视觉与机器人

VLA / 视觉-语言-动作模型

视觉-语言-动作模型、机器人基础模型和语言条件机器人控制。

2025-10-01 至 2025-10-01 共收录 6 篇信号源：cs.RO, cs.CV, cs.AI, cs.LG

1. VLA模型 4 篇

2509.25681 2025-10-01 cs.RO cs.CV 88%

dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thought

Junjie Wen, Minjie Zhu, Jiaming Liu, Zhiyuan Liu, Yicun Yang, Linfeng Zhang, Shanghang Zhang, Yichen Zhu, Yi Xu

机构 * Midea Group（美的集团）； Peking University（北京大学）； Shanghai Jiaotong University（上海交通大学）

专题命中 VLA模型：vision-language-action(title,abstract)；action model(title)；VLA(abstract)；分类 cs.RO、cs.CV

Comments technique report

2509.25718 2025-10-01 cs.RO 83%

VLA Model Post-Training via Action-Chunked PPO and Self Behavior Cloning

Si-Cheng Wang, Tian-Yu Xiang, Xiao-Hu Zhou, Mei-Jiang Gui, Xiao-Liang Xie, Shi-Qi Liu, Shuang-Yi Wang, Ao-Qun Jin, Zeng-Guang Hou

机构 * State Key Laboratory of Multimodal Artificial Intelligence Systems（多模态人工智能系统国家重点实验室）； Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）

专题命中 VLA模型：VLA(title,abstract)；vision-language-action(abstract)；分类 cs.RO

2509.25966 2025-10-01 cs.RO 70%

MUVLA: Learning to Explore Object Navigation via Map Understanding

Peilong Han, Fan Jia, Min Zhang, Yutao Qiu, Hongyao Tang, Yan Zheng, Tiancai Wang, Jianye Hao

机构 * Dexmal

专题命中 VLA模型：vision-language-action(abstract)；action model(abstract)；分类 cs.RO

2509.26002 2025-10-01 cs.AI cs.HC cs.LG cs.MA cs.RO 67%

Towards Human Engagement with Realistic AI Combat Pilots

Ardian Selmonaj, Giacomo Del Rio, Adrian Schneider, Alessandro Antonucci

机构 * Istituto Dalle Molle di Studi sull’Intelligenza Artificiale（日内瓦智能研究 institute）； Armasuisse Science+Technology（阿姆斯瓦尔科学与技术）

专题命中 VLA模型：action model(abstract)；分类 cs.RO、cs.AI、cs.LG

Comments 13th International Conference on Human-Agent Interaction (HAI) 2025

2. 动作表示与策略 2 篇

2506.00613 2025-10-01 cs.RO cs.AI 62%

WorldGym: World Model as An Environment for Policy Evaluation

Julian Quevedo, Ansh Kumar Sharma, Yixiang Sun, Varad Suryavanshi, Percy Liang, Sherry Yang

机构 * Stanford University（斯坦福大学）； NYU（纽约大学）； Google DeepMind（谷歌DeepMind）

专题命中动作表示与策略：VLA(abstract)；分类 cs.RO、cs.AI

Comments https://world-model-eval.github.io

2508.06266 2025-10-01 cs.RO 57%

ADPro: a Test-time Adaptive Diffusion Policy via Manifold-constrained Denoising and Task-aware Initialization for Robotic Manipulation

Zezeng Li, Rui Yang, Ruochen Chen, ZhongXuan Luo, Liming Chen

机构 * École Centrale de Lyon（里昂中央理工大学）； Dalian University of Technology（大连理工大学）

专题命中动作表示与策略：action model(abstract)；分类 cs.RO