Alignment of Diffusion Models: Fundamentals, Challenges, and Future
ACM Computing Surveys · 31.07.2026 · 58 (9) · 1-37
DOI: 10.1145/3796982 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 10.03.2026. Verfasst von Buhua Liu und 8 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 263 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
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.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Liu, B., Shao, S., Li, B., Bai, L., Xu, Z., Xiong, H., Kwok, J. T., Helal, S., & Xie, Z. (2026). Alignment of Diffusion Models: Fundamentals, Challenges, and Future. ACM Computing Surveys, 58(9), 1-37. https://doi.org/10.1145/3796982
Vancouver
Liu B, Shao S, Li B, Bai L, Xu Z, Xiong H, et al. Alignment of Diffusion Models: Fundamentals, Challenges, and Future. ACM Computing Surveys. 2026;58(9):1-37. doi:10.1145/3796982
BibTeX
@article{Liu2026,
author = {Liu, Buhua and Shao, Shitong and Li, Bao and Bai, Lichen and Xu, Zhiqiang and Xiong, Haoyi and Kwok, James T. and Helal, Sumi and Xie, Zeke},
title = {Alignment of Diffusion Models: Fundamentals, Challenges, and Future},
journal = {ACM Computing Surveys},
year = {2026},
volume = {58},
number = {9},
pages = {1--37},
doi = {10.1145/3796982}
}
EUVIMED