An Introduction to Flow Matching

less than 1 minute read

Published:

Flow matching (FM) is a recent generative modelling paradigm which has rapidly been gaining popularity in the deep probabilistic ML community. Flow matching combines aspects from Continuous Normalising Flows (CNFs) and Diffusion Models (DMs), alleviating key issues both methods have. In this blogpost we’ll cover the main ideas and unique properties of FM models starting from the basics.



SEE BLOG POST HERE