系统梳理扩散模型对齐技术，解决生成内容偏离人类意图的问题
Alignment of Diffusion Models: Fundamentals, Challenges, and Future
- 从基础理论到技术方法，全面总结扩散模型对齐框架
- 提出多维度评估体系，涵盖偏好基准与生成质量验证
- 适合从事生成模型安全与可控性研究的工程师和学者
扩散模型已成为生成建模的主流范式，在多种应用中表现优异。然而，这些模型常与人类意图不符，生成不期望甚至有害的内容。受大语言模型对齐成功的启发，近期研究开始探索将扩散模型与人类期望和偏好对齐。本文系统综述了扩散模型对齐的研究进展，涵盖对齐的基础理论、技术方法、偏好基准及评估体系，并讨论当前挑战与未来方向。据我们所知，本工作是首个全面综述扩散模型对齐的论文，旨在帮助研究人员与工程师理解、实践并推进该领域发展。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。