STARE-VLA: Progressive Stage-Aware Reinforcement for Fine-Tuning Vision-Language-Action Models

作者：Feng Xu, Guangyao Zhai, Xin Kong, Tingzhong Fu, Daniel F.N. Gordon, Xueli An, Benjamin Busam · 单位：Technical University of Munich, Imperial College London, Munich Research Center, Huawei Technologies · 会议/期刊：arXiv · 日期：2025-12-04 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with RL