/liliu-avril/Awesome-Segment-Anything)**|
|**2026-07-28**|**CoTinyVLA: Chain-of-Thought Distillation for a Sub-Billion-Parameter Vision-Language-Action Model**|Minhyeok Lee et.al.|[2607.25487](https://arxiv.org/abs/2607.25487)|**[link](https://huggingface.co/models/euphoria-64/CoTinyVLA-Qwen3.5-0.8B)**|
|**2026-07-27**|**Data Pyramid for Embodied Manipulation**|Yifan Ye et.al.|[2607.24744](https://arxiv.org/abs/2607.24744)|**[link](https://github.com/DravenALG/awesome-vla-wam)**|
|**2026-07-30**|**τ: Learning Touch-Augmented Vision-Language-Action Models from Future Visual Supervision**|Ning Cheng et.al.|[2607.24485](https://arxiv.org/abs/2607.24485)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-27**|**DeVA: Decoupled Video-Action Model with physical guidance for robot policy learning**|Mengqi Zhang et.al.|[2607.24159](https://arxiv.org/abs/2607.24159)|**[link](https://huggingface.co/models/mengqz9/DeVA)**|
|**2026-07-26**|**A Few Words Go a Long Way: Language Guided Robot Policy Synthesis**|Daphne Chen et.al.|[2607.23784](https://arxiv.org/abs/2607.23784)|null|
|**2026-07-23**|**HyWorldVLA: A Vision-Language-Action Model with Hybrid World Modeling for Autonomous Driving**|Quanfu Yu et.al.|[2607.20988](https://arxiv.org/abs/2607.20988)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-07-22**|**LENS: LLM-guided Environment Simplification for Planning and Control in Clutter**|Aileen Liao et.al.|[2607.19633](https://arxiv.org/abs/2607.19633)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-20**|**Patch Policy: Efficient Embodied Control via Dense Visual Representations**|Gaoyue Zhou et.al.|[2607.18236](https://arxiv.org/abs/2607.18236)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-20**|**FM-VLA: Force-based Memory for Vision-Language-Action Models in Contact-Rich Manipulation**|Ruicheng Li et.al.|[2607.18231](https://arxiv.org/abs/2607.18231)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-20**|**Reasoning as a Double-Edged Sword: Architecture and Cross-Stage Robustness in Vision-Language-Action Models**|Tuan Duong Trinh et.al.|[2607.17786](https://arxiv.org/abs/2607.17786)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-18**|**What Do They See? Interpreting Complex Road Scenarios Through the Eyes of Vision-Language-Action Models for Safe and Trustworthy Autonomous Vehicle Learning**|Kalpana Panda et.al.|[2607.16938](https://arxiv.org/abs/2607.16938)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-18**|**PhyAgentOS: A Self-Evolving Operating System for Embodied Agents with Decoupled Cognitive Planning and Physical Execution**|Yang Liu et.al.|[2607.16636](https://arxiv.org/abs/2607.16636)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-17**|**Foresight Residual RL for Long-Horizon Robot Manipulation with Vision-Language-Action Models**|Yuhan Liu et.al.|[2607.16506](https://arxiv.org/abs/2607.16506)|**[link](https://github.com/JaySparrow/foresight-residual-rl)**|
|**2026-07-17**|**IMBench: A Benchmark for Intuitive Robotic Manipulation**|Anurag Maurya et.al.|[2607.15641](https://arxiv.org/abs/2607.15641)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-22**|**Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories**|Xiaomi Robotics Team et.al.|[2607.15330](https://arxiv.org/abs/2607.15330)|**[link](https://github.com/DravenALG/awesome-vla-wam)**|
|**2026-07-16**|**CosFly-VLA: A Spatially Aware Vision-Language-Action Model for UAV Tracking**|Ruilong Ren et.al.|[2607.15004](https://arxiv.org/abs/2607.15004)|**[link](https://github.com/983632847/Awesome-Multimodal-Object-Tracking)**|
|**2026-07-16**|**FoMoVLA: Bridging Visual Foresight and Motion Guidance for Vision-Language-Action Models**|Wei Li et.al.|[2607.14739](https://arxiv.org/abs/2607.14739)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-16**|**Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models**|Yufeng Ji et.al.|[2607.14635](https://arxiv.org/abs/2607.14635)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-15**|**DiMaS: Distribution Matching for Steering Vision-Language-Action Models**|Pegah Khayatan et.al.|[2607.14280](https://arxiv.org/abs/2607.14280)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-15**|**S-squared-VLA: Decoupling Semantic and Spatial Streams in Vision-Language-Action Models for Autonomous Driving**|Jianguo Yu et.al.|[2607.13926](https://arxiv.org/abs/2607.13926)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-13**|**See like a Robot: Robot-Centric Pointmaps for Vision-Language-Action Models**|Byungkun Lee et.al.|[2607.11498](https://arxiv.org/abs/2607.11498)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-11**|**On the Efficiency of LoRA Fine-Tuning for Vision-Language-Action Models in Industrial Robotic Manipulation**|Finn Ferchau et.al.|[2607.10172](https://arxiv.org/abs/2607.10172)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-10**|**TS-Mask VLA: 2D Temporal-Spatial Masking for Vision-Language-Action Model with Effective Bridging**|Shengzhuo Yang et.al.|[2607.09818](https://arxiv.org/abs/2607.09818)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-10**|**PAC-ACT: Post-training Actor-Critic for Action Chunking Transformers**|Yujie Pang et.al.|[2607.09590](https://arxiv.org/abs/2607.09590)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-09**|**CLAP: Direct VLM-to-VLA Adaptation via Language-Action Grounding**|Yuri Ishitoya et.al.|[2607.08974](https://arxiv.org/abs/2607.08974)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-10**|**FabriVLA: A Lightweight Vision-Language-Action Model for Precise Multi-Task Manipulation**|Shiyuan Yang et.al.|[2607.08575](https://arxiv.org/abs/2607.08575)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-09**|**WCog-VLA: A Dual-Level World-Cognitive Vision-Language-Action Model for End-to-End Autonomous Driving**|Xuerun Yan et.al.|[2607.08375](https://arxiv.org/abs/2607.08375)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-07-13**|**Post-Training in End-to-End Autonomous Driving**|Ruining Yang et.al.|[2607.08072](https://arxiv.org/abs/2607.08072)|**[link](https://github.com/colorfulfuture/Awesome-Trajectory-Motion-Prediction-Papers)**|
|**2026-07-08**|**Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation**|Hongyu Qu et.al.|[2607.07608](https://arxiv.org/abs/2607.07608)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-07**|**Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinement**|Ryuji Oi et.al.|[2607.06370](https://arxiv.org/abs/2607.06370)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-06**|**From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Model**|Wenhao Li et.al.|[2607.05396](https://arxiv.org/abs/2607.05396)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-06**|**PRISM: Personalized Robotic Dataset Generation via Image-based Scene and Motion Synthesis**|Dogyu Ko et.al.|[2607.04880](https://arxiv.org/abs/2607.04880)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-06**|**CAC-VLA: Context-Gated Action Conditioning for Vision-Language-Action Models**|Yifu Xiong et.al.|[2607.04816](https://arxiv.org/abs/2607.04816)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-06**|**Do Vision-Language-Action Models Mean What They Say? On the Role of Faithfulness in Embodied Reasoning**|Matthew Foutter et.al.|[2607.04681](https://arxiv.org/abs/2607.04681)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-06**|**PixelPilot: Scalable Vision-Language-Action Models for End-to-End Autonomous Driving**|Pin Tang et.al.|[2607.04637](https://arxiv.org/abs/2607.04637)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-05**|**!Imperio, smolVLA: The Implications of Data Poisoning on Open Source Robotics**|Stefan Bühler et.al.|[2607.04146](https://arxiv.org/abs/2607.04146)|**[link](https://github.com/Trustworthy-AI-Group/Adversarial_Examples_Papers)**|
|**2026-07-04**|**CoRE-VLA: Towards Scalable and Robust Vision-Language-Action Modeling via Conditional Routing of Experts**|Haozhe Zhang et.al.|[2607.03693](https://arxiv.org/abs/2607.03693)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-03**|**Present but Not Remembered: Auditing How Frozen VLAs Encode, Deploy, and Steer Visual History**|Chih-Ting Liao et.al.|[2607.03372](https://arxiv.org/abs/2607.03372)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-03**|**AnchorVLA: Bridging Discrete Decisions and Continuous Trajectories for Vision-Language-Action Planning**|Qi Liu et.al.|[2607.03182](https://arxiv.org/abs/2607.03182)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-02**|**Bridge-WA: Predicting Where and How the World Changes for Robotic Action**|Yongjie Bai et.al.|[2607.02195](https://arxiv.org/abs/2607.02195)|**[link](https://huggingface.co/models/baiyu858/Bridge-WA-VLABench)**|
|**2026-07-02**|**Teaching Vision-Language-Action Models What to See and Where to Look**|Yuguang Yang et.al.|[2607.01658](https://arxiv.org/abs/2607.01658)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-02**|**VLAFlow: A Unified Training Framework for Vision-Language-Action Models via Co-training and Future Latent Alignment**|Guoyang Xia et.al.|[2607.01586](https://arxiv.org/abs/2607.01586)|**[link](https://github.com/MindVLA-Team/VLAFlow)**|
|**2026-07-01**|**Neuro-Symbolic Safety Guidance for Vision-Language-Action Models via Constrained Flow Matching**|William English et.al.|[2607.01378](https://arxiv.org/abs/2607.01378)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-01**|**FurnitureVLA: Learning Long-Horizon Bimanual Furniture Assembly with Vision-Language-Action Model**|Chenyang Ma et.al.|[2607.01212](https://arxiv.org/abs/2607.01212)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-01**|**Unleashing More Actions via Action Compositional Training for VLA Models**|Kai Peng et.al.|[2607.00351](https://arxiv.org/abs/2607.00351)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-30**|**Z-1: Efficient Reinforcement Learning for Vision-Language-Action Models**|Lang Cao et.al.|[2606.31846](https://arxiv.org/abs/2606.31846)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-30**|**UniTacVLA: Unified Tactile Understanding and Prediction in Vision Language Action Models**|Xidong Zhang et.al.|[2606.31723](https://arxiv.org/abs/2606.31723)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-30**|**Revisiting Parameter Redundancy in Vision-Language-Action Models: Insights from VLM-to-VLA Adaptation**|Fengnian Zhang et.al.|[2606.31382](https://arxiv.org/abs/2606.31382)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-01**|**3D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidance**|Dongyoon Hwang et.al.|[2606.31329](https://arxiv.org/abs/2606.31329)|**[link](https://huggingface.co/models/DAVIAN-Robotics/3D_HAMSTER)**|
