Awesome Robotics Manipulation · full_paper

DySL-VLA: Efficient Vision-Language-Action Model Inference via Dynamic-Static Layer-Skipping for Robot Manipulation

arXiv · 2026-02-26 · Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Efficiency / Part of Model

VLA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
DySL-VLA: Efficient Vision-Language-Action Model Inference via Dynamic-Static Layer-Skipping for Robot Manipulation figure
AlphaXiv 中文论文页面（可滚动查看）