将偏好对齐融入扩散模型，提升图像生成与编辑能力。
Preference Alignment on Diffusion Model: A Comprehensive Survey for Image Generation and Editing
- 系统梳理强化学习、直接偏好优化等对齐方法
- 展示在自动驾驶、医疗影像等场景的应用效果
- 首次综述该方向，适合研究者快速入门
将偏好对齐与扩散模型（DMs）结合，已成为提升图像生成与编辑能力的变革性方法。尽管该交叉领域对新手存在显著挑战，但系统性综述仍十分匮乏。本文全面调研了扩散模型在图像生成与编辑中的偏好对齐技术。首先，系统回顾了基于人类反馈的强化学习（RLHF）、直接偏好优化（DPO）等前沿优化技术，凸显其在对齐偏好与扩散模型中的关键作用；其次，深入探讨了偏好对齐在自动驾驶、医学影像、机器人等领域的应用；最后，全面分析了当前面临的挑战。据我们所知，这是首个聚焦扩散模型偏好对齐的综述，为该动态领域的发展提供洞见。
原文摘要 · Abstract (English)
The integration of preference alignment with diffusion models (DMs) has emerged as a transformative approach to enhance image generation and editing capabilities. Although integrating diffusion models with preference alignment strategies poses significant challenges for novices at this intersection, comprehensive and systematic reviews of this subject are still notably lacking. To bridge this gap, this paper extensively surveys preference alignment with diffusion models in image generation and editing. First, we systematically review cutting-edge optimization techniques such as reinforcement learning with human feedback (RLHF), direct preference optimization (DPO), and others, highlighting their pivotal role in aligning preferences with DMs. Then, we thoroughly explore the applications of aligning preferences with DMs in autonomous driving, medical imaging, robotics, and more. Finally, we comprehensively discuss the challenges of preference alignment with DMs. To our knowledge, this is the first survey centered on preference alignment with DMs, providing insights to drive future innovation in this dynamic area.
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。