|**2026-06-30**|**Reasoning-aware Speculative Decoding for Efficient Vision-Language-Action Models in Autonomous Driving**|Anh Dung Dinh et.al.|[2606.31160](https://arxiv.org/abs/2606.31160)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-30**|**ELASTIC: Efficiently Learning to Adaptively Scale Test-Time Compute for Generative Control Policies**|Andrew Zou Li et.al.|[2606.31132](https://arxiv.org/abs/2606.31132)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-28**|**Position: Vision-Language-Action Models Cannot Be Verified to Perform Physical Reasoning**|Taozhao Chen et.al.|[2606.30686](https://arxiv.org/abs/2606.30686)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-01**|**Training Vision-Language-Action Models with Dense Embodied Chain-of-Thought Supervision**|Haoyang Li et.al.|[2606.30552](https://arxiv.org/abs/2606.30552)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-29**|**Vision-Language-Action Models: Experimental Insights from a Real-World UR5 Platform**|Mathilde Hochedel et.al.|[2606.30456](https://arxiv.org/abs/2606.30456)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-29**|**SA-VLA: State-aware tokenizer for improving Vision-Language-Action Models' performance**|Tengyue Jiang et.al.|[2606.30113](https://arxiv.org/abs/2606.30113)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-29**|**Trust Your Instincts: Confidence-Driven Test-Time RL for Vision-Language-Action Models**|Siyao Chen et.al.|[2606.29892](https://arxiv.org/abs/2606.29892)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-29**|**Early Warning Signals for OpenVLA Failure under Visual Distribution Shift**|Dipesh Tharu Mahato et.al.|[2606.29699](https://arxiv.org/abs/2606.29699)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-28**|**Event-VLA: Action-Conditioned Event Fusion for Robust Vision-Language-Action Model**|Jiaxin Liu et.al.|[2606.29384](https://arxiv.org/abs/2606.29384)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-28**|**Fast Enough to Act: Spatio-Temporal Visual Token Merging for Low-Latency Robotic VLMs and VLAs**|Junzhou Chen et.al.|[2606.29350](https://arxiv.org/abs/2606.29350)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-28**|**SurgVLA-Bench: Towards Evaluating Vision-Language-Action Models for Laparoscopic Surgical Robotics**|Jiashuo Sun et.al.|[2606.29247](https://arxiv.org/abs/2606.29247)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-27**|**TAP-VLA: Tactile Annotation Prompting for Vision Language Action Models**|Mark Van der Merwe et.al.|[2606.29089](https://arxiv.org/abs/2606.29089)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-26**|**Robotic Arm-Based Spectral Sensing for Strawberry Positioning and Non-Destructive Sweetness Measurement**|Yi Yang et.al.|[2606.28555](https://arxiv.org/abs/2606.28555)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-26**|**Translation as a Bridging Action: Transferring Manipulation Skills from Humans to Robots**|Sijin Chen et.al.|[2606.28133](https://arxiv.org/abs/2606.28133)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-26**|**S $^2$ -VLA: State-Space Guided Vision-Language-Action Models for Long-Horizon Manipulation**|Zhipeng Xie et.al.|[2606.27872](https://arxiv.org/abs/2606.27872)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-26**|**SpikeVLA: Vision-Language-Action Models with Spiking Neural Networks**|Ruiqi Song et.al.|[2606.27807](https://arxiv.org/abs/2606.27807)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-26**|**Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models?**|Guoheng Sun et.al.|[2606.27755](https://arxiv.org/abs/2606.27755)|**[link](https://huggingface.co/models/s1ghhh/VLADrop_pi05_LIBERO_Baseline)**|
|**2026-06-25**|**E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulation**|Wen Ye et.al.|[2606.27268](https://arxiv.org/abs/2606.27268)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-27**|**ForesightSafety-VLA: A Unified Diagnostic Safety Benchmark for Vision-Language-Action Models**|Mingyang Lyu et.al.|[2606.27079](https://arxiv.org/abs/2606.27079)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-25**|**Improving Vision-Language-Action Model Fine-Tuning with Structured Stage and Keyframe Supervision**|Yuan Xu et.al.|[2606.26801](https://arxiv.org/abs/2606.26801)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-24**|**Action ControlNet: A Lightweight Delay-Aware Adapter for Smooth Asynchronous Control in Vision-Language-Action Models**|Tiecheng Guo et.al.|[2606.25985](https://arxiv.org/abs/2606.25985)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-24**|**ROAD-VLA: Robust Online Adaptation via Self-Distillation for Vision-Language-Action Models**|Kejing Wang et.al.|[2606.25800](https://arxiv.org/abs/2606.25800)|**[link](https://github.com/chrisliu298/awesome-on-policy-distillation)**|
|**2026-06-23**|**MANGO: Automated Multi-Agent Test Oracle Generation for Vision-Language-Action Models**|Pablo Valle et.al.|[2606.24815](https://arxiv.org/abs/2606.24815)|**[link](https://github.com/tmgthb/Autonomous-Agents)**|
|**2026-06-23**|**G $^3$ VLA: Geometric inductive bias for Vision-Language-Action Models**|Yue Peng et.al.|[2606.24472](https://arxiv.org/abs/2606.24472)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-23**|**DriveStack-VLA: Render-Teacher Alignment for BEV-Based DeepStack Vision-Language-Action Model**|Jingke Wang et.al.|[2606.24051](https://arxiv.org/abs/2606.24051)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-22**|**Verifiable Foundation Models for Robot Safety**|Davide Corsi et.al.|[2606.23754](https://arxiv.org/abs/2606.23754)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-22**|**LIBERO-Safety: A Comprehensive Benchmark for Physical and Semantic Safety in Vision-Language-Action Models**|Rongxu Cui et.al.|[2606.23686](https://arxiv.org/abs/2606.23686)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-22**|**Flatness Preserves Instruction Following in Vision-Language-Action Models**|Haochen Zhang et.al.|[2606.23641](https://arxiv.org/abs/2606.23641)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-22**|**dVLA-RL: Reinforcement Learning over Denoising Trajectories for Discrete Diffusion Vision-Language-Action Models**|Yuhao Wu et.al.|[2606.23623](https://arxiv.org/abs/2606.23623)|**[link](https://github.com/zezhishao/DailyArXiv)**|
|**2026-06-22**|**RECALL: Recovery Experience Collection for Active Lifelong Learning in Vision-Language-Action Models**|Ulas Berk Karli et.al.|[2606.23617](https://arxiv.org/abs/2606.23617)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-22**|**BiliVLA: Scene-Aware Vision-Language-Action Model with Reinforcement Learning for Autonomous Biliary Endoscopic Navigation**|Jinsong Lin et.al.|[2606.23531](https://arxiv.org/abs/2606.23531)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-22**|**Flowing With Purpose: Latent Action Guided Flow Matching Policies For Robotic Manipulation**|Bruno Machado et.al.|[2606.23420](https://arxiv.org/abs/2606.23420)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-22**|**Assistron: Bayesian Shared Autonomy with Off-the-shelf Vision-Language-Action Models**|Pinhao Song et.al.|[2606.23147](https://arxiv.org/abs/2606.23147)|**[link](https://github.com/mousecpn/Assistron)**|
|**2026-06-22**|**UniFS: Unified Fast-to-Slow Hierarchical Architecture for Vision-Language-Action Models**|Lin Sun et.al.|[2606.22794](https://arxiv.org/abs/2606.22794)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-25**|**PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models**|Xianghui Wang et.al.|[2606.22540](https://arxiv.org/abs/2606.22540)|**[link](https://huggingface.co/models/INCEPTIONwang/PolicyTrim)**|
|**2026-06-19**|**UniviewVLA: A Unified Multiview Vision-Language-Action Model with World Modeling**|Tao Xu et.al.|[2606.21501](https://arxiv.org/abs/2606.21501)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-19**|**Decoupling the Declarative from the Procedural in Vision-Language-Action Models**|Nikolaos Tsagkas et.al.|[2606.21496](https://arxiv.org/abs/2606.21496)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-19**|**Semi-Supervised Vision-Language-Action Model**|Hongyang He et.al.|[2606.21493](https://arxiv.org/abs/2606.21493)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-19**|**VLA-FAIL: Efficient Task Failure Detection for Finetuned Vision-Language-Action Models**|Florian Seligmann et.al.|[2606.21386](https://arxiv.org/abs/2606.21386)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-19**|**NAC: Neural Action Codec for Vision-Language-Action Models**|Ahad Jawaid et.al.|[2606.21372](https://arxiv.org/abs/2606.21372)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-19**|**Remember what you did?: Learning Behavioral Memories for Partially Observable Object Manipulation**|Kuancheng Wang et.al.|[2606.21188](https://arxiv.org/abs/2606.21188)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-19**|**Inductive Generalization for Robotic Manipulation**|Annabella Macaluso et.al.|[2606.20999](https://arxiv.org/abs/2606.20999)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-18**|**Geometric Entropy: When Trajectory Diversity Helps and Hurts in Imitation Learning**|Qian Luo et.al.|[2606.20871](https://arxiv.org/abs/2606.20871)|**[link](https://github.com/zezhishao/DailyArXiv)**|
|**2026-06-18**|**SignVLA: Real-Time Sign Language-Guided Robotic Manipulation via Attention LSTM and Vision-Language-Action Models**|Ningwei Bai et.al.|[2606.20857](https://arxiv.org/abs/2606.20857)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-18**|**Slow Brain, Fast Planner: Latency-Resilient VLM-Augmented Urban Navigation**|Zhenghao "Mark'' Peng et.al.|[2606.20458](https://arxiv.org/abs/2606.20458)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-20**|**Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think**|Gia-Binh Nguyen et.al.|[2606.20246](https://arxiv.org/abs/2606.20246)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-18**|**Frequency-Aware Flow Matching for Continuous and Consistent Robotic Action Generation**|Jianing Guo et.al.|[2606.20135](https://arxiv.org/abs/2606.20135)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-18**|**EquiVLA: A General Framework for Rotationally Equivariant Vision-Language-Action Models**|Thien-Loc Ha et.al.|[2606.19784](https://arxiv.org/abs/2606.19784)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-17**|**Mix-QVLA: Task-Evidence-Aware Mixed-Precision Quantization of Vision-Language-Action Models**|Navin Ranjan et.al.|[2606.19565](https://arxiv.org/abs/2606.19565)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-17**|**Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models**|Nikita Kachaev et.al.|[2606.19297](https://arxiv.org/abs/2606.19297)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-16**|**Uncertainty Quantification for Flow-Based Vision-Language-Action Models**|Ralf Römer et.al.|[2606.18043](https://arxiv.org/abs/2606.18043)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-16**|**MuseVLA: An Adaptive Multimodal Sensing Vision-Language-Action Model for Robotic Manipulation**|Xingyuming Liu et.al.|[2606.17598](https://arxiv.org/abs/2606.17598)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-15**|**Geometric Action Model for Robot Policy Learning**|Jisang Han et.al.|[2606.17046](https://arxiv.org/abs/2606.17046)|**[link](https://github.com/DravenALG/awesome-vla-wam)**|
|**2026-06-15**|**Learned Image Compression for Vision-Language-Action Models**|Hyeonjun Kim et.al.|[2606.16253](https://arxiv.org/abs/2606.16253)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-14**|**Metis: A Generalizable and Efficient World-Action Model for Autonomous Driving and Urban Navigation**|Jingyu Li et.al.|[2606.15869](https://arxiv.org/abs/2606.15869)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-14**|**LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies**|Jialei Chen et.al.|[2606.15768](https://arxiv.org/abs/2606.15768)|**[link](https://huggingface.co/models/jialei02/lawam_pretrain)**|
