cs.LGNov 17, 2026

Correcting Flows with Marginal Matching

Authors: Meital Bojan, Nadav Bojan Sellam, Ev Zisselman, Aviv Tamar

Organizations: Technion – Israel Institute of Technology, Haifa, Israel.

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.

Figures & tables

Appendix figures & tables21 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. CorrFlow: Self-Correcting Flow Matching

    Oct 17, 2026Hangwei Zhang, Nathan Rouillé, Chuanxia ZhengFlow MatchingFlow-Based Generative Modeling

  2. Generative Modeling with Continuous Flows: Sample Complexity of Flow Matching

    Nov 1, 2026Mudit Gaur, Prashant Trivedi, Shuchin Aeron +3Flow MatchingFlow-Based Generative Modeling