arXiv preprint 2025 / 令牌优化

SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning

作者：Hanzhen Wang, Jiaming Xu, Yushun Xiang, Jiayi Pan, Yongkang Zhou, Yong-Lu Li, Guohao Dai · 会议/期刊：arXiv preprint 2025 · 方向：令牌优化 · 发布日期：2025-09-06

视觉语言动作令牌优化高效推理模型压缩剪枝
新标签打开 AlphaXiv
SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning figure
AlphaXiv 中文概览（可滚动查看）