English
Related papers

Related papers: Beyond Binary Preference: Aligning Diffusion Model…

200 papers

Direct Preference Optimization (DPO) is a method for enhancing model performance by directly optimizing for the preferences or rankings of outcomes, instead of traditional loss functions. This approach has proven effective in aligning Large…

Machine Learning · Computer Science 2024-09-18 Ruoyu Wang , Jiachen Sun , Shaowei Hua , Quan Fang

Direct alignment methods typically train large language models (LLMs) by contrasting the likelihoods of preferred and dispreferred responses. While effective at capturing relative preferences, these methods are widely observed to suppress…

Computation and Language · Computer Science 2025-12-04 Kaiyang Guo , Yinchuan Li , Zhitang Chen

Denoising diffusion probabilistic models (DDPMs) have been proven capable of synthesizing high-quality images with remarkable diversity when trained on large amounts of data. Typical diffusion models and modern large-scale conditional…

Computer Vision and Pattern Recognition · Computer Science 2024-01-17 Jingyuan Zhu , Huimin Ma , Jiansheng Chen , Jian Yuan

Direct preference optimization (DPO) is an effective technique to train language models to generate preferred over dispreferred responses. However, this binary "winner-takes-all" approach is suboptimal for vision-language models whose…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Ansel Blume , Burak Uzkent , Shalini Chaudhuri , Garin Kessler

Image restoration (IR) models are typically trained to recover high-quality images using L1 or LPIPS loss. To handle diverse unknown degradations, zero-shot IR methods have also been introduced. However, existing pre-trained and zero-shot…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Bingchen Li , Xin Li , Jiaqi Xu , Jiaming Guo , Wenbo Li , Renjing Pei , Zhibo Chen

Flow-based generative models, including diffusion models, excel at modeling continuous distributions in high-dimensional spaces. In this work, we introduce Flow Policy Optimization (FPO), a simple on-policy reinforcement learning algorithm…

Machine Learning · Computer Science 2025-08-04 David McAllister , Songwei Ge , Brent Yi , Chung Min Kim , Ethan Weber , Hongsuk Choi , Haiwen Feng , Angjoo Kanazawa

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

Diffusion models can be improved with additional guidance towards more effective representations of input. Indeed, prior empirical work has already shown that aligning internal representations of the diffusion model with those of…

Machine Learning · Computer Science 2025-10-14 Chenyu Wang , Cai Zhou , Sharut Gupta , Zongyu Lin , Stefanie Jegelka , Stephen Bates , Tommi Jaakkola

This study addresses the challenge of noise in training datasets for Direct Preference Optimization (DPO), a method for aligning Large Language Models (LLMs) with human preferences. We categorize noise into pointwise noise, which includes…

Machine Learning · Computer Science 2025-04-21 Junkang Wu , Yuexiang Xie , Zhengyi Yang , Jiancan Wu , Jiawei Chen , Jinyang Gao , Bolin Ding , Xiang Wang , Xiangnan He

Sequential decision-making is desired to align with human intents and exhibit versatility across various tasks. Previous methods formulate it as a conditional generation process, utilizing return-conditioned diffusion models to directly…

Machine Learning · Computer Science 2024-10-11 Xudong Yu , Chenjia Bai , Haoran He , Changhong Wang , Xuelong Li

Post-training alignment of large language models (LLMs) is a critical challenge, as not all tokens contribute equally to model performance. This paper introduces a selective alignment strategy that prioritizes high-impact tokens within…

Computation and Language · Computer Science 2025-07-11 Zhijin Dong

Foreground-conditioned inpainting, which aims at generating a harmonious background for a given foreground subject based on the text prompt, is an important subfield in controllable image generation. A common challenge in current methods,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-18 Qirui Li , Yizhe Tang , Ran Yi , Guangben Lu , Fangyuan Zou , Peng Shu , Huan Yu , Jie Jiang

Inference-time alignment provides an efficient alternative for aligning LLMs with humans. However, these approaches still face challenges, such as limited scalability due to policy-specific value functions and latency during the inference…

Computation and Language · Computer Science 2025-05-27 Ruizhe Chen , Wenhao Chai , Zhifei Yang , Xiaotian Zhang , Joey Tianyi Zhou , Tony Quek , Soujanya Poria , Zuozhu Liu

Diffusion Models have revolutionized the field of human motion generation by offering exceptional generation quality and fine-grained controllability through natural language conditioning. Their inherent stochasticity, that is the ability…

Computer Vision and Pattern Recognition · Computer Science 2024-05-08 Massimiliano Pappa , Luca Collorone , Giovanni Ficarra , Indro Spinelli , Fabio Galasso

Preference optimization offers a scalable supervision paradigm based on relative preference signals, yet prior attempts in medical image segmentation remain model-specific and rely on low-diversity prediction sampling. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2025-12-18 Yunseong Nam , Jiwon Jang , Dongkyu Won , Sang Hyun Park , Soopil Kim

Direct preference optimization (DPO) is a successful fine-tuning strategy for aligning large language models with human preferences without the need to train a reward model or employ reinforcement learning. DPO, as originally formulated,…

Computation and Language · Computer Science 2024-06-07 Afra Amini , Tim Vieira , Ryan Cotterell

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

Recent studies have demonstrated significant progress in aligning text-to-image diffusion models with human preference via Reinforcement Learning from Human Feedback. However, while existing methods achieve high scores on automated reward…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Chubin Chen , Sujie Hu , Jiashu Zhu , Meiqi Wu , Jintao Chen , Yanxun Li , Nisha Huang , Chengyu Fang , Jiahong Wu , Xiangxiang Chu , Xiu Li

Large language model reasoning is often treated as a monolithic capability, relying on binary preference supervision that fails to capture partial progress or fine-grained reasoning quality. We introduce Continuous Utility Direct Preference…

Diffusion-based planning, learning, and control methods present a promising branch of powerful and expressive decision-making solutions. Given the growing interest, such methods have undergone numerous refinements over the past years.…

Machine Learning · Computer Science 2025-02-19 Dom Huh , Prasant Mohapatra