STAR: Steering Action Representations during Inference
暂无中文版,显示英文原文。
摘自论文摘要
Vision-language-action models (VLAs) map language instructions and visual observations to robot actions, showing strong capabilities across robotic manipulation tasks. However, in our probing experiment, we find that action representations near the action output do not fully preserve task-relevant visual grounding.
摘自论文摘要,摘要生成中。
论文全文
本文依据 CC BY 4.0 许可发布,全文经署名以英文转载:阅读全文(英文)。原文见 arXiv:2610.41009(PDF)。