English
Related papers

Related papers: Rethinking Preference Alignment for Diffusion Mode…

200 papers

Diffusion models have achieved remarkable success in sequential decision-making by leveraging the highly expressive model capabilities in policy learning. A central problem for learning diffusion policies is to align the policy output with…

Machine Learning · Computer Science 2024-12-17 Zhao Shan , Chenyou Fan , Shuang Qiu , Jiyuan Shi , Chenjia Bai

Using reinforcement learning with human feedback (RLHF) has shown significant promise in fine-tuning diffusion models. Previous methods start by training a reward model that aligns with human preferences, then leverage RL techniques to…

Machine Learning · Computer Science 2024-03-26 Kai Yang , Jian Tao , Jiafei Lyu , Chunjiang Ge , Jiaxin Chen , Qimai Li , Weihan Shen , Xiaolong Zhu , Xiu Li

Efficiently aligning large-scale video diffusion models with human intent requires a scalable and trajectory-aware pathway that bridges the inherent discrepancy between training noise distributions and practical inference trajectories.…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Jingyuan Zhu , Biaolong Chen , Le Zhang , Aixi Zhang , Hao Jiang , Pipei Huang

For aligning large language models (LLMs), prior work has leveraged reinforcement learning via human feedback (RLHF) or variations of direct preference optimization (DPO). While DPO offers a simpler framework based on maximum likelihood…

Artificial Intelligence · Computer Science 2025-05-27 Anirudhan Badrinath , Prabhat Agarwal , Jiajing Xu

Classifier-Free Guidance (CFG) is a widely used technique for improving conditional diffusion models by linearly combining the outputs of conditional and unconditional denoisers. While CFG enhances visual quality and improves alignment with…

Machine Learning · Computer Science 2025-05-28 Badr Moufad , Yazid Janati , Alain Durmus , Ahmed Ghorbel , Eric Moulines , Jimmy Olsson

In recent years, the field of image generation has witnessed significant advancements, particularly in fine-tuning methods that align models with universal human preferences. This paper explores the critical role of preference data in the…

Computer Vision and Pattern Recognition · Computer Science 2025-03-24 Lingfan Zhang , Chen Liu , Chengming Xu , Kai Hu , Donghao Luo , Chengjie Wang , Yanwei Fu , Yuan Yao

We introduce segmentation-free guidance, a novel method designed for text-to-image diffusion models like Stable Diffusion. Our method does not require retraining of the diffusion model. At no additional compute cost, it uses the diffusion…

Computer Vision and Pattern Recognition · Computer Science 2024-07-09 Kambiz Azarian , Debasmit Das , Qiqi Hou , Fatih Porikli

Personalizing diffusion models to specific users or concepts remains challenging, particularly when only a few reference images are available. Existing methods such as DreamBooth and Textual Inversion often overfit to limited data, causing…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 JungWoo Chae , Jiyoon Kim , Sangheum Hwang

Aligning the output of Large Language Models (LLMs) with human preferences (e.g., by means of reinforcement learning with human feedback, or RLHF) is essential for ensuring their effectiveness in real-world scenarios. Despite significant…

Artificial Intelligence · Computer Science 2024-10-23 Pietro Bernardelle , Gianluca Demartini

Direct Preference Optimization (DPO) has emerged as a de-facto approach for aligning language models with human preferences. Recent work has shown DPO's effectiveness relies on training data quality. In particular, clear quality differences…

Machine Learning · Computer Science 2025-01-28 Nirav Diwan , Tolga Ergen , Dongsub Shim , Honglak Lee

Direct Preference Optimization (DPO) aligns text-to-image (T2I) generation models with human preferences using pairwise preference data. Although substantial resources are expended in collecting and labeling datasets, a critical aspect is…

Computer Vision and Pattern Recognition · Computer Science 2025-06-09 Yunhong Lu , Qichao Wang , Hengyuan Cao , Xiaoyin Xu , Min Zhang

Guidance serves as a key concept in diffusion models, yet its effectiveness is often limited by the need for extra data annotation or classifier pretraining. That is why guidance was harnessed from self-supervised learning backbones, like…

Computer Vision and Pattern Recognition · Computer Science 2023-12-15 Vincent Tao Hu , Yunlu Chen , Mathilde Caron , Yuki M. Asano , Cees G. M. Snoek , Bjorn Ommer

Fine-tuning text-to-image diffusion models with human feedback is an effective method for aligning model behavior with human intentions. However, this alignment process often suffers from slow convergence due to the large size and noise…

Machine Learning · Computer Science 2025-04-03 Yongjin Yang , Sihyeon Kim , Hojung Jung , Sangmin Bae , SangMook Kim , Se-Young Yun , Kimin Lee

Aligning text-to-video diffusion models with human preferences is crucial for generating high-quality videos. Existing Direct Preference Otimization (DPO) methods rely on multi-sample ranking and task-specific critic models, which is…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Zitong Huang , Kaidong Zhang , Yukang Ding , Chao Gao , Rui Ding , Ying Chen , Wangmeng Zuo

Denoising diffusion models excel at generating high-quality images conditioned on text prompts, yet their effectiveness heavily relies on careful guidance during the sampling process. Classifier-Free Guidance (CFG) provides a widely used…

Graphics · Computer Science 2026-03-04 Shai Yehezkel , Omer Dahary , Andrey Voynov , Daniel Cohen-Or

While reinforcement learning methods such as Group Relative Preference Optimization (GRPO) have significantly enhanced Large Language Models, adapting them to diffusion models remains challenging. In particular, GRPO demands a stochastic…

Machine Learning · Computer Science 2025-10-10 Yihong Luo , Tianyang Hu , Jing Tang

We investigate the theoretical foundations of classifier-free guidance (CFG). CFG is the dominant method of conditional sampling for text-to-image diffusion models, yet unlike other aspects of diffusion, it remains on shaky theoretical…

Machine Learning · Computer Science 2024-08-26 Arwen Bradley , Preetum Nakkiran

Classifier-Free Guidance (CFG) is a widely adopted technique in diffusion and flow-based generative models, enabling high-quality conditional generation. A key theoretical challenge is characterizing the distribution induced by CFG,…

Machine Learning · Computer Science 2025-05-23 Krunoslav Lehman Pavasovic , Jakob Verbeek , Giulio Biroli , Marc Mezard

Diffusion models often exhibit inconsistent sample quality due to stochastic variations inherent in their sampling trajectories. Although training-based fine-tuning (e.g. DDPO [1]) and inference-time alignment techniques[2] aim to improve…

Computer Vision and Pattern Recognition · Computer Science 2025-05-30 Sixian Wang , Zhiwei Tang , Tsung-Hui Chang

Image generation using diffusion models have demonstrated outstanding learning capabilities, effectively capturing the full distribution of the training dataset. They are known to generate wide variations in sampled images, albeit with a…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Rahul Shenoy , Zhihong Pan , Kaushik Balakrishnan , Qisen Cheng , Yongmoon Jeon , Heejune Yang , Jaewon Kim