Alignment of Diffusion Models: Fundamentals, Challenges, and Future
Liu, Buhua Shao, Shitong Li, Bao Bai, Lichen Xu, Zhiqiang Xiong, Haoyi Kwok, James T Helal, Sumi Xie, Zeke
Liu, Buhua
Shao, Shitong
Li, Bao
Bai, Lichen
Xu, Zhiqiang
Xiong, Haoyi
Kwok, James T
Helal, Sumi
Xie, Zeke
Supervisor
Department
Machine Learning
Embargo End Date
Type
Journal article
Date
License
http://creativecommons.org/licenses/by/4.0/
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Diffusion models have emerged as the leading paradigm in generative modeling, excelling in various applications. Despite their success, these models often misalign with human intentions and generate results with undesired properties or even harmful content. Inspired by the success and popularity of alignment in tuning large language models, recent studies have investigated aligning diffusion models with human expectations and preferences. This work mainly reviews alignment of diffusion models, covering advancements in fundamentals of alignment, alignment techniques of diffusion models, preference benchmarks, and evaluation for diffusion models. Moreover, we discuss key perspectives on current challenges and promising future directions on solving the remaining challenges in alignment of diffusion models. To the best of our knowledge, our work is the first comprehensive review paper for researchers and engineers to comprehend, practice, and research alignment of diffusion models.
Citation
B. Liu, S. Shao, B. Li, L. Bai, Z. Xu, H. Xiong , et al., "Alignment of Diffusion Models: Fundamentals, Challenges, and Future," ACM Computing Surveys, vol. 58, no. 9, pp. 1-37, 2026, https://doi.org/10.1145/3796982.
Source
ACM Computing Surveys
Conference
Keywords
46 Information and Computing Sciences, 4608 Human-Centred Computing
Subjects
Source
Publisher
Association for Computing Machinery