Awesome Robotics Manipulation · full_paper

Do What You Say: Steering Vision-Language-Action Models via Runtime Reasoning-Action Alignment Verification

作者：Yilin Wu, Anqi Li, Tucker Hermans, Fabio Ramos, Andrea Bajcsy, Claudia P´erez-D’Arpino · 单位：University of Sydney · 会议/期刊：ICRA 2026 · 日期：2025-10-18 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Model-agnostic Strategies

视觉语言动作机器人学习
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Project
Do What You Say: Steering Vision-Language-Action Models via Runtime Reasoning-Action Alignment Verification figure
AlphaXiv 中文论文页面（可滚动查看）