π-StepNFT: Wider Space Needs Finer Steps in Online RL for Flow-based VLAs

作者：Siting Wang, Xiaofeng Wang, Zheng Zhu, Minnan Pei, Xinyu Cui, Cheng Deng, Jian Zhao, Guan Huang, Haifeng Zhang, Jun Wang · 单位：GigaAI Institute of Automation, Chinese Academy of Sci · 会议/期刊：arXiv · 日期：2026-03-02 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with RL