扩散模型的偏好对齐：图像生成与编辑的综合综述
Preference Alignment on Diffusion Model: A Comprehensive Survey for Image Generation and Editing
AI总结：
本文针对扩散模型与偏好对齐交叉领域缺乏系统综述的问题，全面调研了相关优化技术（如RLHF、DPO）及其在图像生成与编辑中的应用，是该主题首篇综述，为未来创新提供见解。
摘要：
偏好对齐与扩散模型（DMs）的融合已成为增强图像生成和编辑能力的变革性方法。尽管将扩散模型与偏好对齐策略相结合对该交叉领域的新手构成重大挑战，但该主题的全面系统综述仍显著缺失。为填补这一空白，本文广泛调研了图像生成与编辑中扩散模型的偏好对齐。首先，我们系统回顾前沿优化技术，如基于人类反馈的强化学习（RLHF）、直接偏好优化（DPO）等，强调它们在使偏好与DMs对齐中的关键作用。然后，我们深入探讨偏好与DMs对齐在自动驾驶、医学成像、机器人等领域的应用。最后，我们全面讨论了扩散模型偏好对齐的挑战。据我们所知，这是首个聚焦扩散模型偏好对齐的综述，为推动该动态领域的未来创新提供见解。
英文摘要：
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.
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。
