English
Related papers

Related papers: Pixel-wise RL on Diffusion Models: Reinforcement L…

200 papers

Text-to-image diffusion models are a class of deep generative models that have demonstrated an impressive capacity for high-quality image generation. However, these models are susceptible to implicit biases that arise from web-scale…

Computer Vision and Pattern Recognition · Computer Science 2024-01-24 Yinan Zhang , Eric Tzeng , Yilun Du , Dmitry Kislyuk

Reinforcement learning from human feedback (RLHF) has been popular for aligning text-to-image (T2I) diffusion models with human preferences. As a mainstream branch of RLHF, Direct Preference Optimization (DPO) offers a computationally…

Machine Learning · Computer Science 2026-05-07 Jiaming Hu , Jiamu Bai , Haoyu Wang , Debarghya Mukherjee , Ioannis Ch. Paschalidis

Aligning denoising generative models with human preferences or verifiable rewards remains a key challenge. While policy-gradient online reinforcement learning (RL) offers a principled post-training framework, its direct application is…

Machine Learning · Computer Science 2026-04-28 Bingda Tang , Yuhui Zhang , Xiaohan Wang , Jiayuan Mao , Ludwig Schmidt , Serena Yeung-Levy

Discrete diffusion models have recently gained significant attention due to their ability to process complex discrete structures for language modeling. However, fine-tuning these models with policy gradient methods, as is commonly done in…

Machine Learning · Statistics 2025-12-19 Oussama Zekri , Nicolas Boullé

Fine-tuning pre-trained generative models with Reinforcement Learning (RL) has emerged as an effective approach for aligning outputs more closely with nuanced human preferences. In this paper, we investigate the application of Group…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Matteo Gallici , Haitz Sáez de Ocáriz Borde

Recent theory suggests that reward-model-first methods can be more sample-efficient than direct policy fitting when the reward function is statistically simpler than the induced policy. We propose DDO-RM, a finite-candidate…

Machine Learning · Statistics 2026-05-01 Tiantian Zhang , Jierui Zuo , Michael Chen , Wenping Wang

Reinforcement learning (RL) has shown extraordinary potential in aligning diffusion models to downstream tasks, yet most of them still suffer from significant reward hacking, which degrades generative diversity and quality by inducing…

Machine Learning · Computer Science 2026-05-14 Jiaming Li , Chenyu Zhu , Nanxi Yi , Youjun Bao , Li Sun , Quanying Lv , Xiang Fang , Daizong Liu , Jianjun Li , Kun He , Bowen Zhou , Zhiyuan Ma

Generative diffusion models (DM) have been extensively utilized in image super-resolution (ISR). Most of the existing methods adopt the denoising loss from DDPMs for model optimization. We posit that introducing reward feedback learning to…

Computer Vision and Pattern Recognition · Computer Science 2024-12-05 Xiaopeng Sun , Qinwei Lin , Yu Gao , Yujie Zhong , Chengjian Feng , Dengjie Li , Zheng Zhao , Jie Hu , Lin Ma

Recent work uses reinforcement learning (RL) to fine-tune text-to-image diffusion models, improving text-image alignment and sample quality. However, existing approaches introduce unnecessary complexity: they cache the full sampling…

Machine Learning · Computer Science 2025-07-02 Yanting Miao , William Loh , Pacal Poupart , Suraj Kothawade

In this paper, we tackle the challenging problem of delayed rewards in reinforcement learning (RL). While Proximal Policy Optimization (PPO) has emerged as a leading Policy Gradient method, its performance can degrade under delayed rewards.…

Language model (LM) post-training (or alignment) involves maximizing a reward function that is derived from preference annotations. Direct Preference Optimization (DPO) is a popular offline alignment method that trains a policy directly on…

Machine Learning · Computer Science 2025-03-04 Adam Fisch , Jacob Eisenstein , Vicky Zayats , Alekh Agarwal , Ahmad Beirami , Chirag Nagpal , Pete Shaw , Jonathan Berant

Large language models (LLMs) are fine-tuned using human comparison data with Reinforcement Learning from Human Feedback (RLHF) methods to make them better aligned with users' preferences. In contrast to LLMs, human preference learning has…

Computer Vision and Pattern Recognition · Computer Science 2023-11-23 Bram Wallace , Meihua Dang , Rafael Rafailov , Linqi Zhou , Aaron Lou , Senthil Purushwalkam , Stefano Ermon , Caiming Xiong , Shafiq Joty , Nikhil Naik

Reinforcement learning algorithms require a large amount of samples; this often limits their real-world applications on even simple tasks. Such a challenge is more outstanding in multi-agent tasks, as each step of operation is more costly…

Machine Learning · Computer Science 2022-09-05 Yali Du , Chengdong Ma , Yuchen Liu , Runji Lin , Hao Dong , Jun Wang , Yaodong Yang

Diffusion policies have achieved superior performance in imitation learning and offline reinforcement learning (RL) due to their rich expressiveness. However, the conventional diffusion training procedure requires samples from target…

Machine Learning · Computer Science 2025-07-01 Haitong Ma , Tianyi Chen , Kai Wang , Na Li , Bo Dai

Aligning large language models with human preferences has emerged as a critical focus in language modeling research. Yet, integrating preference learning into Text-to-Image (T2I) generative models is still relatively uncharted territory.…

Computer Vision and Pattern Recognition · Computer Science 2024-06-11 Yi Gu , Zhendong Wang , Yueqin Yin , Yujia Xie , Mingyuan Zhou

Text-to-image diffusion models deliver high-quality images, yet aligning them with human preferences remains challenging. We revisit diffusion-based Direct Preference Optimization (DPO) for these models and identify a critical pathology:…

Computer Vision and Pattern Recognition · Computer Science 2025-12-03 Minghao Fu , Guo-Hua Wang , Tianyu Cui , Qing-Guo Chen , Zhao Xu , Weihua Luo , Kaifu Zhang

Reinforcement learning from human feedback (RLHF) effectively promotes preference alignment of text-to-image (T2I) diffusion models. To improve computational efficiency, direct preference optimization (DPO), which avoids explicit reward…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Zhikai Li , Yue Zhao , Edward Zhongwei Zhang , Xuewen Liu , Jing Zhang , Qingyi Gu , Zhen Dong

Diffusion-based large language models offer a non-autoregressive alternative for text generation, but enabling them to perform complex reasoning remains challenging. Reinforcement learning has recently emerged as an effective post-training…

Artificial Intelligence · Computer Science 2026-04-14 Shaoan Xie , Lingjing Kong , Xiangchen Song , Xinshuai Dong , Guangyi Chen , Eric P. Xing , Kun Zhang

Recent advances in text-to-image (T2I) diffusion model fine-tuning leverage reinforcement learning (RL) to align generated images with learnable reward functions. The existing approaches reformulate denoising as a Markov decision process…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Xinyao Liao , Wei Wei , Xiaoye Qu , Yu Cheng

Offline reinforcement learning (RL) refers to the problem of learning policies entirely from a large batch of previously collected data. This problem setting offers the promise of utilizing such datasets to acquire policies without any…

Machine Learning · Computer Science 2020-11-24 Tianhe Yu , Garrett Thomas , Lantao Yu , Stefano Ermon , James Zou , Sergey Levine , Chelsea Finn , Tengyu Ma