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

作者：Zebin Yang, Yijiahao Qi, Tong Xie, Bo Yu, Shaoshan Liu, Meng Li · 单位：Institute for Artificial Intelligence, School of Integrated Circuits, Peking University, Beijing, China, Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen, China, School of Electronics Engineering and Computer Science, Peking University, Beijing, China, Beijing Advanced Innovation Center for Integrated Circuits, Beijing, China · 会议/期刊：arXiv · 日期：2026-02-26 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Efficiency / Part of Model