Awesome Robotics Manipulation · full_paper

EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models

作者：Zechen Bai, Chen Gao, Mike Zheng Shou · 单位：Show Lab, National University of Singapore · 会议/期刊：arXiv · 日期：2025-12-16 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models for Generalization / Test-time Adaptation

视觉语言动作泛化机器人学习数据集/基准
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Code
EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models figure
AlphaXiv 中文论文页面（可滚动查看）