Awesome Robotics Manipulation · full_paper

MAPS: Preserving Vision-Language Representations via Module-Wise Proximity Scheduling for Better Vision-Language-Action Generalization

作者：作者信息待提取 · 单位：Georgia Institute of Technology · 会议/期刊：arXiv · 日期：2025-11-25 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Model-agnostic Strategies

视觉语言动作泛化机器人学习
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Project
MAPS: Preserving Vision-Language Representations via Module-Wise Proximity Scheduling for Better Vision-Language-Action Generalization figure
AlphaXiv 中文论文页面（可滚动查看）