arXiv preprint 2025 / 令牌优化

CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification

作者：Wei Li, Renshan Zhang, Rui Shao, Jie He, Liqiang Nie · 单位：School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen · 会议/期刊：arXiv preprint 2025 · 方向：令牌优化 · 发布日期：2025-08-28

视觉语言动作令牌优化模型压缩
新标签打开 AlphaXiv新标签打开 Project新标签打开 Code
CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification figure
AlphaXiv 中文概览（可滚动查看）