← 返回论文检索
ICLR 2025Blog Track PosterAccept

Diffusion Models and Gaussian Flow Matching: Two Sides of the Same Coin

Ruiqi Gao, Emiel Hoogeboom, Jonathan Heek, Valentin De Bortoli, Kevin Murphy, Tim Salimans

Google · Google Brain · Google DeepMind

PDF 由论文原始站点提供,PaperCompass 不保存论文文件。

摘要

Flow matching and diffusion models are two popular frameworks in generative modeling. Despite seeming similar, there is some confusion in the community about their exact connection. In this post we aim to clear up this confusion and show that diffusion models and Gaussian flow matching are the same -- Different model specifications lead to different noise schedules and loss weightings but correspond to the same generative model. That's great news, it means that you can use the two frameworks interchangeably.