|**2026-06-14**|**Beyond English: Uncovering the Multilingual Gap in Vision-Language-Action Models**|Hanyang Chen et.al.|[2606.15714](https://arxiv.org/abs/2606.15714)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-14**|**Retrieve, Don't Retrain: Extending Vision Language Action Models to New Tasks at Test Time**|Jeongeun Park et.al.|[2606.15631](https://arxiv.org/abs/2606.15631)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-13**|**Acting While Understanding: Asynchronous Semantic-Action Decoupling for Real-Time Vision-Language-Action Models**|Shenhao Yan et.al.|[2606.15285](https://arxiv.org/abs/2606.15285)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-13**|**VLALeaks: Membership Inference Attacks against Vision-Language-Action Models**|Xukun Luan et.al.|[2606.15165](https://arxiv.org/abs/2606.15165)|**[link](https://github.com/Trustworthy-AI-Group/Adversarial_Examples_Papers)**|
|**2026-06-13**|**MotionVLA: Vision-Language-Action Model for Humanoid Motion**|Nonghai Zhang et.al.|[2606.15142](https://arxiv.org/abs/2606.15142)|**[link](https://github.com/Foruck/Awesome-Human-Motion)**|
|**2026-06-13**|**Think Less, Act Early: Reinforced Latent Reasoning with Early Exit in Vision-Language-Action Models**|Dianqiao Lei et.al.|[2606.15099](https://arxiv.org/abs/2606.15099)|**[link](https://github.com/EIT-NLP/Awesome-Latent-CoT)**|
|**2026-06-12**|**Hy-Embodied-0.5-VLA: From Vision-Language-Action Models to a Real-World Robot Learning Stack**|He Zhang et.al.|[2606.14409](https://arxiv.org/abs/2606.14409)|**[link](https://huggingface.co/models/tencent/Hy-Embodied-0.5-VLA-RoboTwin)**|
|**2026-06-12**|**RT-VLA: Real-Time Vision-Language-Action Models via Knowledge Distillation**|Xiangyu Huang et.al.|[2606.14010](https://arxiv.org/abs/2606.14010)|**[link](https://github.com/Thinklab-SJTU/Awesome-LLM4AD)**|
|**2026-06-11**|**Output-Level Regularization Eliminates the Seed Lottery in Single-GPU VLA Fine-Tuning**|Jeffrin Sam et.al.|[2606.13856](https://arxiv.org/abs/2606.13856)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-15**|**LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories**|Baochang Ren et.al.|[2606.13578](https://arxiv.org/abs/2606.13578)|**[link](https://github.com/wadeKeith/Awesome-Embodied-AI)**|
|**2026-06-11**|**GIVE: Grounding Human Gestures in Vision-Language-Action Models**|Pengfei Liu et.al.|[2606.13435](https://arxiv.org/abs/2606.13435)|**[link](https://github.com/wadeKeith/Awesome-Embodied-AI)**|
|**2026-06-11**|**Real-Time Execution with Autoregressive Policies**|Sangkyu Lee et.al.|[2606.13355](https://arxiv.org/abs/2606.13355)|**[link](https://github.com/wadeKeith/Awesome-Embodied-AI)**|
|**2026-06-13**|**Trajectory-Level Redirection Attacks on Vision-Language-Action Models**|Gokul Puthumanaillam et.al.|[2606.12978](https://arxiv.org/abs/2606.12978)|**[link](https://github.com/Trustworthy-AI-Group/Adversarial_Examples_Papers)**|
|**2026-06-10**|**World Pilot: Steering Vision-Language-Action Models with World-Action Priors**|Zefu Lin et.al.|[2606.12403](https://arxiv.org/abs/2606.12403)|**[link](https://huggingface.co/models/Chedan86/WorldPilot-LIBERO)**|
|**2026-06-10**|**VLGA: Vision-Language-Geometry-Action Models for Autonomous Driving**|Jin Yao et.al.|[2606.12396](https://arxiv.org/abs/2606.12396)|**[link](https://github.com/Thinklab-SJTU/Awesome-LLM4AD)**|
|**2026-06-10**|**Learning What to Say to Your VLA: Mostly Harmless Vision Language Action Model Steering**|Hyun Joe Jeong et.al.|[2606.12299](https://arxiv.org/abs/2606.12299)|**[link](https://github.com/wadeKeith/Awesome-Embodied-AI)**|
|**2026-06-10**|**DAM-VLA: Decoupled Asynchronous Multimodal Vision Language Action model**|Pankhuri Vanjani et.al.|[2606.12105](https://arxiv.org/abs/2606.12105)|**[link](https://github.com/wadeKeith/Awesome-Embodied-AI)**|
|**2026-06-10**|**When Does Language Matter? Multilingual Instructions Reveal Step-wise Language Sensitivity in Vision-Language-Action Models**|Xuan Dong et.al.|[2606.11906](https://arxiv.org/abs/2606.11906)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-10**|**Vision-Language-Action Models Meet World Models: Embodied Agentic AI for Low-Altitude Wireless Networks**|Feibo Jiang et.al.|[2606.11618](https://arxiv.org/abs/2606.11618)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-09**|**Dynamic Execution Horizon Prediction for Chunk-based Robot Policies**|Yuchi Zhao et.al.|[2606.11408](https://arxiv.org/abs/2606.11408)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-09**|**LIBERO-Occ: Evaluating and Improving Vision-Language-Action Models under Scene-Induced Occlusion via Viewpoint Imagination**|Taishan Li et.al.|[2606.10862](https://arxiv.org/abs/2606.10862)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-09**|**VeriSpace: Spatially Grounded Action Verification for Vision-Language-Action Models**|Guiyu Zhao et.al.|[2606.10568](https://arxiv.org/abs/2606.10568)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-09**|**Uncovering Vulnerability of Vision-Language-Action Models under Joint-Level Physical Faults**|Minsoo Jo et.al.|[2606.10501](https://arxiv.org/abs/2606.10501)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-09**|**Act on What You See: Unlocking Safe Social Navigation in Vision-Language-Action Models**|Qingzi Wang et.al.|[2606.10495](https://arxiv.org/abs/2606.10495)|**[link](https://github.com/wadeKeith/Awesome-Embodied-AI)**|
|**2026-06-08**|**Flow Control: Steering Vision-Language-Action Models with Simple Real-Time Inputs**|Jonathan C. Kao et.al.|[2606.10180](https://arxiv.org/abs/2606.10180)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-08**|**MemoryVLA++: Temporal Modeling via Memory and Imagination in Vision-Language-Action Models**|Hao Shi et.al.|[2606.09827](https://arxiv.org/abs/2606.09827)|**[link](https://github.com/shihao1895/MemoryVLA)**|
|**2026-06-08**|**Your Model Already Knows: Attention-Guided Safety Filter for Vision-Language-Action Models**|Seongbin Park et.al.|[2606.09749](https://arxiv.org/abs/2606.09749)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-08**|**ProbeAct: Probe-Guided Training-Free Failure Recovery in Vision-Language-Action Models**|Fan Zhang et.al.|[2606.09740](https://arxiv.org/abs/2606.09740)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-08**|**CT-VAM: A Cerebello-Thalamic-Inspired Vision-Action Model for Efficient Visuomotor Control**|Jiacheng Li et.al.|[2606.09572](https://arxiv.org/abs/2606.09572)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-08**|**Scaling by Diversified Experience for Vision-Language-Action Models**|Leiyu Wang et.al.|[2606.09009](https://arxiv.org/abs/2606.09009)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-07**|**Benchmarking Vision-Language-Action Models on SO-101: Failure and Recovery Analysis**|Yi Yu et.al.|[2606.08881](https://arxiv.org/abs/2606.08881)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-07**|**BLUE: Toward Better Language Use in Efficient Vision-Language-Action Models for Autonomous Driving**|George Ling et.al.|[2606.08684](https://arxiv.org/abs/2606.08684)|**[link](https://huggingface.co/models/George-Ling/blue_gate)**|
|**2026-06-06**|**MotionVLA: Injecting Geometric Motion into Vision-Language-Action Model**|Shanglin Yuan et.al.|[2606.08288](https://arxiv.org/abs/2606.08288)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-06**|**vla.cpp: A Unified Inference Runtime for Vision-Language-Action Models**|Khanh D. Nguyen et.al.|[2606.08094](https://arxiv.org/abs/2606.08094)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-05**|**TBD-VLA: Temporal Block Diffusion Vision Language Action Model**|Sung-Wook Lee et.al.|[2606.07895](https://arxiv.org/abs/2606.07895)|**[link](https://huggingface.co/models/sean1295/tbdvla_libero)**|
|**2026-06-05**|**Coarse-to-Control: Action-Token Planning for Vision-Language-Action Models**|Jinhao Wu et.al.|[2606.07107](https://arxiv.org/abs/2606.07107)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-05**|**LARA: Latent Action Representation Alignment for Vision-Language-Action Models**|Mengya Liu et.al.|[2606.07100](https://arxiv.org/abs/2606.07100)|**[link](https://github.com/DravenALG/awesome-vla-wam)**|
|**2026-06-04**|**TempoVLA: Learning Speed-Controllable Vision-Language-Action Policies**|Dong Jing et.al.|[2606.06491](https://arxiv.org/abs/2606.06491)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-04**|**AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding**|Qize Yu et.al.|[2606.06155](https://arxiv.org/abs/2606.06155)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-04**|**WorldFly: A World-Model-Based Vision-Language-Action Model for UAV Navigation**|Shengtao Zheng et.al.|[2606.06147](https://arxiv.org/abs/2606.06147)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-04**|**Let It Be Simple: One-Step Action Generation for Vision-Language-Action Models**|Yitong Chen et.al.|[2606.05737](https://arxiv.org/abs/2606.05737)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-03**|**3DThinkVLA: Endowing Vision-Language-Action Models with Latent 3D Priors via 3D-Thinking-Guided Co-training**|Jiaxin Shi et.al.|[2606.04436](https://arxiv.org/abs/2606.04436)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-02**|**Dive into the Scene: Breaking the Perceptual Bottleneck in Vision-Language Decision Making via Focus Plan Generation**|Boyuan Xiao et.al.|[2606.04046](https://arxiv.org/abs/2606.04046)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-03**|**PHASER: Phase-Aware and Semantic Experience Replay for Vision-Language-Action Models**|Ziyang Chen et.al.|[2606.03598](https://arxiv.org/abs/2606.03598)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-02**|**Partially Observable Adversarial Patch Attacks on Vision-Language-Action Models in Robotics**|Xiaofei Wang et.al.|[2606.03556](https://arxiv.org/abs/2606.03556)|**[link](https://github.com/liudaizong/Awesome-LVLM-Attack)**|
|**2026-06-02**|**TTT-VLA: Test-Time Latent Prompt Optimization for Vision-Language-Action Models**|Wenbo Zhang et.al.|[2606.03127](https://arxiv.org/abs/2606.03127)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-01**|**SeeTraceAct: Visibility-Aware Latent Planning from Cross-Embodiment Demonstration Videos**|Jaehyeon Son et.al.|[2606.02745](https://arxiv.org/abs/2606.02745)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-01**|**FATE-VLA:Failue-aware test generation for vision-language-action models**|Arusa Kanwal et.al.|[2606.02307](https://arxiv.org/abs/2606.02307)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-05-31**|**Lagrangian Perturbation Diffusion Steering: Latent Reinforcement Learning for Generative Policies**|Hikmet Simsir et.al.|[2606.01151](https://arxiv.org/abs/2606.01151)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-05-31**|**Threading Optimization for Vision-Language-Action Model Inference in Low-Cost Smart Agricultural Manipulation**|Keith Truongcao et.al.|[2606.00966](https://arxiv.org/abs/2606.00966)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-05-30**|**SafeVLA-Bench: A Benchmark for the Success-Safety Gap in Vision-Language-Action Models**|Jialiang Fan et.al.|[2606.00773](https://arxiv.org/abs/2606.00773)|**[link](https://github.com/BaiShuanghao/Awesome-Robotics-Manipulation)**|
