arXiv preprint 2025 / 令牌优化

VLA-Cache: Towards Efficient Vision-Language-Action Model via Adaptive Token Caching in Robotic Manipulation

作者：Siyu Xu, Yunke Wang, Chenghao Xia, Dihao Zhu, Tao Huang, Chang Xu · 单位：School of Computer Science, University of Sydney, Australia, John Hopcropt Center for Computer Science, Shanghai Jiao Tong University, China · 会议/期刊：arXiv preprint 2025 · 方向：令牌优化 · 发布日期：2025-02-04

视觉语言动作令牌优化高效推理模型压缩操作
新标签打开 AlphaXiv新标签打开 Project新标签打开 Code
VLA-Cache: Towards Efficient Vision-Language-Action Model via Adaptive Token Caching in Robotic Manipulation figure
AlphaXiv 中文概览（可滚动查看）