arXiv preprint 2025 / 层剪枝 / 量化

RLRC: Reinforcement Learning-based Recovery for Compressed Vision-Language-Action Models

作者：Yuxuan Chen, Xiao Li · 单位：School of Mechanical Engineering, Shanghai Jiao Tong University · 会议/期刊：arXiv preprint 2025 · 方向：层剪枝 / 量化 · 发布日期：2025-06-21

视觉语言动作层剪枝模型压缩强化学习剪枝量化
新标签打开 AlphaXiv新标签打开 Project新标签打开 Code
RLRC: Reinforcement Learning-based Recovery for Compressed Vision-Language-Action Models figure
AlphaXiv 中文概览（可滚动查看）