<ul data-eligibleForWebStory="false"><li>Flow Matching (FM) is a simulation-free method for learning a continuous and invertible flow to interpolate between two distributions.</li><li>Local Flow Matching (LFM) is introduced as a stepwise FM model that learns a sequence of FM sub-models, each matching a diffusion process.</li><li>LFM enables the use of smaller models with faster training by consecutively matching distributions closer to each other.</li><li>Empirical demonstrations show improved training efficiency and competitive generative performance of LFM compared to FM on various datasets.</li></ul>

Local Flow Matching Generative Models

Discover more