English
Related papers

Related papers: Diffusion-NPO: Negative Preference Optimization fo…

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

Human visual preferences are inherently multi-dimensional, encompassing aesthetics, detail fidelity, and semantic alignment. However, existing datasets provide only single, holistic annotations, resulting in severe label noise: images that…

Computer Vision and Pattern Recognition · Computer Science 2026-04-29 Xinxin Liu , Ming Li , Zonglin Lyu , Yuzhang Shang , Chen Chen

Efficient text-to-image generation remains a challenging task due to the high computational costs associated with the multi-step sampling in diffusion models. Although distillation of pre-trained diffusion models has been successful in…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Jeeyung Kim , Ze Wang , Qiang Qiu

The class-conditional image generation based on diffusion models is renowned for generating high-quality and diverse images. However, most prior efforts focus on generating images for general categories, e.g., 1000 classes in ImageNet-1k. A…

Computer Vision and Pattern Recognition · Computer Science 2024-06-05 Ziying Pan , Kun Wang , Gang Li , Feihong He , Yongxuan Lai

Post-training of language models, either through reinforcement learning, preference optimization or supervised finetuning, tends to sharpen the output probability distribution and reduce the diversity of generated responses. This is…

Computation and Language · Computer Science 2025-05-23 Jack Lanchantin , Angelica Chen , Shehzaad Dhuliawala , Ping Yu , Jason Weston , Sainbayar Sukhbaatar , Ilia Kulikov

Diffusion Probabilistic Models (DPMs) are powerful generative models that have achieved unparalleled success in a number of generative tasks. In this work, we aim to build inductive biases into the training and sampling of diffusion models…

Machine Learning · Computer Science 2025-03-14 Thomas Jiralerspong , Berton Earnshaw , Jason Hartford , Yoshua Bengio , Luca Scimeca

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

Preference learning algorithms (e.g., RLHF and DPO) are frequently used to steer LLMs to produce generations that are more preferred by humans, but our understanding of their inner workings is still limited. In this work, we study the…

Machine Learning · Computer Science 2024-11-01 Angelica Chen , Sadhika Malladi , Lily H. Zhang , Xinyi Chen , Qiuyi Zhang , Rajesh Ranganath , Kyunghyun Cho

Preference optimization has made significant progress recently, with numerous methods developed to align language models with human preferences. This paper introduces $f$-divergence Preference Optimization ($f$-PO), a novel framework that…

Computation and Language · Computer Science 2025-02-18 Jiaqi Han , Mingjian Jiang , Yuxuan Song , Stefano Ermon , Minkai Xu

Modern preference alignment methods, such as DPO, rely on divergence regularization to a reference model for training stability-but this creates a fundamental problem we call "reference mismatch." In this paper, we investigate the negative…

Computer Vision and Pattern Recognition · Computer Science 2025-12-04 Jiwoo Hong , Sayak Paul , Noah Lee , Kashif Rasul , James Thorne , Jongheon Jeong

Direct Preference Optimization (DPO), which derives reward signals directly from pairwise preference data, has shown its effectiveness on aligning Large Language Models (LLMs) with human preferences. Despite its widespread use across…

Computation and Language · Computer Science 2024-04-09 Duanyu Feng , Bowen Qin , Chen Huang , Zheng Zhang , Wenqiang Lei

Recent advances in denoising diffusion models have enabled rapid generation of optimized structures for topology optimization. However, these models often rely on surrogate predictors to enforce physical constraints, which may fail to…

Machine Learning · Computer Science 2025-08-05 Euihyun Kim , Keun Park , Yeoneung Kim

Diffusion probabilistic models (DPMs) have become a popular approach to conditional generation, due to their promising results and support for cross-modal synthesis. A key desideratum in conditional synthesis is to achieve high…

Computer Vision and Pattern Recognition · Computer Science 2023-02-17 Ye Zhu , Yu Wu , Kyle Olszewski , Jian Ren , Sergey Tulyakov , Yan Yan

The ability to train high-performing reward models with few-shot data is critical for enhancing the efficiency and scalability of Reinforcement Learning from Human Feedback (RLHF). We propose a data augmentation and expansion framework that…

Machine Learning · Computer Science 2025-06-11 Yiyang Zhao , Huiyu Bai , Xuejiao Zhao

Preference optimization has emerged as an efficient alternative to online reinforcement learning from human feedback (RLHF) for aligning text-to-image diffusion models. However, existing methods largely reduce supervision to binary pairwise…

Machine Learning · Computer Science 2026-05-27 Austin Wang , Jiaqi Han , Stefano Ermon , Yisong Yue

In this paper, we make the first attempt to align diffusion models for image inpainting with human aesthetic standards via a reinforcement learning framework, significantly improving the quality and visual appeal of inpainted images.…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Kendong Liu , Zhiyu Zhu , Chuanhao Li , Hui Liu , Huanqiang Zeng , Junhui Hou

Cross-Domain Sequential Recommendation (CDSR) leverages user behaviors across domains to enhance recommendation quality. However, naive aggregation of sequential signals can introduce conflicting domain-specific preferences, leading to…

Information Retrieval · Computer Science 2025-09-12 Xiaoxin Ye , Chengkai Huang , Hongtao Huang , Lina Yao

Offline reinforcement learning (RL) aims to learn optimal policies from previously collected datasets. Recently, due to their powerful representational capabilities, diffusion models have shown significant potential as policy models for…

Machine Learning · Computer Science 2024-05-30 Tianle Zhang , Jiayi Guan , Lin Zhao , Yihang Li , Dongjiang Li , Zecui Zeng , Lei Sun , Yue Chen , Xuelong Wei , Lusong Li , Xiaodong He

Diffusion models for continuous data gained widespread adoption owing to their high quality generation and control mechanisms. However, controllable diffusion on discrete data faces challenges given that continuous guidance methods do not…

Large language models in the past have typically relied on some form of reinforcement learning with human feedback (RLHF) to better align model responses with human preferences. However, because of oft-observed instabilities when…

Computation and Language · Computer Science 2024-07-15 Xiangkun Hu , Tong He , David Wipf