Awesome Robotics Manipulation · full_paper

Rethinking Visual-Language-Action Model Scaling: Alignment, Mixture, and Regularization

作者：Ye Wang, Sipeng Zheng, Hao Luo, Wanpeng Zhang, Haoqi Yuan, Chaoyi Xu, Haiweng Xu, Yicheng Feng, Mingyang Yu, Zhiyu Kang, Zongqing Lu, Qin Jin · 单位：Renmin University of China, Peking University · 会议/期刊：arXiv · 日期：2026-02-10 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / Evaluation of Vision Language Action Models

视觉语言动作感知机器人学习
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Code
Rethinking Visual-Language-Action Model Scaling: Alignment, Mixture, and Regularization figure
AlphaXiv 中文论文页面（可滚动查看）