English
Related papers

Related papers: Training Diffusion Models with Reinforcement Learn…

200 papers

Diffusion-based policies have gained growing popularity in solving a wide range of decision-making tasks due to their superior expressiveness and controllable generation during inference. However, effectively training large diffusion…

Diffusion models have achieved remarkable success in conditional image generation, yet their outputs often remain misaligned with human preferences. To address this, recent work has applied Direct Preference Optimization (DPO) to diffusion…

Computer Vision and Pattern Recognition · Computer Science 2025-11-12 Shaomeng Wang , He Wang , Xiaolu Wei , Longquan Dai , Jinhui Tang

Diffusion models excel at modeling complex data distributions, including those of images, proteins, and small molecules. However, in many cases, our goal is to model parts of the distribution that maximize certain properties: for example,…

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

Diffusion large language models (dLLMs) are promising alternatives to autoregressive large language models (AR-LLMs), as they potentially allow higher inference throughput. Reinforcement learning (RL) is a crucial component for dLLMs to…

Machine Learning · Computer Science 2026-02-24 Yuchen Zhu , Wei Guo , Jaemoo Choi , Petr Molodyk , Bo Yuan , Molei Tao , Yongxin Chen

Diffusion models have achieved remarkable success in text-to-image generation. However, their practical applications are hindered by the misalignment between generated images and corresponding text prompts. To tackle this issue,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-28 Zijing Hu , Fengda Zhang , Long Chen , Kun Kuang , Jiahui Li , Kaifeng Gao , Jun Xiao , Xin Wang , Wenwu Zhu

Reinforcement learning (RL) has emerged as a powerful tool for aligning diffusion models with human preferences, typically by optimizing a single reward function under a KL regularization constraint. In practice, however, human preferences…

Machine Learning · Computer Science 2026-04-17 Qi Zhang , Dawei Wang , Shaofeng Zou

Without using explicit reward, direct preference optimization (DPO) employs paired human preference data to fine-tune generative models, a method that has garnered considerable attention in large language models (LLMs). However, exploration…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Yunhong Lu , Qichao Wang , Hengyuan Cao , Xierui Wang , Xiaoyin Xu , Min Zhang

Few-step diffusion models enable efficient high-resolution image synthesis but struggle to align with specific downstream objectives due to limitations of existing reinforcement learning (RL) methods in low-step regimes with limited state…

Machine Learning · Computer Science 2026-03-02 Ziyi Zhang , Li Shen , Sen Zhang , Deheng Ye , Yong Luo , Miaojing Shi , Dongjing Shan , Bo Du , Dacheng Tao

Reinforcement Learning with Verifiable Rewards (RLVR) has achieved remarkable success in improving autoregressive models, especially in domains requiring correctness like mathematical reasoning and code generation. However, directly…

Machine Learning · Computer Science 2026-03-03 Chenxing Wei , Jiazhen Kang , Hong Wang , Jianqing Zhang , Hao Jiang , Xiaolong Xu , Ningyuan Sun , Ying He , F. Richard Yu , Yao Shu , Bo Jiang

Vision-language-action (VLA) models have shown strong generalization across tasks and embodiments; however, their reliance on large-scale human demonstrations limits their scalability owing to the cost and effort of manual data collection.…

Robotics · Computer Science 2025-09-30 Rushuai Yang , Hangxing Wei , Ran Zhang , Zhiyuan Feng , Xiaoyu Chen , Tong Li , Chuheng Zhang , Li Zhao , Jiang Bian , Xiu Su , Yi Chen

RLHF techniques like DPO can significantly improve the generation quality of text-to-image diffusion models. However, these methods optimize for a single reward that aligns model generation with population-level preferences, neglecting the…

Machine Learning · Computer Science 2025-01-14 Meihua Dang , Anikait Singh , Linqi Zhou , Stefano Ermon , Jiaming Song

Recent research has highlighted the powerful capabilities of imitation learning in robotics. Leveraging generative models, particularly diffusion models, these approaches offer notable advantages such as strong multi-task generalization,…

Robotics · Computer Science 2025-09-15 Xinyao Qin , Xiaoteng Ma , Yang Qi , Qihan Liu , Chuanyi Xue , Ning Gui , Qinyu Dong , Jun Yang , Bin Liang

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

Direct Preference Optimization (DPO) is successful for alignment in LLMs but still faces challenges in text-to-image generation. Existing studies are confined to denoising diffusion models while overlooking flow-matching, and suffer from an…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Kesong Li , Yixuan Xu , Kuo-kun Tseng , Weiyi Lu , Kan Liu , Tao Lan

Diffusion models produce high-fidelity speech but are inefficient for real-time use due to long denoising steps and challenges in modeling intonation and rhythm. To improve this, we propose Diffusion Loss-Guided Policy Optimization (DLPO),…

Sound · Computer Science 2025-08-06 Jingyi Chen , Ju Seung Byun , Micha Elsner , Pichao Wang , Andrew Perrault

Reinforcement learning from human feedback (RLHF) has proven effectiveness for aligning text-to-image (T2I) diffusion models with human preferences. Although Direct Preference Optimization (DPO) is widely adopted for its computational…

Computer Vision and Pattern Recognition · Computer Science 2025-10-03 Jiamu Bai , Xin Yu , Meilong Xu , Weitao Lu , Xin Pan , Kiwan Maeng , Daniel Kifer , Jian Wang , Yu Wang

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

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

Diffusion-based robot navigation policies trained on large-scale imitation learning datasets, can generate multi-modal trajectories directly from the robot's visual observations, bypassing the traditional localization-mapping-planning…

Robotics · Computer Science 2026-03-16 Junhe Sheng , Ruofei Bai , Kuan Xu , Ruimeng Liu , Jie Chen , Shenghai Yuan , Wei-Yun Yau , Lihua Xie