RL for Flow Matching Models

RL: Reinforcement Learning

Follow this topic Ask about this topic

Latest papers

22 papers7 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

SIFR: Stable Signed Flow Reinforcement
Nov 6, 2026Runlong Liao, Xingqian Xu, Lizhang Chen +7RL for Flow Matching Models RL Stability
NVIDIA · The University of Texas at Austin
Optimizing Stochastic Policy Geometry for Few-Step Flow Reinforcement Learning
Oct 30, 2026Zhuguanyu Wu, Congjia Chen, Ruihao Gong +4RL for Flow Matching Models Reinforcement Learning
Beihang University · Sensetime Research
Value-Rectified Distillation for Flow-based Offline Reinforcement Learning
Oct 21, 2026Ke Jiang, Wen Jiang, Yoshinobu Kawahara +1Offline RL Policy Distillation
College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics · MIIT Key Laboratory of Pattern Analysis and Machine Intelligence · Graduate School of Information Science and Technology, The University of Osaka +1
Doob-Based Generative Policy Optimization
Oct 20, 2026Maojiang Su, Qijie Zhu, Yu Xiao +4Policy Optimization RL for Diffusion Models
Department of Computer Science, Northwestern University · Center for Foundation Models and Generative AI, Northwestern University · Department of Statistics and Data Science, Northwestern University +1
ArcFlow: Training Flow Policies for Multiple Solver Budgets
Oct 20, 2026Hieu Tran, Hong YuFlow-Based Policy Learning RL for Flow Matching Models
University of Massachusetts Amherst · University of Massachusetts Lowell
Distribution-Based Regularization for Reward Fine-Tuning Diffusion and Flow Models
Oct 17, 2026Romeo Passaro, Jeongjae Lee, Jong Chul Ye +4Generative Modeling Diffusion Model Alignment
University of Oxford · AITHYRA · KAIST +2
QF3: Fast Flow RL with Filtered Q-Gradients
Oct 6, 2026Chung Min Kim, Brent Yi, David McAllister +7Robotic RL RL for Legged Locomotion
UC Berkeley · Amazon FAR
MEND: RL For Flow Models via Proximal Velocity Matching
Oct 5, 2026Shreshth Saini, Neil Birkbeck, Yilin Wang +2Flow Matching RL for Image Generation
The University of Texas at Austin · Google · University of Colorado Boulder
QAMM: Adjoint MeanFlow Matching for Few-Step Offline Reinforcement Learning
Sep 28, 2026Yuehu Gong, Shutong Ding, Mokai Pan +4Flow Matching MeanFlow
School of Data Science, Fudan University · ShanghaiTech University · Shanghai Innovation Institute
Timestep Weighting: A Hidden Key to Effective ELBO-Based Flow-Matching RL
Sep 26, 2026Qinwei Ma, Jingzhe Shi, Simin Fan +2RL for Image Generation Adaptive Loss Weighting
College of AI, Tsinghua University · Department of Electrical and Computer Engineering, Princeton University · EPFL +1
LC-GRPO: Bridging Train-Inference Gap for Flow-Based GRPO with Langevin Correction
Aug 6, 2026Yingqing Guo, Hui Yuan, Zijian He +2RL for Video Generation RL for Image Generation
VINE: Taming Generative Control Policies for Reinforcement Learning
Jul 11, 2026Rushuai Yang, Zhuo Han, Houlin Li +10RL for Robotics Offline RL
1AgiBot · 3Peking University · 2The Hong Kong University of Science and Technology
ReFPO: Reflow Regularization for Flow Matching Policy Gradients
Jun 19, 2026Ge Wang, Yibo Peng, Fan Feng +10Policy Gradient Reinforcement Learning
Ising AI · CUHK-Shenzhen · FNii-Shenzhen
Reversal Q-Learning
Jun 16, 2026Aditya Oberai, Seohong Park, Sergey LevineOff-Policy RL Flow-Based Policy Learning
University of California, Berkeley.
Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models
Jun 9, 2026Bowen Ping, Xiangxin Zhou, Penghui Qi +3RL for Video Generation RL for Image Generation
Xi’an Jiaotong University · Tencent Hunyuan · National University of Singapore
Reinforcement Learning for Flow-Matching Policies with Density Transport
Jun 7, 2026Boshu Lei, Kostas Daniilidis, Antonio LoquercioFlow Matching Robotic RL
University of Pennsylvania · Philadelphia, PA 19103
AdvantageFlow: Regularized Advantage-Weighted RL in Flow Models
May 25, 2026Branislav Kveton, Anup Rao, Subhojyoti Mukherjee +2Rectified Flow RL for Image Generation
Adobe Research
Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching Models
May 11, 2026Andreas Bergmeister, Stefanie Jegelka, Nikolas Nüsken +2Diffusion Model Alignment Flow Matching
1TU Munich, MCML · 2MIT CSAIL · 3King’s College London +2
ScoRe-Flow: Complete Distributional Control via Score-Based Reinforcement Learning for Flow Matching
Apr 13, 2026Xiaotian Qiu, Lukai Chen, Jinhao Li +3RL for Flow Matching Models Flow-Based Policy Learning
Zhejiang University, Hangzhou, China · Shanghai Innovation Institute · Shanghai Jiao Tong University, Shanghai, China +1
Discrete Flow Matching Policy Optimization
Apr 7, 2026Maojiang Su, Po-Chung Hsieh, Weimin Wu +4TV Regularization RL for Flow Matching Models
Center for Foundation Models and Generative AI, Northwestern University, Evanston, IL 60208, USA · Department of Electrical Engineering, National Taiwan University, Taipei 10617, Taiwan · Department of Physics, National Taiwan University, Taipei 10617, Taiwan +1
Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO
Feb 6, 2026Yunze Tong, Mushui Liu, Canyu Zhao +7Flow Matching Temporal Credit Assignment
1Zhejiang University, Hangzhou, China · 2Taobao & Tmall Group of Alibaba, Hangzhou, China · 3Tsinghua University, Beijing, China
Dual-Grained Policy Optimization for Hallucination Reduction in Flow-Based RL
Feb 3, 2026Xiaofeng Tan, Jun Liu, Yuanting Fan +7RL for Flow Matching Models RL Fine-Tuning
Southeast University · Tencent Youtu Lab · Southern University of Science and Technology

