通过迭代优化控制策略，实现扩散模型的高效条件采样。
Iterative Importance Fine-tuning of Diffusion Models
- 基于路径重要性权重构建合成数据集，自监督学习最优控制
- 在图像分类、逆问题和文本生成中实现高精度条件采样
- 适合需要快速精准采样的生成模型应用开发者
扩散模型是生成建模的重要工具，广泛应用于成像与蛋白质设计等领域。在下游任务中高效从后验分布采样是一大挑战，可通过Doob的$h$-变换解决。本文提出一种自监督微调算法，通过学习最优控制实现近似条件采样。该方法利用基于路径的重要性权重重采样生成合成数据集，迭代优化控制策略。实验表明，该框架在类别条件采样、逆问题求解以及文本到图像扩散模型的奖励微调任务中均表现优异。
原文摘要 · Abstract (English)
Diffusion models are an important tool for generative modelling, serving as effective priors in applications such as imaging and protein design. A key challenge in applying diffusion models for downstream tasks is efficiently sampling from resulting posterior distributions, which can be addressed using Doob's $h$-transform. This work introduces a self-supervised algorithm for fine-tuning diffusion models by learning the optimal control, enabling amortised conditional sampling. Our method iteratively refines the control using a synthetic dataset resampled with path-based importance weights. We demonstrate the effectiveness of this framework on class-conditional sampling, inverse problems and reward fine-tuning for text-to-image 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。