|**2026-05-29**|**Closed-Loop Neural Activation Control in Vision-Language-Action Models**|Abhijith Babu et.al.|[2606.00269](https://arxiv.org/abs/2606.00269)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-05-29**|**Per-Group Error, Not Total MSE: Fine-Tuning Vision-Language-Action Models for 11-DoF Mobile Manipulation**|Pau Montagut Bofi et.al.|[2606.00253](https://arxiv.org/abs/2606.00253)|**[link](https://huggingface.co/models/PauMontagut/per-group-mse-smolvla)**|
|**2026-05-29**|**DriveMA: Driving Vision-Language-Action Models with verifiable Meta-Actions**|Weicheng Zheng et.al.|[2605.31271](https://arxiv.org/abs/2605.31271)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-05-29**|**HARP-VLA: Human-Robot Aligned Representation Learning for Vision-Language-Action Model**|Xiang Zhu et.al.|[2605.31234](https://arxiv.org/abs/2605.31234)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-05-29**|**Does Visual Information Play a Decisive Role in Vision-Language-Action Model Driving Behavior?**|Jingtao He et.al.|[2605.31041](https://arxiv.org/abs/2605.31041)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-05-28**|**ELAN4D: Embodiment-Centric 4D Supervision for Vision-Language-Action Models via Plug-and-Play Adaptation**|Zeyuan He et.al.|[2605.30484](https://arxiv.org/abs/2605.30484)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-01**|**Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments**|Qiuyue Wang et.al.|[2605.30280](https://arxiv.org/abs/2605.30280)|**[link](https://github.com/jonyzhang2023/awesome-embodied-vla-va-vln)**|
|**2026-05-28**|**VLA-Trace: Diagnosing Vision-Language-Action Models through Representation and Behavior Tracing**|Haoyuan Shi et.al.|[2605.30117](https://arxiv.org/abs/2605.30117)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-05-28**|**VLAConf: Calibrated Task-Success Confidence for Vision-Language-Action Models**|Dehao Huang et.al.|[2605.29605](https://arxiv.org/abs/2605.29605)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-05-28**|**Mitigating State Aliasing in Vision-Language-Action Models via Inverse Dynamics Learning**|Kyujin Lee et.al.|[2605.29577](https://arxiv.org/abs/2605.29577)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|

(<a href=#updated-on-20260823>back to top</a>)

## Imitation Learning

|Publish Date|Title|Authors|PDF|Code|
|---|---|---|---|---|
|**2026-08-20**|**Planning-Oriented End-to-End Autonomous Driving: Architectures, Evaluation, and Emerging Paradigms**|Yanchen Guan et.al.|[2608.20111](https://arxiv.org/abs/2608.20111)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-20**|**Learning Highly Dynamic Skills Transition for Quadruped Jumping Through Constrained Space**|Zeren Luo et.al.|[2608.19977](https://arxiv.org/abs/2608.19977)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-19**|**ADEPT: Accelerating Dexterity via Pre-Training and Post-Training using Reinforcement Learning**|Jayjun Lee et.al.|[2608.19182](https://arxiv.org/abs/2608.19182)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-19**|**HarvestPoint-ACT: Explicit Target Selection and Harvest-Point Conditioning for Robotic Fruit Harvesting under Occlusion**|Hanying Hu et.al.|[2608.18446](https://arxiv.org/abs/2608.18446)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-18**|**VERAGMIL: Virtual Environment for Scooping Granular Foods with Imitation Learning Models**|Amanuel Ergogo et.al.|[2608.18258](https://arxiv.org/abs/2608.18258)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-18**|**Revisiting the "Push-T" Robot Manipulation Task with Agentic Robotics**|Shuangyu Xie et.al.|[2608.18227](https://arxiv.org/abs/2608.18227)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-18**|**UniReflex: Plug-and-Play Force Control for Pretrained Generative Policies via Fast-Slow Reflex**|Yan Huang et.al.|[2608.17432](https://arxiv.org/abs/2608.17432)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-18**|**Repetition as Reinforcement: Enhancing Sample Efficiency via Instant Episode Repetition in Reinforcement Learning**|Hoda Yamani et.al.|[2608.17347](https://arxiv.org/abs/2608.17347)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-18**|**ORPA: Online Residual Policy Adaptation for Robot Manipulation Control with Human Feedback**|Muhammad A. Muttaqien et.al.|[2608.17323](https://arxiv.org/abs/2608.17323)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-18**|**Robust Brachiation on a Life-Sized Dual-Arm Robot Using Waypoint-Guided Reinforcement Learning**|Ayumu Iwata et.al.|[2608.17320](https://arxiv.org/abs/2608.17320)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-17**|**FetchMan: Learning Visual Humanoid Loco-Manipulation Policies from Simulated Experiences**|Omar Rayyan et.al.|[2608.17027](https://arxiv.org/abs/2608.17027)|null|
|**2026-08-17**|**HAF: Adapting Generalist VLAs to Humanoid Whole-Body Loco-manipulation via Hierarchical Action Flow and Spectral Latent RL**|Langzhe Gu et.al.|[2608.16837](https://arxiv.org/abs/2608.16837)|null|
|**2026-08-17**|**MatchingPolicy: Correspondence-Aware Policy Enables Cross-Object In-Context Learning**|Qijin She et.al.|[2608.16715](https://arxiv.org/abs/2608.16715)|null|
|**2026-08-18**|**PANDA: A Matrix-Free Differentiable NMPC Solver via Proximal Averaged Quasi-Newton with Adaptive Linesearch Algorithm**|Yuankun Chen et.al.|[2608.16280](https://arxiv.org/abs/2608.16280)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-17**|**SurgVIL: Scaling Surgical Robot Imitation Learning with Open-source Surgical Videos**|Xinhao Chen et.al.|[2608.16058](https://arxiv.org/abs/2608.16058)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-19**|**Revisiting Open-Loop Execution in Robotics: Toward Reactive, Higher-Performing Policies**|Michael Zeng et.al.|[2608.15938](https://arxiv.org/abs/2608.15938)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-16**|**RAPAC-DP: Response-Aligned Pending-Action Compensation for Diffusion Policies under Delayed Execution**|Tao Wang et.al.|[2608.15924](https://arxiv.org/abs/2608.15924)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-16**|**Pre-training Visual Dexterity in Simulation**|Sarthak Kamat et.al.|[2608.15917](https://arxiv.org/abs/2608.15917)|**[link](https://github.com/YanjieZe/Paper-List)**|
|**2026-08-16**|**Learning Stock Trading Policies via Barycenter-Based Adversarial Inverse Reinforcement Learning**|Arishi Orra et.al.|[2608.15770](https://arxiv.org/abs/2608.15770)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-15**|**Learning Sequential Mobility Choice: A Review of Route and Activity Choice through Inverse Reinforcement and Imitation Learning**|Tien Mai et.al.|[2608.15339](https://arxiv.org/abs/2608.15339)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-14**|**PILOT: Privileged Imitation Learning for End-to-End Motion Planning of Autonomous UAVs under Partial Observability**|Qingrui Zhang et.al.|[2608.14082](https://arxiv.org/abs/2608.14082)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-13**|**Dynamic Multi-Depot Vehicle Routing with Online Requests: Event-Driven Transformer--DRL and Rolling-Horizon Benchmarking**|Faezeh Ardali et.al.|[2608.13799](https://arxiv.org/abs/2608.13799)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-12**|**Enhancing Visual Domain Robustness in Behaviour Cloning via Saliency-Guided Augmentation**|Zheyu Zhuang et.al.|[2608.11870](https://arxiv.org/abs/2608.11870)|**[link](https://github.com/zheyu-zhuang/RoboSaGA)**|
|**2026-08-11**|**Adaptation of Generalist Robot Policies with Minimal Data**|Shreyas Kowshik et.al.|[2608.11363](https://arxiv.org/abs/2608.11363)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-11**|**Enabling Scalable Kinesthetic Teaching via Observer-based Hand-guiding with Active Support**|Anna Tuma et.al.|[2608.10847](https://arxiv.org/abs/2608.10847)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-10**|**RecoverFly: A Failure-Aware Reinforcement Learning Post-Training Framework for Aerial Vision-Language Navigation**|Boxiong Wang et.al.|[2608.09467](https://arxiv.org/abs/2608.09467)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-10**|**Skills in Weights, Memory in Code: Hybrid Learning for Memory-Dependent Robot Manipulation**|Yunhao Zhao et.al.|[2608.09410](https://arxiv.org/abs/2608.09410)|null|
|**2026-08-10**|**SAFE-CHEM: Uncertainty-Aware Policy Switching for Robust Robotic Chemistry**|Laura Jones et.al.|[2608.09303](https://arxiv.org/abs/2608.09303)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-11**|**SpeedTuning: Speeding Up Policy Execution with Lightweight Reinforcement Learning**|David D. Yuan et.al.|[2608.09138](https://arxiv.org/abs/2608.09138)|**[link](https://github.com/DoongLi/ICRA2025-Paper-List)**|
|**2026-08-08**|**SAGE: SLO-Aware Adaptive Retrieval for Production RAG Systems**|Muhammad Faizan Raza et.al.|[2608.08237](https://arxiv.org/abs/2608.08237)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-02**|**AeroDPO: Unleashing Lightweight UAV Navigation with High-Fidelity Perception and Automated Preference Optimization**|Peng Xu et.al.|[2608.07557](https://arxiv.org/abs/2608.07557)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-07**|**AutoIntervene: Calibrated Intervention for Action-Chunking Imitation Learning Policies**|Jinhe Tang et.al.|[2608.07065](https://arxiv.org/abs/2608.07065)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-09**|**$ω$ -0: A Latent Predictive World Action Model for Concurrent Humanoid Loco-Manipulation**|Zhe Li et.al.|[2608.06375](https://arxiv.org/abs/2608.06375)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-08-06**|**VIDP: Variable Impedance Diffusion Policy for Compliant Robot Manipulation from Diverse Demonstrations**|Hisham Khalil et.al.|[2608.06210](https://arxiv.org/abs/2608.06210)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-06**|**In-Context VLA: Endowing Vision-Language-Action Models with Language via In-Context Post-Training and Agentic Tool Use**|Jiarui Yang et.al.|[2608.05738](https://arxiv.org/abs/2608.05738)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-05**|**Spectral Distillation: From Nonlinear Dynamics to Linear State-Space Models**|Liane Galanti et.al.|[2608.05416](https://arxiv.org/abs/2608.05416)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-04**|**Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent**|Zhen Fang et.al.|[2608.03979](https://arxiv.org/abs/2608.03979)|**[link](https://github.com/zli12321/Vision-Language-Models-Overview)**|
|**2026-08-04**|**Bimanual Manipulation Within an 8 GB Budget: Zero-Copy Sensing and Quantized ACT on an Entry-Level Jetson**|Ekansh Singh et.al.|[2608.03938](https://arxiv.org/abs/2608.03938)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-04**|**Learning Clinical-Trial Strategy: Offline Policy Training for Decision Agents**|William Bolton et.al.|[2608.03606](https://arxiv.org/abs/2608.03606)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-04**|**A Hierarchical Approach to Imitation Learning for Manipulation Tasks Requiring Time Varying Forces**|Rishabh Shukla et.al.|[2608.03103](https://arxiv.org/abs/2608.03103)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-03**|**ValueFormer: A Causal Transformer Value Function with Stage-Aware Labels for Semi-Autonomous Vision-Language-Action Policies**|Inkyu Sa et.al.|[2608.02958](https://arxiv.org/abs/2608.02958)|null|
