arXivDaily arXiv每日学术速递 周一至周五更新

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。

2025-08-14 至 2025-08-14 共收录 5 信号源:cs.RO, cs.CV, cs.AI, cs.LG

1. VLA模型 3 篇

2508.09071 2025-08-14 cs.RO 88%

GeoVLA: Empowering 3D Representations in Vision-Language-Action Models

Lin Sun, Bin Xie, Yingfei Liu, Hao Shi, Tiancai Wang, Jiale Cao

机构 * Tianjin University(天津大学) Dexmal Tsinghua University(清华大学)

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

Comments The project is visible at https://linsun449.github.io/GeoVLA/

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.03936 2025-08-14 cs.CV 57%

Learning Adaptive Node Selection with External Attention for Human Interaction Recognition

Chen Pang, Xuequan Lu, Qianyu Zhou, Lei Lyu

机构 * Shandong Normal University(山东师范大学) University of Western Australia(西澳大学) Jilin University(吉林大学) University of Western(西澳大学)

专题命中 VLA模型 :action model(abstract);分类 cs.CV

Comments Accepted by ACM MM25

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.09282 2025-08-14 astro-ph.HE astro-ph.CO astro-ph.GA 50%

Numerical modelling of the lobes of radio galaxies VI. Polarimetric simulations of universal pressure profile cluster atmospheres

Michael Stimpson, Martin Hardcastle, Martin Krause

专题命中 VLA模型 :VLA(abstract)

Comments 24 pages, 18 figures

Journal ref Monthly Notices of the Royal Astronomical Society, Volume 539, Issue 2, pp. 1668-1691, 24 pp. 2025

详情

展开后加载摘要…

URL PDF HTML 收藏

2. 数据集与评测 1 篇

2508.09404 2025-08-14 cs.CV cs.MM 74%

Waymo-3DSkelMo: A Multi-Agent 3D Skeletal Motion Dataset for Pedestrian Interaction Modeling in Autonomous Driving

Guangxun Zhu, Shiyu Fan, Hang Dai, Edmond S. L. Ho

机构 * University of Glasgow(格拉斯哥大学) Wuhan University(武汉大学)

专题命中 数据集与评测 :action model(title);分类 cs.CV

Comments ACM Multimedia 2025 (Dataset Track) Paper

详情

展开后加载摘要…

URL PDF HTML 收藏

3. 部署与泛化 1 篇

2508.07770 2025-08-14 cs.RO 70%

AgentWorld: An Interactive Simulation Platform for Scene Construction and Mobile Robotic Manipulation

Yizheng Zhang, Zhenjun Yu, Jiaxin Lai, Cewu Lu, Lei Han

机构 * Tencent Robotics X(腾讯机器人X) Shanghai Jiao Tong University(上海交通大学)

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

Comments Accepted by Conference on Robot Learning 2025

详情

展开后加载摘要…

URL PDF HTML 收藏