Awesome Robotics Manipulation · full_paper

RoboAlign: Learning Test-Time Reasoning for Language-Action Alignment in Vision-Language-Action Models

作者：Dongyoung Kim Sumin Park, Woomin Song, Seungku Kim, Taeyoung Kim · 单位：KAIST, UC Berkeley · 会议/期刊：arXiv · 日期：2026-03-22 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Auxiliary Tasks - Text Goal Extraction

辅助任务视觉语言动作机器人学习
新标签打开 AlphaXiv新标签打开 Paper
RoboAlign: Learning Test-Time Reasoning for Language-Action Alignment in Vision-Language-Action Models figure
AlphaXiv 中文论文页面（可滚动查看）