Awesome Robotics Manipulation · full_paper

Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning

作者：Jiaheng Hu, Jay Shim, Chen Tang, Yoonchang Sung, Bo Liu, Peter Stone, Roberto Martín-Martín, {jiahengh, jshim, pstone, robertomm}@utexas.edu · 单位：UT Austin UCLA NTU Sony AI · 会议/期刊：arXiv · 日期：2026-03-12 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models for Generalization / Continue Learning

强化学习视觉语言动作触觉泛化机器人学习
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Code
Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning figure
AlphaXiv 中文论文页面（可滚动查看）