|**2026-08-03**|**Why Does Action Chunking Improve Behavioral Cloning Performance in Robotic Control?**|Filippo Lazzati et.al.|[2608.02547](https://arxiv.org/abs/2608.02547)|**[link](https://github.com/YanjieZe/Paper-List)**|
|**2026-08-03**|**TWINS: A Tactile Wearable Isomorphic Arm Networked System for Contact-Rich Manipulation Learning**|Takahide Kitamura et.al.|[2608.01733](https://arxiv.org/abs/2608.01733)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-08-03**|**AffordTrajDP: Dynamic Affordance-Guided Visuomotor Policy Learning for Robotic Manipulation**|Gaoyuan Wu et.al.|[2608.01603](https://arxiv.org/abs/2608.01603)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-31**|**RayViT: Ray-Conditioned Visual Representations for Viewpoint-Robust Imitation Learning**|Qian Wang et.al.|[2607.29622](https://arxiv.org/abs/2607.29622)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-31**|**When Does On-Policy Interaction Help? Representational Tradeoffs in Value-Based Imitation Learning**|Luca Viano et.al.|[2607.29617](https://arxiv.org/abs/2607.29617)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-31**|**STAGE: STyle-controllable Action GEneration for personalized autonomous driving**|Zihao Liu et.al.|[2607.29517](https://arxiv.org/abs/2607.29517)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-31**|**BWM: A Low-Cost High-Fidelity World Simulator for Robot Learning**|BWM Team et.al.|[2607.29302](https://arxiv.org/abs/2607.29302)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-08-06**|**TRACT: Temporally Routed Action Chunks with Chronological Phase Authority for Contact-Rich Manipulation**|Jiahao Liu et.al.|[2607.29285](https://arxiv.org/abs/2607.29285)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-30**|**Mirror Learning**|Yunpeng Liu et.al.|[2607.28737](https://arxiv.org/abs/2607.28737)|**[link](https://github.com/yingchengyang/Reinforcement-Learning-Papers)**|
|**2026-07-30**|**ACE-Data-0: Human-Centric Ambient Capture as Embodied Data Engine**|Yukang Cao et.al.|[2607.28625](https://arxiv.org/abs/2607.28625)|**[link](https://huggingface.co/datasets/ACERobotics/ACE-Data-0)**|
|**2026-07-30**|**LM-GRASP: Instance-Specific Language Models for Combinatorial Construction via Online Imitation Learning**|Mohand Mezmaz et.al.|[2607.28135](https://arxiv.org/abs/2607.28135)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-30**|**World Action Planner: Generalizable Decision-Making with Action-Conditioned World Models**|Xiangcheng Zhang et.al.|[2607.27599](https://arxiv.org/abs/2607.27599)|**[link](https://huggingface.co/models/XiangchengZhang/world-action-planner)**|
|**2026-07-30**|**Cross-Embodiment Transfer via Behavior-Aligned Representations**|Ajay Sridhar et.al.|[2607.27549](https://arxiv.org/abs/2607.27549)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-29**|**Failure Detection for Surgical Robot Imitation Policies via Flow-Matching World Modeling**|Zhefeng Huang et.al.|[2607.27511](https://arxiv.org/abs/2607.27511)|**[link](https://github.com/LMD0311/Awesome-World-Model)**|
|**2026-07-29**|**It's Not Just More Demos: Counterfactual Action Sensitivity Coverage for Data-Efficient Robust Robot Imitation**|Giovanni D'urso et.al.|[2607.27261](https://arxiv.org/abs/2607.27261)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-30**|**RL $^2$ -VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models**|Derek Ming Siang Tan et.al.|[2607.26991](https://arxiv.org/abs/2607.26991)|**[link](https://huggingface.co/models/rl2-vla/rl2-vla-qam-bridge)**|
|**2026-07-31**|**Temporally Centered SIGReg Improves Multi-Task LeWorldModel Learning: From Analysis to Method**|Chang Liu et.al.|[2607.26924](https://arxiv.org/abs/2607.26924)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-29**|**Beyond Action Imitation: Learning a Decision-Aware User Simulator for Online Advertising**|Zipeng Chen et.al.|[2607.26893](https://arxiv.org/abs/2607.26893)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-28**|**MoMo: Dial Motion Mode in Robot Manipulation with Spatiotemporal Action Tokenization**|Yuhan Hu et.al.|[2607.26315](https://arxiv.org/abs/2607.26315)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-28**|**S2A2: Audio-Visual Imitation Learning for Manipulation Tasks Using Acoustic Spatial Information**|Kaneyoshi Hiratsuka et.al.|[2607.26047](https://arxiv.org/abs/2607.26047)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-29**|**Tri-Manual Visuomotor Imitation Learning of Robot Policies**|James Zhao et.al.|[2607.25731](https://arxiv.org/abs/2607.25731)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-28**|**Decompose and Reorganize: Planning with Primitives and Visuomotor Policies Learned from Demonstrations**|Yizhou Chen et.al.|[2607.25397](https://arxiv.org/abs/2607.25397)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-26**|**Learning Input-Constrained Funnel Controllers from State Trajectory Data**|Panagiotis S. Trakas et.al.|[2607.23876](https://arxiv.org/abs/2607.23876)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-26**|**PRISM: Polynomial Representations for Interaction-Structured Motor Control**|Seung Hyun Lee et.al.|[2607.23473](https://arxiv.org/abs/2607.23473)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-25**|**The Curse of Precision: A Data Scaling Law for High-Precision Robotic Manipulation**|Cuijie Xu et.al.|[2607.23108](https://arxiv.org/abs/2607.23108)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-22**|**Cortex: Compact Behavior Cloning for Quake with Frozen Visual Features**|Dzmitry Malyshau et.al.|[2607.22739](https://arxiv.org/abs/2607.22739)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-24**|**GuidedAttention: Interpretable and Correctable Visual Attention for OOD-Robust Robot Manipulation via Imitation Learning**|Masaki Murooka et.al.|[2607.21049](https://arxiv.org/abs/2607.21049)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-29**|**EA-Nav: Learning Safe Visual Navigation Policies with Embodiment Awareness**|Jialu Zhang et.al.|[2607.19880](https://arxiv.org/abs/2607.19880)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-21**|**End-to-end Conditional Diffusion for Realistic and Controllable Visual Traffic Scenario Generation**|Jingzheng Li et.al.|[2607.18637](https://arxiv.org/abs/2607.18637)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-23**|**Anticipate Before Acting: Future-State-Conditioned Vision-Language Navigation**|Lingfeng Zhang et.al.|[2607.18042](https://arxiv.org/abs/2607.18042)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-20**|**MEVION: Low-Cost Open-Source Data Collection System for Powerful and High-Speed Dual-Arm Manipulation**|Kento Kawaharazuka et.al.|[2607.17970](https://arxiv.org/abs/2607.17970)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-19**|**Asynchronous Multimodal Diffusion Policy Composition via Latency-Aware Guidance Fusion**|Zihao He et.al.|[2607.17257](https://arxiv.org/abs/2607.17257)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-18**|**Scalable Causal Imitation Learning**|Eylam Tagor et.al.|[2607.17003](https://arxiv.org/abs/2607.17003)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-17**|**When to Plan: Learning to Select Between Reactive Control and Deliberative Planning**|Adam Labiosa et.al.|[2607.16421](https://arxiv.org/abs/2607.16421)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-17**|**Dynamics-Aware Meta-Imitation for Generalization to Unseen Robotic Manipulation**|Zhenduo Shang et.al.|[2607.15880](https://arxiv.org/abs/2607.15880)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-16**|**NavCMPO: Critic-Guided MeanFlow Policy Optimization for Adaptive Navigation**|Junjie An et.al.|[2607.14643](https://arxiv.org/abs/2607.14643)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-15**|**Augmentations for Robust and Efficient Imitation Learning in Streamed Video Games**|Somjit Nath et.al.|[2607.14200](https://arxiv.org/abs/2607.14200)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-15**|**Semantic Audio-driven Understanding for Dynamic Humanoid Whole Body Control**|J. M. A. Marcelo et.al.|[2607.14182](https://arxiv.org/abs/2607.14182)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-24**|**Industrial Dexterity Benchmark: A Hardware-Software Benchmarking Platform for Industrial Dexterous Manipulation**|Honglu He et.al.|[2607.14021](https://arxiv.org/abs/2607.14021)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-15**|**Discriminative Barrier Functions for Safe Adversarial Imitation Learning from Observation**|Anubhav Vishwakarma et.al.|[2607.13938](https://arxiv.org/abs/2607.13938)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-15**|**Joint On-and-Off Policy Learning for Vision-and-Language Navigation**|Qingrong He et.al.|[2607.13461](https://arxiv.org/abs/2607.13461)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-07-15**|**Distributionally Robust and Safe Imitation Learning**|Ahmed Aboudonia et.al.|[2607.13436](https://arxiv.org/abs/2607.13436)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-15**|**Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment**|Dwip Dalal et.al.|[2607.13429](https://arxiv.org/abs/2607.13429)|**[link](https://huggingface.co/models/Dwipz/Anchor-Align)**|
|**2026-07-14**|**DenseReward: Dense Reward Learning via Failure Synthesis for Robotic Manipulation**|Yu Fang et.al.|[2607.13033](https://arxiv.org/abs/2607.13033)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-17**|**NeuralActuator: Neural Actuation Modeling for Robot Dynamics and External Force Perception**|Zhiyang Dou et.al.|[2607.11734](https://arxiv.org/abs/2607.11734)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-13**|**Towards Human-level Dexterous Teleoperation**|Puhao Li et.al.|[2607.11481](https://arxiv.org/abs/2607.11481)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-13**|**Pix2Act: Image-Space Manipulation Policies with Equivariant Augmentation**|Haojie Huang et.al.|[2607.11167](https://arxiv.org/abs/2607.11167)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-13**|**SegDiff: Segmented Trajectory Diffusion for Consistent and Adaptive Robot Manipulation**|Haidong Cao et.al.|[2607.11027](https://arxiv.org/abs/2607.11027)|**[link](https://github.com/zezhishao/DailyArXiv)**|
|**2026-07-12**|**A Single Diffusion-Policy Controller for Multi-Task Block Pushing with Zero-Shot Sim-to-Real Transfer**|Haitong Ma et.al.|[2607.10892](https://arxiv.org/abs/2607.10892)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-12**|**Dual-Process Atomic Skill Learning: Decoupling Semantic Reasoning and Real-Time Control**|Jun Chen et.al.|[2607.10625](https://arxiv.org/abs/2607.10625)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-11**|**Large Language Model Enhanced Differentiable Trajectory Planning for IoT-Enabled Autonomous Driving**|Shihao Zhang et.al.|[2607.10438](https://arxiv.org/abs/2607.10438)|**[link](https://github.com/zezhishao/DailyArXiv)**|
|**2026-07-11**|**VINE: Taming Generative Control Policies for Reinforcement Learning**|Rushuai Yang et.al.|[2607.10369](https://arxiv.org/abs/2607.10369)|**[link](https://github.com/AgibotTech/vine)**|
