arXiv preprint 2025 / 监督微调

ControlVLA: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Models

作者：Puhao Li, Yingying Wu, Ziheng Xi, Wanlin Li, Yuzhe Huang, Zhiyuan Zhang, Yinghan Chen, Jianan Wang, Song-Chun Zhu, Tengyu Liu, Siyuan Huang · 单位：Tsinghua University State Key Lab of General Artificial Intelligence, BIGAI, Peking University Astribot Inc · 会议/期刊：arXiv preprint 2025 · 方向：监督微调 · 发布日期：2025-06-19

视觉语言动作监督微调高效训练
新标签打开 AlphaXiv新标签打开 Project新标签打开 Code
ControlVLA: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Models figure
AlphaXiv 中文概览（可滚动查看）