arXiv preprint 2025 / 量化 / 令牌优化

SQAP-VLA: A Synergistic Quantization-Aware Pruning Framework for High-Performance Vision-Language-Action Models

作者：Hengyu Fang, Yijiang Liu, Yuan Du, Li Du, Huanrui Yang · 单位：School of Electronic Science and Engineering, Nanjing University, University of Arizona · 会议/期刊：arXiv preprint 2025 · 方向：量化 / 令牌优化 · 发布日期：2025-09-11

视觉语言动作量化模型压缩剪枝令牌优化
新标签打开 AlphaXiv新标签打开 Code
SQAP-VLA: A Synergistic Quantization-Aware Pruning Framework for High-Performance Vision-Language-Action Models figure
AlphaXiv 中文概览（可滚动查看）