Awesome Robotics Manipulation · full_paper

Token Expand-Merge: Training-Free Token Compression for Vision-Language-Action Models

作者：Yifan Ye, Jiaqi Ma, Jun Cen, Zhihe Lu · 单位：Hamad Bin Khalifa University, Education City, Doha 24404, Qatar, University, Hangzhou 310058, China · 会议/期刊：arXiv · 日期：2025-12-10 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Efficiency / Token Pruning

视觉语言动作数据筛选机器人学习
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Code
Token Expand-Merge: Training-Free Token Compression for Vision-Language-Action Models figure
AlphaXiv 中文论文页面（可滚动查看）