|**2026-07-11**|**PIER-Flow: Physics-Informed Efficient Rectified Flow for Real-Time Mobile Robot Navigation**|Shibo Li et.al.|[2607.10288](https://arxiv.org/abs/2607.10288)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-11**|**Source-Lifted Flow Matching for Intervenable Multimodal Imitation**|He Zhang et.al.|[2607.10206](https://arxiv.org/abs/2607.10206)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-10**|**Robo-ValueRL: Reliable Value Estimation for Offline-to-Online Reinforcement Learning**|Wenke Xia et.al.|[2607.09866](https://arxiv.org/abs/2607.09866)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-10**|**More Structure, Not More Capacity: Object-Centric Representations for Visuomotor Imitation Learning**|Yi Li et.al.|[2607.09825](https://arxiv.org/abs/2607.09825)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-10**|**PAC-ACT: Post-training Actor-Critic for Action Chunking Transformers**|Yujie Pang et.al.|[2607.09590](https://arxiv.org/abs/2607.09590)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-10**|**Risk-Aware General-Utility Markov Decision Processes**|Pedro P. Santos et.al.|[2607.09298](https://arxiv.org/abs/2607.09298)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-10**|**Implicit-Behavior Coordination from Unlabeled Sub-Task Demonstrations for Rearrangement Tasks**|Ahmed Shokry et.al.|[2607.09234](https://arxiv.org/abs/2607.09234)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-08**|**EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Data**|Baoyu Li et.al.|[2607.08436](https://arxiv.org/abs/2607.08436)|**[link](https://github.com/knightnemo/Awesome-World-Models)**|
|**2026-07-09**|**AnyDexRT: Calibration-Free Dexterous Hand Retargeting with Few-Shot Human Guidance**|Chenxi Wang et.al.|[2607.08341](https://arxiv.org/abs/2607.08341)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-08**|**Feedback Manipulation Regularization: Enabling Offline Agent Alignment for Imitation Learning**|Benjamin Poole et.al.|[2607.07859](https://arxiv.org/abs/2607.07859)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-08**|**Shift & Drift: A Zero-Shot Benchmark for Generalizable and Robust Autonomous Driving Motion Planning**|Alessandro Canevaro et.al.|[2607.07844](https://arxiv.org/abs/2607.07844)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-08**|**Immersive Social Interaction with VR and LLM-Assisted Humanoids**|Niraj Pudasaini et.al.|[2607.07430](https://arxiv.org/abs/2607.07430)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-08**|**PriGo: Test-Time Primitive Guidance to Diffusion and Flow Policies for Adaptive Robotic Manipulation**|Zezeng Li et.al.|[2607.07076](https://arxiv.org/abs/2607.07076)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-08**|**SPECTRA: Context-Conditioned Spectral Movement Primitives for Robot Skill Generalization**|Boxuan Zhang et.al.|[2607.06978](https://arxiv.org/abs/2607.06978)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-07**|**RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation**|Haoyu Zhao et.al.|[2607.06558](https://arxiv.org/abs/2607.06558)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-07**|**SIEVE: Structure-Aware Data Selection for Imitation Learning with VLA Models**|Changti Wu et.al.|[2607.06442](https://arxiv.org/abs/2607.06442)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-07**|**LAMP: Latent Motion Prior-Guided Real-World Learning for Dexterous Hand Manipulation**|Xinye Yang et.al.|[2607.06323](https://arxiv.org/abs/2607.06323)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-07**|**GraspIT: A Dataset Bridging the Sim-to-Real gap and back for Validated Grasping SE(3) Pose Generation**|Paul Koch. Adem Karakurt et.al.|[2607.05869](https://arxiv.org/abs/2607.05869)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-05**|**Learning to Control LLM Agent Harnesses with Offline Reinforcement Learning**|Haiwen Yi et.al.|[2607.05458](https://arxiv.org/abs/2607.05458)|**[link](https://github.com/xianshang33/llm-paper-daily)**|
|**2026-07-06**|**SILO: Simulation-in-the-Loop Sim-to-Real Transfer for Multi-Stage Cable Routing**|Stone Tao et.al.|[2607.04616](https://arxiv.org/abs/2607.04616)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-06**|**Simple-to-Complex Structured Demonstrations for Vision-Language-Action Learning**|Xinchuan Qiu et.al.|[2607.04591](https://arxiv.org/abs/2607.04591)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-06**|**A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training**|Junze Ye et.al.|[2607.04574](https://arxiv.org/abs/2607.04574)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-04**|**WSA $_1$ : a 3D-Centric World-Spatial-Action Model for Generalizable Robot Control**|Jiahao Jiang et.al.|[2607.03941](https://arxiv.org/abs/2607.03941)|**[link](https://huggingface.co/models/zaleni/WSA-Base)**|
|**2026-07-03**|**CLEAR: Closed-Loop Reinforcement Learning at Scale for End-to-End Autonomous Driving**|Yunxiao Shi et.al.|[2607.02841](https://arxiv.org/abs/2607.02841)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-02**|**Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAs**|Junhao Shi et.al.|[2607.02466](https://arxiv.org/abs/2607.02466)|**[link](https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas)**|
|**2026-07-02**|**WorldSample: Closed-loop Real-robot RL with World Modelling**|Yuquan Xue et.al.|[2607.02431](https://arxiv.org/abs/2607.02431)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-03**|**ComplexMimic: Human-Scene Interaction Imitation in Complex 3D Environments**|Lu Pan et.al.|[2607.02034](https://arxiv.org/abs/2607.02034)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-02**|**One Demonstration Is Enough for Real-World Robotic Reinforcement Learning**|Yuwan Liu et.al.|[2607.01651](https://arxiv.org/abs/2607.01651)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-01**|**Language-Critique Imitation Learning from Suboptimal Demonstrations**|Chih-Han Yang et.al.|[2607.01225](https://arxiv.org/abs/2607.01225)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-07-01**|**Active-GRPO: Adaptive Imitation and Self-Improving Reasoning for Molecular Optimization**|Xuefeng Liu et.al.|[2607.00531](https://arxiv.org/abs/2607.00531)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-30**|**Scalable Behaviour Cloning on Browser Using via Skill Distillation**|Kaisen Yang et.al.|[2606.32014](https://arxiv.org/abs/2606.32014)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-30**|**OopsieVerse: A Safety Benchmark with Damage-Aware Simulation for Robot Manipulation**|Arnav Balaji et.al.|[2606.31993](https://arxiv.org/abs/2606.31993)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-30**|**Z-1: Efficient Reinforcement Learning for Vision-Language-Action Models**|Lang Cao et.al.|[2606.31846](https://arxiv.org/abs/2606.31846)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-30**|**RoboTacDex: A Dexterous Visual-Tactile-Action Dataset for Humanoid Manipulation**|Xinyi Wang et.al.|[2606.31836](https://arxiv.org/abs/2606.31836)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-30**|**Reinforcement Learning-Based Control for an Inline Skating Humanoid Robot**|Ethan Marot et.al.|[2606.31807](https://arxiv.org/abs/2606.31807)|**[link](https://github.com/Foruck/Awesome-Human-Motion)**|
|**2026-06-30**|**What Probing Reveals about Autonomous Driving: Linking Internal Prediction Errors to Ego Planning**|Hyeonchang Jeon et.al.|[2606.31106](https://arxiv.org/abs/2606.31106)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-29**|**Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback**|Ved Sriraman et.al.|[2606.30923](https://arxiv.org/abs/2606.30923)|**[link](https://github.com/nick7nlp/Awesome-LLM-On-Policy-Distillation)**|
|**2026-06-29**|**From Grasps to Dexterity: Large-Scale Grasp Pretraining for Dexterous Manipulation**|Ying Yuan et.al.|[2606.30749](https://arxiv.org/abs/2606.30749)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-29**|**When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon**|Huaqing Zhang et.al.|[2606.30445](https://arxiv.org/abs/2606.30445)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-29**|**Toward an Energy-Optimized Operation of Data Centers Located in Wind Farms Using Reinforcement Learning**|Jan Stenner et.al.|[2606.30316](https://arxiv.org/abs/2606.30316)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-29**|**Trust Your Instincts: Confidence-Driven Test-Time RL for Vision-Language-Action Models**|Siyao Chen et.al.|[2606.29892](https://arxiv.org/abs/2606.29892)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-28**|**CORE: Common Outcome Regularities from Action-Free Visual Demonstrations for Robot Manipulation**|Juyi Sheng et.al.|[2606.29517](https://arxiv.org/abs/2606.29517)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-28**|**Behavior Uncloning: Distilling Mode Redirection into Policy Weights without Inference-Time Steering**|Hao Wang et.al.|[2606.29201](https://arxiv.org/abs/2606.29201)|**[link](https://github.com/Trustworthy-AI-Group/Adversarial_Examples_Papers)**|
|**2026-06-27**|**ReGuide: From Test-Time Guidance to Self-Improving Diffusion Policies**|Tzu-Hsiang Lin et.al.|[2606.28939](https://arxiv.org/abs/2606.28939)|**[link](https://huggingface.co/models/thl1246/reguide-checkpoints)**|
|**2026-06-26**|**WARP-RM: A Warp-Augmented Relative Progress Reward Model for Data Curation**|Justin Yu et.al.|[2606.28320](https://arxiv.org/abs/2606.28320)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-25**|**Scalable Behavior Cloning with Open Data, Training, and Evaluation**|Arthur Allshire et.al.|[2606.27375](https://arxiv.org/abs/2606.27375)|**[link](https://github.com/amazon-far/abc)**|
|**2026-06-25**|**World Action Models Enable Continual Imitation Learning with Recurrent Generative Replays**|Manish Kumar Govind et.al.|[2606.27374](https://arxiv.org/abs/2606.27374)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-25**|**Ordinal Neural Collapse as a Representation Prior for Visual Navigation**|E-In Son et.al.|[2606.26839](https://arxiv.org/abs/2606.26839)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-24**|**Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly?**|Tyler Ga Wei Lum et.al.|[2606.26428](https://arxiv.org/abs/2606.26428)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-24**|**MPC-Injection: Biasing Off-Policy Locomotion RL Toward Controller-Induced Behavior Basins**|Roy Xing et.al.|[2606.26392](https://arxiv.org/abs/2606.26392)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-24**|**Scaling Nonlinear Optimization: Many Problems One GPU**|John Viljoen et.al.|[2606.26341](https://arxiv.org/abs/2606.26341)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-25**|**G2DP: Diffusion Planning with Spatio-Temporal Grid Guidance**|Hang Yu et.al.|[2606.26017](https://arxiv.org/abs/2606.26017)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-24**|**Stage-Aware and Roughness-Constrained Diffusion Policy for Multi-Stage Robotic Polishing**|Shuai Ke et.al.|[2606.25754](https://arxiv.org/abs/2606.25754)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-24**|**Decoupling Semantics and Geometric Grounding: Spatial Visual Prompts for Language-Conditioned Imitation Learning**|Yanzhe Tang et.al.|[2606.25360](https://arxiv.org/abs/2606.25360)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-23**|**Spatio-Temporal Retrieval-based Priors for Adaptive Computational Teaching in Driving**|Deepak Edakkattil Gopinath et.al.|[2606.25224](https://arxiv.org/abs/2606.25224)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-23**|**Memory Retrieval in Visuomotor Policies for Long-Horizon Robot Control**|Rutav Shah et.al.|[2606.25136](https://arxiv.org/abs/2606.25136)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-23**|**Beyond Monotonic Progress: Retry-Supervised Value Learning for Robot Imitation**|Xinyao Qin et.al.|[2606.24633](https://arxiv.org/abs/2606.24633)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-23**|**RE4: Transformation-aware Imitation of Object Interactions Using Manipulation Modes**|Arsh Chawla et.al.|[2606.24403](https://arxiv.org/abs/2606.24403)|**[link](https://github.com/Jianqiuer/Awesome6DPoseEstimation)**|
