EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models

作者：Yantai Yang, Yuhao Wang, Zichen Wen, Luo Zhongwei, Chang Zou, Zhipeng Zhang, Chuan Wen, Linfeng Zhang · 单位：School of Artificial Intelligence, Shanghai Jiao Tong University, Harbin Institute of Technology, Xi’an Jiaotong University, University of Electronic Science and Technology of China · 会议/期刊：arXiv preprint 2025 · 方向：层剪枝 / 令牌优化 · 发布日期：2025-06-11