Flow-GRPO: Training Flow Matching Models via Online RL

Jie Liu 0047, Gongye Liu, Jiajun Liang, Yangguang Li 0001, Jiaheng Liu, Xintao Wang 0002, Pengfei Wan 0001, Di Zhang 0026, Wanli Ouyang. Flow-GRPO: Training Flow Matching Models via Online RL. In Danielle Belgrave, Cheng Zhang 0005, Laura N. Montoya, Hsuan-Tien Lin, Razvan Pascanu, Piotr Koniusz, Marzyeh Ghassemi, Nancy Chen, Iván Vladimir Meza Ruíz, Arturo Loaiza-Bonilla, editors, Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, NeurIPS 2025, San Diago, CA, USA, December 2-7, 2025 / Mexico City, Mexico, November 30 - December 5, 2025. 2025. [doi]

Abstract

Abstract is missing.