← Back to all news
arXiv Machine Learning By Zhengyan Wan, Yidong Ouyang, Panwen Hu, Qiang Sun

dFlowGRPO: Rate-Aware Policy Optimization for Discrete Flow Models

Read the original on arXiv Machine Learning →

The paper introduces dFlowGRPO, a reinforcement learning framework tailored for discrete flow models (DFMs). It generalizes previous work on diffusion large language models by supporting various probability paths and non-masked source distributions, and formulates denoising as a Markov decision process that leverages transition rates and posterior models. Experiments on the multimodal DFM FUDOKI show that dFlowGRPO outperforms existing GRPO methods on text‑to‑image generation and matches continuous flow models on multimodal understanding tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Jul 17

A Continuous-Time Reinforcement Learning Framework for Fine-Tuning Discrete Diffusion Models

arXiv:2607. 14522v1 Announce Type: new Abstract: We formulate reinforcement learning (RL) in continuous time with discrete state spaces and possibly arbitrary action spaces via a stochastic control approach, where the state dynamics are modeled as a controlled continuous-time Markov chain (CTMC).

By Zikun Zhang, Jiayuan Sheng, David D. Yao, Wenpin Tang
llmsdiffusionreinforcement-learningfine-tuning
More like this →
arXiv Machine Learning
Aug 31

Amortizing intractable inference in diffusion models for vision, language, and control

The paper introduces a data‑free learning objective called relative trajectory balance for training diffusion models to sample from a posterior defined by a diffusion prior and an arbitrary black‑box constraint or likelihood. It proves asymptotic correctness of this objective and demonstrates its use across vision, language, and multimodal tasks, including classifier guidance, language infilling, and text‑to‑image generation. Additionally, the method is applied to continuous control with a score‑based behavior prior, achieving state‑of‑the‑art results in offline reinforcement learning.

By Siddarth Venkatraman, Moksh Jain, Luca Scimeca, Minsu Kim, Marcin Sendera, Mohsin Hasan, Luke Rowe, Sarthak Mittal, Pablo Lemos, Emmanuel Bengio, Alexandre Adam, Jarrid Rector-Brooks, Yoshua Bengio, Glen Berseth, Esmeralda S. Whitammer
llmsdiffusionreinforcement-learningmultimodalbenchmarks
More like this →
arXiv AI
Jun 30

Dual-Flow Reinforcement Learning with State-Aware Exploration

arXiv:2606. 29820v1 Announce Type: cross Abstract: In complex continuous-control reinforcement learning tasks, multimodal optimal actions often coincide with uncertain, multimodal return distributions, making reliable value estimation and multimodal exploration challenging.

By Qijun Li, Zheng Fu, Qi Song, Yifei He, Weitao Zhou, Kun Jiang, Diange Yang
diffusionreinforcement-learningmultimodalbenchmarks
More like this →
arXiv AI
Jun 16

QPILOTS: Efficient Test-Time Q-Steering for Flow Policies

arXiv:2606. 14801v1 Announce Type: cross Abstract: Flow-matching and diffusion policies are expressive action generators, but optimizing them with temporal-difference reinforcement learning (RL) remains difficult.

By Yifan Ruan, Chenyang Cao, Andreas Burger, Ali Pesaranghader, Kaveh Kamali, Jaehong Kim, Nandita Vijaykumar, Alan Aspuru-Guzik, Igor Gilitschenski, Nicholas Rhinehart
diffusionreinforcement-learningroboticsfine-tuningmultimodalbenchmarks
More like this →