One-Step Flow Policy: Self-Distillation for Fast Visuomotor Policies

作者：Shaolong Li · 单位：CSE Department, University of Michigan, Lehigh University, College of AI, Tsinghua University · 会议/期刊：arXiv · 日期：2026-03-12 · 来源：Low-Level Learning-Based Action Modelling / Policy Learning / Flow Matching Policy