English
Related papers

Related papers: Forward KL Regularized Preference Optimization for…

200 papers

Online reinforcement learning (RL) has been central to post-training language models, but its extension to diffusion models remains challenging due to intractable likelihoods. Recent works discretize the reverse sampling process to enable…

Machine Learning · Computer Science 2026-02-17 Kaiwen Zheng , Huayu Chen , Haotian Ye , Haoxiang Wang , Qinsheng Zhang , Kai Jiang , Hang Su , Stefano Ermon , Jun Zhu , Ming-Yu Liu

Preference-based reinforcement learning (PbRL) is an approach that enables RL agents to learn from preference, which is particularly useful when formulating a reward function is challenging. Existing PbRL methods generally involve a…

Machine Learning · Computer Science 2023-10-30 Gaon An , Junhyeok Lee , Xingdong Zuo , Norio Kosaka , Kyung-Min Kim , Hyun Oh Song

Offline reinforcement learning (RL) aims to learn optimal policies from offline datasets, where the parameterization of policies is crucial but often overlooked. Recently, Diffsuion-QL significantly boosts the performance of offline RL by…

Machine Learning · Computer Science 2023-10-27 Bingyi Kang , Xiao Ma , Chao Du , Tianyu Pang , Shuicheng Yan

Diffusion models are powerful generative models that allow for precise control over the characteristics of the generated samples. While these diffusion models trained on large datasets have achieved success, there is often a need to…

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

Generative models, particularly diffusion models, have achieved remarkable success in density estimation for multimodal data, drawing significant interest from the reinforcement learning (RL) community, especially in policy modeling in…

Machine Learning · Computer Science 2024-12-03 Jinouwen Zhang , Rongkun Xue , Yazhe Niu , Yun Chen , Jing Yang , Hongsheng Li , Yu Liu

Offline reinforcement learning has received extensive attention from scholars because it avoids the interaction between the agent and the environment by learning a policy through a static dataset. However, general reinforcement learning…

Machine Learning · Computer Science 2026-02-12 Yi Shen , Hanyan Huang

Diffusion and flow models achieve State-Of-The-Art (SOTA) generative performance, yet many practically important behaviors such as fine-grained prompt fidelity, compositional correctness, and text rendering are weakly specified by score or…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Yuanzhi Zhu , Xi Wang , Stéphane Lathuilière , Vicky Kalogeiton

The complexity of designing reward functions has been a major obstacle to the wide application of deep reinforcement learning (RL) techniques. Describing an agent's desired behaviors and properties can be difficult, even for experts. A new…

Machine Learning · Computer Science 2024-05-09 Wanqi Xue , Bo An , Shuicheng Yan , Zhongwen Xu

Preference alignment in Large Language Models (LLMs) has significantly improved their ability to adhere to human instructions and intentions. However, existing direct alignment algorithms primarily focus on relative preferences and often…

Machine Learning · Computer Science 2025-05-13 Shenao Zhang , Zhihan Liu , Boyi Liu , Yufeng Zhang , Yingxiang Yang , Yongfei Liu , Liyu Chen , Tao Sun , Zhaoran Wang

Preference learning has garnered extensive attention as an effective technique for aligning diffusion models with human preferences in visual generation. However, existing alignment approaches such as Diffusion-DPO suffer from two…

Machine Learning · Computer Science 2026-05-19 Xiaomeng Yang , Mengping Yang , Junyan Wang , Zhijian Zhou , Zhiyu Tan , Hao Li

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

We address the problem of making a pre-trained reinforcement learning (RL) policy safety-aware by incorporating cost constraints without retraining it from scratch. While costs could be numerically encoded, we assume a more general setting…

Machine Learning · Computer Science 2026-05-21 Richa Verma , Bavish Kulur , Sanjay Chawla , Balaraman Ravindran

Reinforcement Learning (RL) has emerged as a central paradigm for advancing Large Language Models (LLMs), where pre-training and RL post-training share the same log-likelihood formulation. In contrast, recent RL approaches for diffusion…

Machine Learning · Computer Science 2025-09-30 Shuchen Xue , Chongjian Ge , Shilong Zhang , Yichen Li , Zhi-Ming Ma

Learning from preference labels plays a crucial role in fine-tuning large language models. There are several distinct approaches for preference fine-tuning, including supervised learning, on-policy reinforcement learning (RL), and…

Diffusion models have been successfully applied in areas such as image, video, and audio generation. Recent works show their promise for sequential decision-making and dexterous manipulation, leveraging their ability to model complex action…

Robotics · Computer Science 2026-03-17 Maria Makarova , Qian Liu , Dzmitry Tsetserukou

This paper studies the alignment process of generative models with Reinforcement Learning from Human Feedback (RLHF). We first identify the primary challenges of existing popular methods like offline PPO and offline DPO as lacking in…

Machine Learning · Computer Science 2024-05-02 Wei Xiong , Hanze Dong , Chenlu Ye , Ziqi Wang , Han Zhong , Heng Ji , Nan Jiang , Tong Zhang

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

The alignment of language models with human preferences is vital for their application in real-world tasks. The problem is formulated as optimizing the model's policy to maximize the expected reward that reflects human preferences with…

Computation and Language · Computer Science 2024-06-06 Haozhe Ji , Cheng Lu , Yilin Niu , Pei Ke , Hongning Wang , Jun Zhu , Jie Tang , Minlie Huang

Discrete diffusion models have demonstrated great promise in modeling various sequence data, ranging from human language to biological sequences. Inspired by the success of RL in language models, there is growing interest in further…

Machine Learning · Computer Science 2026-02-03 Jiaqi Han , Austin Wang , Minkai Xu , Wenda Chu , Meihua Dang , Haotian Ye , Huayu Chen , Yisong Yue , Stefano Ermon