|**2026-06-23**|**An Introduction to Causal Reinforcement Learning**|Elias Bareinboim et.al.|[2606.24160](https://arxiv.org/abs/2606.24160)|**[link](https://github.com/tmgthb/Autonomous-Agents)**|
|**2026-06-23**|**MinInter: Minimizing Trajectory Interpolation During Data Augmentation for Imitation Learning**|Qingyang Wang et.al.|[2606.24078](https://arxiv.org/abs/2606.24078)|**[link](https://github.com/zezhishao/DailyArXiv)**|
|**2026-06-23**|**SPACE: Enabling Learning from Cross-Robot Data Toward Generalist Policies**|Haeone Lee et.al.|[2606.24049](https://arxiv.org/abs/2606.24049)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-23**|**TurboMPC: Fast, Scalable, and Differentiable Model Predictive Control on the GPU**|Gabriel Bravo-Palacios et.al.|[2606.24039](https://arxiv.org/abs/2606.24039)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-22**|**Learning to See While Learning to Act: Diffusion Models for Active Perception in Robot Imitation**|Kuancheng Wang et.al.|[2606.23625](https://arxiv.org/abs/2606.23625)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-22**|**RECALL: Recovery Experience Collection for Active Lifelong Learning in Vision-Language-Action Models**|Ulas Berk Karli et.al.|[2606.23617](https://arxiv.org/abs/2606.23617)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-25**|**MORL-A2C: Multi-Objective Reinforcement Learning Reranker for Optimizing Healthiness in MOPI-HFRS**|Aarya Vasantlal et.al.|[2606.23603](https://arxiv.org/abs/2606.23603)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-22**|**Flowing With Purpose: Latent Action Guided Flow Matching Policies For Robotic Manipulation**|Bruno Machado et.al.|[2606.23420](https://arxiv.org/abs/2606.23420)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-22**|**TSD: A Physics-Inspired Trajectory Saliency Detector for Efficient Imitation Learning**|Yiming Zhao et.al.|[2606.23371](https://arxiv.org/abs/2606.23371)|**[link](https://github.com/zezhishao/DailyArXiv)**|
|**2026-06-22**|**Improving Robotic Imitation Learning via Trajectory Standardization**|Licheng Yang et.al.|[2606.22907](https://arxiv.org/abs/2606.22907)|**[link](https://github.com/zezhishao/DailyArXiv)**|
|**2026-06-22**|**HiL-ResRL: A Model-Agnostic Finetuning Adapter via Human-in-the-loop Residual Reinforcement Learning**|Jingyi Liu et.al.|[2606.22860](https://arxiv.org/abs/2606.22860)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-21**|**ARP: Enhancing Quantized Skill Abstractions via Visual Alignment and Iterative Refinement for Robotic Manipulation**|Yuntian Wang et.al.|[2606.22480](https://arxiv.org/abs/2606.22480)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-21**|**Do Rigid-Body Simulators Dream of Soft Robots? Learning Contact-Rich Manipulation for Tendon-Driven Continuum Robots**|Chengnan Shentu et.al.|[2606.22397](https://arxiv.org/abs/2606.22397)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-20**|**Provably Efficient Policy-Reward Co-Pretraining for Adversarial Imitation Learning**|Tian Xu et.al.|[2606.22056](https://arxiv.org/abs/2606.22056)|**[link](https://github.com/Trustworthy-AI-Group/Adversarial_Examples_Papers)**|
|**2026-06-20**|**CoRDE: Concept-Prior Routed Diffusion Experts for Structural Generalization in Robot Manipulation**|Haidong Huang et.al.|[2606.21935](https://arxiv.org/abs/2606.21935)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-19**|**Imitation from Heterogeneous Demonstrations using Grounded Latent-Action World Models**|Tianyou Wang et.al.|[2606.21672](https://arxiv.org/abs/2606.21672)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-19**|**Decoupling the Declarative from the Procedural in Vision-Language-Action Models**|Nikolaos Tsagkas et.al.|[2606.21496](https://arxiv.org/abs/2606.21496)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-23**|**Topological Neural Dynamics: A Neuron-wise Framework for Sequence Modeling**|Borui Cai et.al.|[2606.21295](https://arxiv.org/abs/2606.21295)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-19**|**Imitation Learning for Elder-Facing Speech Synthesis**|Dongrui Han et.al.|[2606.21053](https://arxiv.org/abs/2606.21053)|**[link](https://github.com/liutaocode/TTS-arxiv-daily)**|
|**2026-06-18**|**Geometric Entropy: When Trajectory Diversity Helps and Hurts in Imitation Learning**|Qian Luo et.al.|[2606.20871](https://arxiv.org/abs/2606.20871)|**[link](https://github.com/RLCL-EIT/robotics_arxiv_daily)**|
|**2026-06-18**|**FOCA: Future-Oriented Conditioning for Data-Efficient Vision-Language-Action Adaptation**|Duc Minh Nguyen et.al.|[2606.20867](https://arxiv.org/abs/2606.20867)|**[link](https://github.com/ducido/foca_site)**|
|**2026-06-18**|**CoLI: A Reproducible Platform for Continuum Robot Learning via Monolithic 3D Printing and Isomorphic Teleoperation**|Ziyuan Tang et.al.|[2606.20389](https://arxiv.org/abs/2606.20389)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-18**|**VFILC: Accurate Frequency Extrapolations in Imitation Learning via Sampling Frequency ILC**|Nozomu Masuya et.al.|[2606.20056](https://arxiv.org/abs/2606.20056)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-19**|**Temporal Self-Imitation Learning**|Yinsen Jia et.al.|[2606.19752](https://arxiv.org/abs/2606.19752)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-17**|**Object-Centric Residual RL for Zero-Shot Sim-to-Real VLA Enhancement**|Kinam Kim et.al.|[2606.18953](https://arxiv.org/abs/2606.18953)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-17**|**Skill-Guided Continuation Distillation for GUI Agents**|Zhimin Fan et.al.|[2606.18890](https://arxiv.org/abs/2606.18890)|**[link](https://github.com/tmgthb/Autonomous-Agents)**|
|**2026-06-16**|**Ghost Attractor Networks: Basin-Structured Dynamical Decoders for Closed-Loop Sequential Generation**|Tianyu Wang et.al.|[2606.18315](https://arxiv.org/abs/2606.18315)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-16**|**Learning Red Agent Policy from Observations for Neurosymbolic Autonomous Cyber Agents**|Ankita Samaddar et.al.|[2606.18223](https://arxiv.org/abs/2606.18223)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-16**|**WireCraft: A Simulation Benchmark for Industrial DLO Manipulation**|Chongyu Zhu et.al.|[2606.18097](https://arxiv.org/abs/2606.18097)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-16**|**When Robots Sleep: Offline Skill Consolidation for Shared-Policy Robot Learning**|Nethmi Jayasinghe et.al.|[2606.17493](https://arxiv.org/abs/2606.17493)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-15**|**Hierarchical Advantage Weighting for Online RL Fine-Tuning of VLAs from Sparse Episode Outcomes**|Tongyan Fang et.al.|[2606.17043](https://arxiv.org/abs/2606.17043)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-15**|**R2RDreamer: 3D-aware Data Augmentation for Spatially-generalized 2D Manipulation Policies**|Xiuwei Xu et.al.|[2606.17040](https://arxiv.org/abs/2606.17040)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-15**|**APEX: Adaptive Policy Execution for Precise Manipulation**|Mengfei Zhao et.al.|[2606.16504](https://arxiv.org/abs/2606.16504)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-15**|**Training and Evaluating Diffusion Policies with Long Context Lengths**|Abhinav Agarwal et.al.|[2606.16447](https://arxiv.org/abs/2606.16447)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-15**|**FlowMPC: Improving Flow Matching policies with World Models**|Chandon Hamel et.al.|[2606.16286](https://arxiv.org/abs/2606.16286)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-15**|**ATHENA: Accelerated Multi-Task Heterogeneous Influence Functions for Robot Data Curation**|Tao Xu et.al.|[2606.16208](https://arxiv.org/abs/2606.16208)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-15**|**Scaling Short-Term Memory of Visuomotor Policies for Long-Horizon Tasks**|Rutav Shah et.al.|[2606.16178](https://arxiv.org/abs/2606.16178)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-14**|**Perfect Demo Makes Poor Teacher: Learning Robust Alignment from Critical Motion Segments**|Mingyu Liu et.al.|[2606.15587](https://arxiv.org/abs/2606.15587)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-13**|**Reinforcement Learning-Guided Retrieval with Soft Fusion for Robust Multimodal Imitation Learning under Missing Modalities**|Hassan Ismkhan et.al.|[2606.15514](https://arxiv.org/abs/2606.15514)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-13**|**Rethinking Implicit Spatial Representation in Visuomotor Policy Learning**|Xiangyu Chen et.al.|[2606.15232](https://arxiv.org/abs/2606.15232)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-12**|**Spatially Conditioned Diffusion Policy: Learning Precise and Robust Manipulation with a Single RGB Camera**|Seoyoon Kim et.al.|[2606.14535](https://arxiv.org/abs/2606.14535)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-12**|**Kine2Go: Kinematic dataset for the Unitree Go2 robot with diverse gaits and motions**|Władysław Pałucki et.al.|[2606.14433](https://arxiv.org/abs/2606.14433)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-12**|**FloVerse: Floor Plan-Guided Multi-Modal Navigation**|Weiqi Huang et.al.|[2606.14267](https://arxiv.org/abs/2606.14267)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-12**|**Improving Robotic Generalist Policies via Flow Reversal Steering**|Andy Tang et.al.|[2606.13675](https://arxiv.org/abs/2606.13675)|**[link](https://github.com/wadeKeith/Awesome-Embodied-AI)**|
|**2026-06-11**|**Rarity-Gated Context Conditioning for Offline Imitation Learning-Based Maritime Anomaly Detection**|Yongmin Kim et.al.|[2606.13311](https://arxiv.org/abs/2606.13311)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-11**|**EmbodiSteer: Steering Embodiment-Agnostic Visuomotor Policies with Joint-Space Guidance for Zero-Shot Cross-Embodiment Deployment**|Shihefeng Wang et.al.|[2606.12965](https://arxiv.org/abs/2606.12965)|**[link](https://github.com/wadeKeith/Awesome-Embodied-AI)**|
|**2026-06-10**|**From Imitation to Alignment: Human-Preference Flow Policies for Long-Horizon Sidewalk Navigation**|Honglin He et.al.|[2606.12603](https://arxiv.org/abs/2606.12603)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-10**|**Speculative Rollback Correction for Quality-Diverse Web Agent Imitation**|Longkun Hao et.al.|[2606.12485](https://arxiv.org/abs/2606.12485)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-10**|**Learning to Assist: Collaborative VLAs for Implicit Human-Robot Collaboration**|Leo Xu et.al.|[2606.12475](https://arxiv.org/abs/2606.12475)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-10**|**FACTR 2: Learning External Force Sensing for Commodity Robot Arms Improves Policy Learning**|Steven Oh et.al.|[2606.12406](https://arxiv.org/abs/2606.12406)|**[link](https://github.com/wadeKeith/Awesome-Embodied-AI)**|
