ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning

v1v2v3v4v5 (latest)

ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning

28 May 2025

ArXiv (abs)PDF HTML HuggingFace (1 upvotes)

Papers citing "ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning"

4 / 4 papers shown

Title
VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators Hengtao Li Pengxiang Ding Runze Suo Yihao Wang Zirui Ge ... Kexian Yu Mingyang Sun Hongyin Zhang Donglin Wang Weihua Su 24 0 0 01 Oct 2025
Learning a Diffusion Model Policy from Rewards via Q-Score Matching Michael Psenka Alejandro Escontrela Pieter Abbeel Yi-An Ma DiffM 261 45 0 17 Feb 2025
Online Reward-Weighted Fine-Tuning of Flow Matching with Wasserstein Regularization Jiajun Fan Shuaike Shen Chaoran Cheng Yuxin Chen Chumeng Liang Ge Liu 109 7 0 09 Feb 2025
One Step Diffusion via Shortcut Models Kevin Frans Danijar Hafner Sergey Levine Pieter Abbeel VLM DiffM 296 99 0 16 Oct 2024