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。

2025-09-19 至 2025-09-19 共收录 9 篇信号源：cs.RO, cs.CV, cs.AI, cs.LG

1. VLA模型 8 篇

2507.16815 2025-09-19 cs.CV cs.AI cs.LG cs.RO 88%

ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning

Chi-Pin Huang, Yueh-Hua Wu, Min-Hung Chen, Yu-Chiang Frank Wang, Fu-En Yang

机构 * NVIDIA ； National Taiwan University（国立台湾大学）

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

Comments NeurIPS 2025. Project page: https://jasper0314-huang.github.io/thinkact-vla/

2509.14889 2025-09-19 cs.RO 86%

CollabVLA: Self-Reflective Vision-Language-Action Model Dreaming Together with Human

Nan Sun, Yongchang Li, Chenxu Wang, Huiying Li, Huaping Liu

机构 * Department of Computer Science and Technology, Tsinghua University（计算机科学与技术系，清华大学）

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

Comments 8 pages, 5 figures, 3 tables

2505.22159 2025-09-19 cs.RO cs.CV 84%

ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulation

Jiawen Yu, Hairuo Liu, Qiaojun Yu, Jieji Ren, Ce Hao, Haitong Ding, Guangyu Huang, Guofan Huang, Yan Song, Panpan Cai, Cewu Lu, Wenqiang Zhang

机构 * Fudan University（复旦大学）； Shanghai Jiao Tong University（上海交通大学）； Shanghai Innovation Institute（上海创新研究院）； Shanghai AI Lab（上海人工智能实验室）； National University of Singapore（新加坡国立大学）； Shanghai University（上海大学）； Xi’an Jiaotong University（西安交通大学）； Noematrix Intelligence（Noematrix智能科技）

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

Comments NeurIPS 2025

2509.14687 2025-09-19 cs.RO 83%

RealMirror: A Comprehensive, Open-Source Vision-Language-Action Platform for Embodied AI

Cong Tai, Zhaoyu Zheng, Haixu Long, Hansheng Wu, Haodong Xiang, Zhengbin Long, Jun Xiong, Rong Shi, Shizhuang Zhang, Gang Qiu, He Wang, Ruifeng Li, Jun Huang, Bin Chang, Shuai Feng, Tao Shen

机构 * ZTE Corporation（中通服科技有限公司）； The Chinese University of Hong Kong（香港中文大学）

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

2509.14630 2025-09-19 cs.RO 79%

Toward Embodiment Equivariant Vision-Language-Action Policy

Anzhe Chen, Yifei Yang, Zhenjie Zhu, Kechun Xu, Zhongxiang Zhou, Rong Xiong, Yue Wang

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

2509.15212 2025-09-19 cs.CV cs.RO 73%

RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation

Yuming Jiang, Siteng Huang, Shengke Xue, Yaxi Zhao, Jun Cen, Sicong Leng, Kehan Li, Jiayan Guo, Kexiang Wang, Mingxiu Chen, Fan Wang, Deli Zhao, Xin Li

机构 * DAMO Academy, Alibaba Group（达摩院，阿里巴巴集团）； Hupan Lab（虎扑实验室）

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

Comments GitHub Project: https://github.com/alibaba-damo-academy/RynnVLA-001

2508.11458 2025-09-19 astro-ph.HE 50%

Improving Air Shower Simulations by Tuning Pythia 8/Angantyr with Accelerator Data

Michael Windau, Chloé Gaudu, Karl-Heinz Kampert, Kevin Kröninger

专题命中 VLA模型：action model(abstract)

Comments 10 pages, 7 figures, 39th International Cosmic Ray Conference (ICRC 2025) proceeding

2505.13950 2025-09-19 cs.IR 50%

An Empirical Study of Position Bias in Modern Information Retrieval

Ziyang Zeng, Dun Zhang, Jiacheng Li, Panxiang Zou, Yudong Zhou, Yuqing Yang

专题命中 VLA模型：action model(abstract)

Comments EMNLP 2025 Findings (camera-ready)

2. 机器人基础模型 1 篇

2509.15155 2025-09-19 cs.LG cs.RO 81%

Self-Improving Embodied Foundation Models

Seyed Kamyar Seyed Ghasemipour, Ayzaan Wahid, Jonathan Tompson, Pannag Sanketi, Igor Mordatch

机构 * Generalist ； Google DeepMind（谷歌DeepMind）

专题命中机器人基础模型：embodied foundation model(title,abstract)；分类 cs.RO、cs.LG

Comments Appearing in the Conference on Neural Information Processing Systems (NeurIPS 2025)