|**2026-06-10**|**Ambient Diffusion Policy: Imitation Learning from Suboptimal Data in Robotics**|Adam Wei et.al.|[2606.12365](https://arxiv.org/abs/2606.12365)|**[link](https://github.com/wadeKeith/Awesome-Embodied-AI)**|
|**2026-06-10**|**Fourier Features Let Agents Learn High Precision Policies with Imitation Learning**|Balázs Gyenes et.al.|[2606.12334](https://arxiv.org/abs/2606.12334)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-10**|**DuoBench: A Reproducible Benchmark for Bimanual Manipulation in Simulation and the Real World**|Tobias Jülg et.al.|[2606.11901](https://arxiv.org/abs/2606.11901)|**[link](https://huggingface.co/datasets/RobotControlStack/duobench_raw)**|
|**2026-06-10**|**Critic Architecture Matters: Dual vs. Unified Critics for Humanoid Loco-Manipulation**|Mehmet Turan Yardımcı et.al.|[2606.11891](https://arxiv.org/abs/2606.11891)|**[link](https://github.com/Foruck/Awesome-Human-Motion)**|
|**2026-06-10**|**Distortion-Resilient Robotic Imitation Learning for Autonomous Cable Routing**|Hao Wang et.al.|[2606.11577](https://arxiv.org/abs/2606.11577)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-09**|**PLUME: Probabilistic Latent Unified World Modeling and Parameter Estimation for Multi-Finger Manipulation**|Abhinav Kumar et.al.|[2606.11396](https://arxiv.org/abs/2606.11396)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-09**|**TacForeSight: Force-Guided Tactile World Model for Contact-Rich Manipulation**|Yujie Zang et.al.|[2606.11184](https://arxiv.org/abs/2606.11184)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-09**|**Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning**|Zhiyuan Zhou et.al.|[2606.11087](https://arxiv.org/abs/2606.11087)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-09**|**MODIP: Efficient Model-Based Optimization for Diffusion Policies**|Zakariae El Asri et.al.|[2606.10825](https://arxiv.org/abs/2606.10825)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-09**|**IMPACT: Learning Internal-Model Predictive Control for Forceful Robotic Manipulation**|Jiawei Gao et.al.|[2606.10818](https://arxiv.org/abs/2606.10818)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-09**|**LAFP: Preserving Latent Action Structure in Latent Policy Learning via Flow Matching**|Jiexi Lyu et.al.|[2606.10517](https://arxiv.org/abs/2606.10517)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-09**|**Act on What You See: Unlocking Safe Social Navigation in Vision-Language-Action Models**|Qingzi Wang et.al.|[2606.10495](https://arxiv.org/abs/2606.10495)|**[link](https://github.com/wadeKeith/Awesome-Embodied-AI)**|
|**2026-06-09**|**GuideWalk: Learning Unified Autonomous Navigation and Locomotion for Humanoid Robots across Versatile Terrains**|Haoxuan Han et.al.|[2606.10449](https://arxiv.org/abs/2606.10449)|**[link](https://github.com/wadeKeith/Awesome-Embodied-AI)**|
|**2026-06-09**|**SARM2: Multi-Task Stage Aware Reward Modeling for Self Improving Robotic Manipulation**|Qianzhong Chen et.al.|[2606.10305](https://arxiv.org/abs/2606.10305)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-08**|**What Demonstration Curation Metrics Do to Your Policy**|Aarav Bedi et.al.|[2606.10229](https://arxiv.org/abs/2606.10229)|**[link](https://huggingface.co/spaces/HaptalAI/haptal-curate)**|
|**2026-06-08**|**FlexPath: Learned Semantic Path Priors for Image-Based Planning**|Taehyoung Kim et.al.|[2606.10167](https://arxiv.org/abs/2606.10167)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-08**|**Difference-Aware Retrieval Policies for Imitation Learning**|Quinn Pfeifer et.al.|[2606.09758](https://arxiv.org/abs/2606.09758)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-08**|**DexPIE: Stable Dexterous Policy Improvement from Real-World Experience**|Ruizhe Liao et.al.|[2606.09615](https://arxiv.org/abs/2606.09615)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-08**|**ReGIL: Retrieval-Guided Imitation Learning from a Single Demonstration**|Yuying Zhang et.al.|[2606.09381](https://arxiv.org/abs/2606.09381)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-07**|**Benchmarking Vision-Language-Action Models on SO-101: Failure and Recovery Analysis**|Yi Yu et.al.|[2606.08881](https://arxiv.org/abs/2606.08881)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-06**|**Learning from Human Driving: A Human-in-the-Loop Online Behavior Cloning Framework for Autonomous Driving**|Yuhong Shi et.al.|[2606.08170](https://arxiv.org/abs/2606.08170)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-06**|**CLASP: Language-Driven Robot Skill Selection and Composition using Task-Parameterized Learning**|Markus Knauer et.al.|[2606.08169](https://arxiv.org/abs/2606.08169)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-06**|**SynthICL: Scalable In-context Imitation Learning with Synthetic Data**|Cheng Qian et.al.|[2606.08154](https://arxiv.org/abs/2606.08154)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-05**|**Simulation-Driven Imitation Learning for Biosignals-Free Shared-Autonomy Prosthetic Grasping**|Kaijie Shi et.al.|[2606.07389](https://arxiv.org/abs/2606.07389)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-05**|**Spline Policy: A Structured Representation for Robot Policies**|Mengze Tian et.al.|[2606.07386](https://arxiv.org/abs/2606.07386)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-04**|**AxisGuide: Grounding Robot Action Coordinate System in RGB Observations for Robust Visuomotor Manipulation**|Jiyun Jang et.al.|[2606.06761](https://arxiv.org/abs/2606.06761)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-04**|**VOLT: Vision and Language Trajectory Segmentation for Faster-than-Demonstration Policies**|Robert Ramirez Sanchez et.al.|[2606.06323](https://arxiv.org/abs/2606.06323)|**[link](https://github.com/zezhishao/DailyArXiv)**|
|**2026-06-04**|**Multi-Resolution Tactile Imitation Learning for Contact-Rich Robotic Manipulation**|Rickmer Krohn et.al.|[2606.06281](https://arxiv.org/abs/2606.06281)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-04**|**Towards a Data Flywheel for Embodied Intelligence in Logistics**|Anlan Yu et.al.|[2606.05960](https://arxiv.org/abs/2606.05960)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-04**|**Auditing Demonstration Curation Metrics: Action-Only Scorers Fail on the Structural Defects That Degrade Imitation Policies**|Aarav Bedi et.al.|[2606.05588](https://arxiv.org/abs/2606.05588)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-03**|**MoDex: A Diffusion Policy for Sequential Multi-Object Dexterous Grasping**|Haofei Lu et.al.|[2606.05407](https://arxiv.org/abs/2606.05407)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-05**|**Reinforcement Learning from Rich Feedback with Distributional DAgger**|Rishabh Agrawal et.al.|[2606.05152](https://arxiv.org/abs/2606.05152)|**[link](https://github.com/chrisliu298/awesome-on-policy-distillation)**|
|**2026-06-03**|**Potential-Guided Flow Matching for Vision-Language-Action Policy Improvement**|Yunpeng Mei et.al.|[2606.04968](https://arxiv.org/abs/2606.04968)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-03**|**HapTile: A Haptic-Informed Vision-Tactile-Language-Action Dataset for Contact-Rich Imitation Learning**|Amirhosein Alian et.al.|[2606.04825](https://arxiv.org/abs/2606.04825)|**[link](https://github.com/linchangyi1/Awesome-Touch)**|
|**2026-06-03**|**Stateful Visual Encoders for Vision-Language Models**|Zirui Wang et.al.|[2606.04433](https://arxiv.org/abs/2606.04433)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-02**|**Instant-Fold: In-Context Imitation Learning for Deformable Object Manipulation**|Yilong Wang et.al.|[2606.04269](https://arxiv.org/abs/2606.04269)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-02**|**CoPark: Learning Reactive Parking via Self-Play**|Jiarong Wei et.al.|[2606.04149](https://arxiv.org/abs/2606.04149)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-02**|**CLAW: Learning Continuous Latent Action World Models via Adversarial Latent Regularization**|Tewodros Ayalew et.al.|[2606.04130](https://arxiv.org/abs/2606.04130)|**[link](https://github.com/leofan90/Awesome-World-Models)**|
|**2026-06-02**|**Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories**|Ali Behrouz et.al.|[2606.03979](https://arxiv.org/abs/2606.03979)|**[link](https://github.com/TeleAI-UAGI/Awesome-Agent-Memory)**|
|**2026-06-02**|**Let the Dynamics Flow: Stable Flow Matching Dynamical Systems**|Rodrigo Pérez-Dattari et.al.|[2606.03834](https://arxiv.org/abs/2606.03834)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-02**|**SPADE: Sketch-guided Path Planning Augmented with Diffusion Experts**|Charbel Abi Hana et.al.|[2606.03512](https://arxiv.org/abs/2606.03512)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-02**|**Human2Humanoid: Physics-Aware Cross-Morphology Motion Retargeting for Humanoid Robots**|Tianchen Huang et.al.|[2606.03476](https://arxiv.org/abs/2606.03476)|**[link](https://github.com/Foruck/Awesome-Human-Motion)**|
|**2026-06-02**|**GPU-Parallel Multi-Task Reinforcement Learning with Demonstration Guided Policy Optimization**|Rui Zhang et.al.|[2606.03335](https://arxiv.org/abs/2606.03335)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-02**|**EaDex: A Cross-Embodiment Dexterous Manipulation Framework from Low-Cost Demonstrations**|Qian Zhao et.al.|[2606.03268](https://arxiv.org/abs/2606.03268)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-02**|**How Visible Are Silent Manipulation Failures? An Observability Study of False-Success Detection in Simulated Robot Episodes**|Aarav Bedi et.al.|[2606.03134](https://arxiv.org/abs/2606.03134)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-01**|**Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards**|Christian Scherer et.al.|[2606.02194](https://arxiv.org/abs/2606.02194)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-06-01**|**Co-training with Ego-centric Video and Demonstration for Robot Navigation Task**|Shoya Kuno et.al.|[2606.01951](https://arxiv.org/abs/2606.01951)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-06-01**|**Set-Supervised Diffusion Policy: Learning Action-Chunking Diffusion through Corrections**|Zhaoting Li et.al.|[2606.01865](https://arxiv.org/abs/2606.01865)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|
|**2026-05-31**|**Training-Free Imitation Learning with Closed-Form Diffusion Policies**|Raghav Mishra et.al.|[2606.01238](https://arxiv.org/abs/2606.01238)|**[link](https://github.com/BaiShuanghao/my_arXiv_daily)**|
|**2026-05-31**|**Lagrangian Perturbation Diffusion Steering: Latent Reinforcement Learning for Generative Policies**|Hikmet Simsir et.al.|[2606.01151](https://arxiv.org/abs/2606.01151)|**[link](https://github.com/luohongk/Embodied-AI-Daily)**|
|**2026-05-31**|**Implicit Drifting Policy: One-Step Action Generation via Conditional Expert Geometry**|Zemin Yang et.al.|[2606.01098](https://arxiv.org/abs/2606.01098)|**[link](https://github.com/RainbowNebula/robot-paper-daily)**|

(<a href=#updated-on-20260823>back to top</a>)

my_arXiv_daily

파일 탐색기

# 설치 가이드

2. Python

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

my_arXiv_daily

파일 탐색기

# 설치 가이드

2. Python

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README