MEKAWIRE
专业arXiv

Beyond Actions: Learning Future Operation Targets for Vision-Language-Action Models

Min Lin, Bokai Zhou, Jianqi Lin, Kaiyuan Yang, Yicheng Chang, Junjie Yu, Xiaofan Liu, Jianhua Han, Rui Li, Shen Zhao, Xiaodan Liang
论文原文 阅读论文全文（PDF）
暂无中文版，显示英文原文。
摘自论文摘要

Actions specify what a robot should execute, but do not describe what those commands will achieve. Vision-language-action (VLA) policies nevertheless learn primarily by predicting action chunks from images, language, and state.

摘自论文摘要，摘要生成中。

受许可协议限制，本站不转载该论文全文，仅提供摘要和原文链接。