Awesome Robotics Manipulation · full_paper

Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning

作者：Huihan Liu, Changyeon Kim Bo Liu, Minghuan Liu · 会议/期刊：arXiv · 日期：2026-03-04 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models for Generalization / Continue Learning

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 Code
Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning figure
AlphaXiv 中文论文页面（可滚动查看）