arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.07253cs.LGcs.CV
收藏

扩散模型对齐:基础、挑战与未来

Alignment of Diffusion Models: Fundamentals, Challenges, and Future

The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);Baidu Inc.(百度公司);The University of Bologna(博洛尼亚大学)

Buhua Liu, Shitong Shao, Bao Li, Lichen Bai, Zhiqiang Xu, Haoyi Xiong, James Kwok, Sumi Helal, Zeke Xie

AI总结:

本文综述了扩散模型对齐的基础、挑战及未来方向,探讨了对齐技术、评估方法及当前挑战的解决方案。

摘要:

扩散模型已成为生成建模的主导范式,在各种应用中表现出色。尽管取得成功,这些模型往往与人类意图不一致,并生成具有不希望性质或甚至有害内容的结果。受大语言模型调谐中对齐的成功和流行启发,近期研究开始探讨如何将扩散模型对齐于人类期望和偏好。本文主要回顾扩散模型的对齐,涵盖对齐基础的进展、扩散模型的对齐技术、偏好基准以及扩散模型的评估。此外,我们讨论了当前挑战的关键视角以及解决剩余挑战的有前途的未来方向。据我们所知,我们的工作是首个全面的综述论文,为研究人员和工程师理解、实践和研究扩散模型的对齐提供了指导。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