From Flow to One Step: Real-Time Multi-Modal Trajectory Policies via Implicit Maximum Likelihood Estimation-based Distribution Distillation

作者：Ju Dong, Liding Zhang, Lei Zhang, Yu Fu, Kaixin Bai, Zolt´an-Csaba M´arton, Zhenshan Bing, Zhaopeng Chen, Alois Christian Knoll, Jianwei Zhang, Consistency Door Open Dynamic Pick, Place · 单位：Technical University of Munich, Germany · 会议/期刊：arXiv · 日期：2026-03-10 · 来源：Low-Level Learning-Based Action Modelling / Policy Learning / Flow Matching Policy