Awesome Robotics Manipulation · full_paper

VLA-OPD: Bridging Offline SFT and Online RL for Vision-Language-Action Models via On-Policy Distillation

作者：Zhide Zhong, Haodong Yan, Junfeng Li, Junjie He, Tianran Zhang, Haoang Li · 单位：HKUST (GZ) · 会议/期刊：arXiv · 日期：2026-03-27 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with RL

视觉语言动作机器人学习
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Project
VLA-OPD: Bridging Offline SFT and Online RL for Vision-Language-Action Models via On-Policy Distillation figure
AlphaXiv 中文论文页面（可滚动查看）