Awesome Robotics Manipulation · full_paper

Beyond Attention Magnitude: Leveraging Inter-layer Rank Consistency for Efficient Vision-Language-Action Models

arXiv · 2026-03-26 · Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Efficiency / Token Pruning

VLA机器人学习
新标签打开 AlphaXiv新标签打开 Paper
Beyond Attention Magnitude: Leveraging Inter-layer Rank Consistency for Efficient Vision-Language-Action Models figure
AlphaXiv 中文论文页面（可滚动查看）