Awesome Robotics Manipulation · full_paper

AC2-VLA: Action-Context-Aware Adaptive Computation in Vision-Language-Action Models for Efficient Robotic Manipulation

作者：Wenda Yu, Tianshi Wang, Fengling Li, Jingjing Li, Lei Zhu · 单位：Tongji University, University of Technology Sydney, University of Electronic Science and Technology of China · 会议/期刊：arXiv · 日期：2026-01-27 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Efficiency / Token Pruning

视觉语言动作机器人学习操作
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Code
AC2-VLA: Action-Context-Aware Adaptive Computation in Vision-Language-Action Models for Efficient Robotic Manipulation figure
AlphaXiv 中文论文页面（可滚动查看）