Awesome Robotics Manipulation · full_paper

Learning to Accelerate Vision-Language-Action Models through Adaptive Visual Token Caching

arXiv · 2026-01-31 · Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Efficiency / Token Pruning

VLA感知机器人学习
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Code
Learning to Accelerate Vision-Language-Action Models through Adaptive Visual Token Caching figure
AlphaXiv 中文论文页面（可滚动查看）