LatBot: Distilling Universal Latent Actions for Vision-Language-Action Models

作者：Zuolei Li, Xingyu Gao, B Xiaofan Wang, Jianlong Fu · 单位：Institute of Microelectronics, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Microsoft Research · 会议/期刊：arXiv · 日期：2025-11-28 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Latent Learning