arXiv preprint 2025 / 强化学习方法

CO-RFT: Efficient Fine-Tuning of Vision-Language-Action Models through Chunked Offline Reinforcement Learning

作者：Dongchi Huang, Zhirui Fang, Tianle Zhang, Yihang Li, Lin Zhao, Chunhe Xia · 会议/期刊：arXiv preprint 2025 · 方向：强化学习方法 · 发布日期：2025-08-04

视觉语言动作强化学习方法高效推理高效训练强化学习
新标签打开 AlphaXiv
CO-RFT: Efficient Fine-Tuning of Vision-Language-Action Models through Chunked Offline Reinforcement Learning figure
AlphaXiv 中文概览（可滚动查看）