Discrete Flow Matching Policy Optimization
arXiv:2604.06491v1 Announce Type: new Abstract: We introduce Discrete flow Matching policy Optimization (DoMinO), a unified framework for Reinforcement Learning (RL) fine-tuning Discrete Flow Matching (DFM) …
Maojiang Su, Po-Chung Hsieh, Weimin Wu, Mingcheng Lu, Jiunhau Chen, Jerry Yao-Chieh Hu, Han Liu
21 views