Nov 6, 2026J/K move · Enter open · S save

SIFR: Stable Signed Flow Reinforcement

Runlong Liao, Xingqian Xu, Lizhang Chen, Baiyu Su+6

NVIDIA · The University of Texas at Austin

RL for Flow Matching Models RL Stability Regularized RL T2I Generation

Open paper AskPDF arXiv

Reward-based fine-tuning of flow models requires effectively promoting high-reward and suppressing low-reward samples, while maintaining training stability over many rounds of iterative updates. Iterative reward fine-tuning provides a simple starting point, but the positive reward weights give no explicit unfitting signal, and repeated reweighting concentrates the distribution and causes collapse. We propose Stable Signed Flow Reinforcement (SIFR), which replaces the reward weights by signed advantages to supply the missing unfitting signal, and constrains the velocity drift from a reference model to stabilize the updates, with a Lagrange multiplier that adapts the regularization strength to a prescribed drift budget. We further show that existing flow RL methods fall within this framework: they implicitly minimize the signed loss, differing in their regularization choices. We validate SIFR on SD3.5 Medium (2.5B) and FLUX.2 Klein (9B) and scale it to Cosmos 3 Super Text2Image (64B): across all 12 backbone--reward pairs with preference and rule-based rewards, it matches or exceeds existing methods, reaches their peak rewards much faster, and keeps improving over long training where they plateau or collapse.