LaST-R1: Reinforcing Action via Adaptive Physical Latent Reasoning for VLA Models

作者：Jiaming Liu, Jialin Gao, Ziyu Guo, Siyuan Qian, Yinxi Wang, Peng Jia, Shanghang Zhang, Pheng-Ann Heng · 单位：The Chinese University of Hong Kong State Key Laboratory of Multimedia Information · 会议/期刊：arXiv · 日期：2026-04-30 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with RL