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。

2025-10-31 至 2025-10-31 共收录 8 篇信号源：cs.RO, cs.CV, cs.AI, cs.LG

1. VLA模型 6 篇

2506.09937 2025-10-31 cs.RO cs.AI 90%

SAFE: Multitask Failure Detection for Vision-Language-Action Models

Qiao Gu, Yuanliang Ju, Shengxiang Sun, Igor Gilitschenski, Haruki Nishimura, Masha Itkina, Florian Shkurti

机构 * University of Toronto（多伦多大学）； UofT Robotics Institute（UofT机器人研究所）； Vector Institute（向量研究所）； Toyota Research Institute（丰田研究院）

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

Comments NeurIPS 2025 camera ready. Project Page: https://vla-safe.github.io/

2506.19816 2025-10-31 cs.RO cs.CV 88%

CronusVLA: Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling

Hao Li, Shuai Yang, Yilun Chen, Xinyi Chen, Xiaoda Yang, Yang Tian, Hanqing Wang, Tai Wang, Dahua Lin, Feng Zhao, Jiangmiao Pang

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

Comments 39 pages, 24 figures

2510.26406 2025-10-31 cs.RO cs.AI 73%

Human-in-the-loop Online Rejection Sampling for Robotic Manipulation

Guanxing Lu, Rui Zhao, Haitao Lin, He Zhang, Yansong Tang

机构 * Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）； Tencent Robotics X（腾讯机器人实验室）

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

Comments 8 pages

2510.26536 2025-10-31 cs.RO 70%

RoboOS-NeXT: A Unified Memory-based Framework for Lifelong, Scalable, and Robust Multi-Robot Collaboration

Huajie Tan, Cheng Chi, Xiansheng Chen, Yuheng Ji, Zhongxia Zhao, Xiaoshuai Hao, Yaoxu Lyu, Mingyu Cao, Junkai Zhao, Huaihai Lyu, Enshen Zhou, Ning Chen, Yankai Fu, Cheng Peng, Wei Guo, Dong Liang, Zhuo Chen, Mengsi Lyu, Chenrui He, Yulong Ao, Yonghua Lin, Pengwei Wang, Zhongyuan Wang, Shanghang Zhang

机构 * State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University（1 多媒体信息处理国家重点实验室，计算机学院，北京大学）； Beijing Academy of Artificial Intelligence（2 北京人工智能研究院）； Institute of Automation, Chinese Academy of Sciences（3 中国科学院自动化研究所）； Beihang University（4 北航大学）

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

2510.26499 2025-10-31 cs.CR 50%

CyberNER: A Harmonized STIX Corpus for Cybersecurity Named Entity Recognition

Yasir Ech-Chammakhy, Anas Motii, Anass Rabii, Oussama Azrara, Jaafar Chbili

专题命中 VLA模型：action model(abstract)

Comments Accepted for publication at the 24th IEEE International Conference on Trust, Security and Privacy in Computing and Communications (IEEE TrustCom 2025)

2506.22579 2025-10-31 eess.SY cs.SY 50%

Data-Efficient Excavation Force Estimation for Wheel Loaders

Armin Abdolmohammadi, Navid Mojahed, Shima Nazari, Bahram Ravani

专题命中 VLA模型：action model(abstract)

Journal ref IEEE Access, vol. 13, pp. 181846-181862, Oct. 16, 2025

2. 动作表示与策略 1 篇

2510.26742 2025-10-31 cs.RO 61%

Running VLAs at Real-time Speed

Yunchao Ma, Yizhuang Zhou, Yunhuan Yang, Tiancai Wang, Haoqiang Fan

机构 * Dexmal ； StepFun

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

Comments Code is available at https://github.com/Dexmal/realtime-vla

3. 部署与泛化 1 篇

2506.07127 2025-10-31 cs.RO cs.AI 73%

Human-assisted Robotic Policy Refinement via Action Preference Optimization

Wenke Xia, Yichu Yang, Hongtao Wu, Xiao Ma, Tao Kong, Di Hu

机构 * Gaoling School of Artificial Intelligence, Renmin University of China, Beijing（中国人民大学北京校区人工智能学院）； Engineering Research Center of Next-Generation Intelligent Search（下一代智能搜索与推荐工程研究中心）； Beijing Key Laboratory of Research on Large Models（北京大型模型研究重点实验室）

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

Comments Accepted By NeurIPS 2025