arXiv · 2611.23134
Correcting Flows with Marginal Matching
Abstract
Flow matching models, ODE-based generative models, generate samples by gradually morphing a simple source distribution into a target distribution. However, these models still face challenges in optimally balancing computational efficiency with generation fidelity. While predictor-corrector schemes have been proven to help address this issue in diffusion models effectively, their application to flow matching models remains under-explored. In this work we present a novel training-based predictor-corrector framework for flow matching, which exploits the fact that the ODE can be easily reversed. Our key idea, termed Marginal Matching, is to correct samples at a particular time step in the forward ODE towards a matching marginal distribution of the backward ODE. This scheme proves to reduce a bound on the distance between the data distribution and the learned distribution, motivating two different implementations for the correction function. We show that our proposed method improves sample quality on CIFAR-10 and ImageNet-64, with minimal overhead in computation time.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Meital Bojan, Nadav Bojan Sellam, Ev Zisselman, Aviv Tamar. 2026-11-17. Correcting Flows with Marginal Matching. https://searcharxiv.com/abs/2611.23134
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.