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。

2025-10-30 至 2025-10-30 共收录 6 篇信号源：cs.RO, cs.CV, cs.AI, cs.LG

1. VLA模型 4 篇

2510.25713 2025-10-30 cs.RO 88%

Robotic Assistant: Completing Collaborative Tasks with Dexterous Vision-Language-Action Models

Boshi An, Chenyu Yang, Robert Katzschmann

机构 * Soft Robotics Lab, ETHz, Switzerland（苏黎世联邦理工学院软机器人实验室）

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

2510.25616 2025-10-30 cs.LG cs.AI cs.RO 87%

Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization

Nikita Kachaev, Mikhail Kolosov, Daniil Zelezetsky, Alexey K. Kovalev, Aleksandr I. Panov

机构 * Cognitive AI Lab（认知人工智能实验室）； Cognitive AI Lab, IAI MIPT（认知人工智能实验室，IAI MIPT）

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

Comments 13 pages, 6 figures

2510.25198 2025-10-30 astro-ph.GA 78%

Tracing Gas Kinematics and Interactions between H II Regions and Molecular Clouds using VLA Observations of Recombination Lines and Hydroxyl

E. Cappellazzo, J. R. Dawson, Mark Wardle, Trey V. Wenger, Anita Hafner, Dana S. Balser, L. D. Anderson, Elizabeth K. Mahony, M. R. Rugel, John M. Dickey

专题命中 VLA模型：VLA(title,abstract)

Comments 26 pages, 16 figures. Accepted for publication in ApJ

2305.07073 2025-10-30 stat.ME stat.AP stat.CO 71%

Hierarchical additive interaction modelling with Gaussian process prior and its efficient implementation for multidimensional grid data

Sahoko Ishida, Francesca Panero, Wicher Bergsma

专题命中 VLA模型：action model(title)

2. 数据集与评测 1 篇

2506.06677 2025-10-30 cs.RO cs.CV 73%

RoboCerebra: A Large-scale Benchmark for Long-horizon Robotic Manipulation Evaluation

Songhao Han, Boxiang Qiu, Yue Liao, Siyuan Huang, Chen Gao, Shuicheng Yan, Si Liu

机构 * Beihang University（北航大学）； National University of Singapore（新加坡国立大学）； Shanghai Jiao Tong University（上海交通大学）

专题命中数据集与评测：vision-language-action(abstract)；VLA(abstract)；分类 cs.RO、cs.CV

Comments 25 pages, 18 figures, Accepted by NeurIPS 2025

3. 部署与泛化 1 篇

2510.25122 2025-10-30 cs.RO 70%

NanoVLA: Routing Decoupled Vision-Language Understanding for Nano-sized Generalist Robotic Policies

Jiahong Chen, Jing Wang, Long Chen, Chuwei Cai, Jinghui Lu

机构 * University of British Columbia（不列颠哥伦比亚大学）； University of Alberta（阿尔伯塔大学）； Xiaomi EV（小米电动车）； Northeastern University（东北大学）

专题命中部署与泛化：vision-language-action(abstract)；VLA(abstract)；分类 cs.RO