Awesome Robotics Manipulation · full_paper

Scaling Verification Can Be More Effective than Scaling Policy Learning for Vision-Language-Action Alignment

作者：Jacky Kwok, Xilun Zhang, Mengdi Xu, Yuejiang Liu, Azalia Mirhoseini, Chelsea Finn, Marco Pavone · 单位：Stanford University, NVIDIA Research · 会议/期刊：arXiv · 日期：2026-02-12 · 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 Code
Scaling Verification Can Be More Effective than Scaling Policy Learning for Vision-Language-Action Alignment figure
AlphaXiv 中文论文页面（可滚动查看）