Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance

作者：Songsheng Wang, Rucheng Yu, Zhihang Yuan, Chao Yu, Feng Gao, Yu Wang, Derek F. Wong · 单位：CT Lab, Department of Computer and Information Science, University of Macau, Tsinghua University, Zhongguancun Academy · 会议/期刊：Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing · 方向：高效动作解码 · 发布日期：2025-07-30