English
Related papers

Related papers: One-Step Flow Policy Mirror Descent

200 papers

Sampling from diffusion models involves a slow iterative process that hinders their practical deployment, especially for interactive applications. To accelerate generation speed, recent approaches distill a multi-step diffusion model into a…

Machine Learning · Computer Science 2025-03-11 Yilun Xu , Weili Nie , Arash Vahdat

We propose DiFFPO, Diffusion Fast and Furious Policy Optimization, a unified framework for training masked diffusion large language models (dLLMs) to reason not only better (furious), but also faster via reinforcement learning (RL). We…

Machine Learning · Computer Science 2026-01-13 Hanyang Zhao , Dawen Liang , Wenpin Tang , David Yao , Nathan Kallus

In Reinforcement Learning (RL), regularization has emerged as a popular tool both in theory and practice, typically based either on an entropy bonus or a Kullback-Leibler divergence that constrains successive policies. In practice, these…

Machine Learning · Computer Science 2025-06-18 Alena Shilova , Alex Davey , Brahim Driss , Riad Akrour

In this paper, we present a new policy gradient (PG) methods, namely the block policy mirror descent (BPMD) method for solving a class of regularized reinforcement learning (RL) problems with (strongly)-convex regularizers. Compared to the…

Machine Learning · Computer Science 2022-09-20 Guanghui Lan , Yan Li , Tuo Zhao

Discrete flow models (DFMs) are a class of flexible generative models for generating discrete data, and diffusion large language models (dLLMs) can be viewed as a special case with a specific choice of mixture path and a masked source…

Machine Learning · Computer Science 2026-05-12 Zhengyan Wan , Yidong Ouyang , Panwen Hu , Qiang Sun

Reinforcement learning (RL) has become a standard technique for post-training diffusion-based image synthesis models, as it enables learning from reward signals to explicitly improve desirable aspects such as image quality and prompt…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 David McAllister , Miika Aittala , Tero Karras , Janne Hellsten , Angjoo Kanazawa , Timo Aila , Samuli Laine

Controllable diffusion generation often relies on various heuristics that are seemingly disconnected without a unified understanding. We bridge this gap with Diffusion Controller (DiffCon), a unified control-theoretic view that casts…

Machine Learning · Computer Science 2026-03-10 Tong Yang , Moonkyung Ryu , Chih-Wei Hsu , Guy Tennenholtz , Yuejie Chi , Craig Boutilier , Bo Dai

Flow Matching (FM) is a simulation-free method for learning a continuous and invertible flow to interpolate between two distributions, and in particular to generate data from noise. Inspired by the variational nature of the diffusion…

Machine Learning · Statistics 2025-07-14 Chen Xu , Xiuyuan Cheng , Yao Xie

Diffusion-based image super-resolution (SR) has recently attracted significant attention by leveraging the expressive power of large pre-trained text-to-image diffusion models (DMs). A central practical challenge is resolving the trade-off…

Image and Video Processing · Electrical Eng. & Systems 2026-01-26 Maxence Noble , Gonzalo Iñaki Quintana , Benjamin Aubin , Clément Chadebec

This paper studies the policy mirror descent (PMD) method, which is a general policy optimization framework in reinforcement learning and can cover a wide range of policy gradient methods by specifying difference mirror maps. Existing…

Optimization and Control · Mathematics 2026-01-01 Wenye Li , Hongxu Chen , Jiacai Liu , Ke Wei

Deep reinforcement learning (RL) algorithms typically parameterize the policy as a deep network that outputs either a deterministic action or a stochastic one modeled as a Gaussian distribution, hence restricting learning to a single…

Machine Learning · Computer Science 2024-06-04 Zechu Li , Rickmer Krohn , Tao Chen , Anurag Ajay , Pulkit Agrawal , Georgia Chalvatzaki

We propose Diffusion-Sharpening, a fine-tuning approach that enhances downstream alignment by optimizing sampling trajectories. Existing RL-based fine-tuning methods focus on single training timesteps and neglect trajectory-level alignment,…

Computer Vision and Pattern Recognition · Computer Science 2025-02-18 Ye Tian , Ling Yang , Xinchen Zhang , Yunhai Tong , Mengdi Wang , Bin Cui

Diffusion distillation, exemplified by Distribution Matching Distillation (DMD), has shown great promise in few-step generation but often sacrifices quality for sampling speed. While integrating Reinforcement Learning (RL) into distillation…

Machine Learning · Computer Science 2026-04-22 Linwei Dong , Ruoyu Guo , Ge Bai , Zehuan Yuan , Yawei Luo , Changqing Zou

Diffusion language models (DLMs) enable parallel, order-agnostic generation with iterative refinement, offering a flexible alternative to autoregressive large language models (LLMs). However, adapting reinforcement learning (RL) fine-tuning…

Machine Learning · Computer Science 2026-02-12 Kevin Rojas , Jiahe Lin , Kashif Rasul , Anderson Schneider , Yuriy Nevmyvaka , Molei Tao , Wei Deng

Standard knowledge distillation for autoregressive models often suffers from distribution mismatch. While on-policy methods mitigate this by leveraging student-generated outputs, they rely on computationally expensive Reinforcement Learning…

Machine Learning · Computer Science 2026-05-08 Miao Rang , Zhenni Bi , Hang Zhou , Kai Han , Xuechun Wang , An Xiao , Xinghao Chen , Yunhe Wang , Hanting Chen

Diffusion models have garnered widespread attention in Reinforcement Learning (RL) for their powerful expressiveness and multimodality. It has been verified that utilizing diffusion policies can significantly improve the performance of RL…

Machine Learning · Computer Science 2024-12-17 Shutong Ding , Ke Hu , Zhenhao Zhang , Kan Ren , Weinan Zhang , Jingyi Yu , Jingya Wang , Ye Shi

While diffusion distillation has enabled one-step generation through methods like Variational Score Distillation, adapting distilled models to emerging new controls -- such as novel structural constraints or latest user preferences --…

Computer Vision and Pattern Recognition · Computer Science 2025-03-13 Yihong Luo , Tianyang Hu , Yifan Song , Jiacheng Sun , Zhenguo Li , Jing Tang

Generative policies based on expressive model classes, such as diffusion and flow matching, are well-suited to complex control problems with highly multimodal action distributions. Their expressivity, however, comes at a significant…

Machine Learning · Computer Science 2026-05-13 Christos Ziakas , Alessandra Russo , Avishek Joey Bose

A commonly used family of RL algorithms for diffusion policies conducts softmax reweighting over samples from the behavior policy, which often induces an overgreedy policy and fails to utilize feedback from negative samples. In this work,…

Machine Learning · Computer Science 2026-05-26 Haitong Ma , Chenxiao Gao , Tianyi Chen , Na Li , Bo Dai

Sampling from unnormalized target distributions is a fundamental yet challenging task in machine learning and statistics. Existing sampling algorithms typically require many iterative steps to produce high-quality samples, leading to high…

Machine Learning · Statistics 2026-02-27 Pascal Jutras-Dube , Jiaru Zhang , Ziran Wang , Ruqi Zhang