Faster Inference of Flow-Based Generative Models via Improved Data-Noise Coupling

• URL: http://arxiv.org/abs/2603.15279v1
• Date: Mon, 16 Mar 2026 13:42:28 GMT
• Title: Faster Inference of Flow-Based Generative Models via Improved Data-Noise Coupling
• Abstract summary: Conditional Flow Matching (CFM) is a simulation-free method for training continuous normalizing flows.<n>We introduce LOOM-CFM, a novel method to extend the scope of minibatch optimal transport (OT) by preserving and optimizing these assignments across minibatches over training time.<n>Our approach demonstrates consistent improvements in the sampling speed-quality trade-off across multiple datasets.
• Score: 69.7108839028336
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Conditional Flow Matching (CFM), a simulation-free method for training continuous normalizing flows, provides an efficient alternative to diffusion models for key tasks like image and video generation. The performance of CFM in solving these tasks depends on the way data is coupled with noise. A recent approach uses minibatch optimal transport (OT) to reassign noise-data pairs in each training step to streamline sampling trajectories and thus accelerate inference. However, its optimization is restricted to individual minibatches, limiting its effectiveness on large datasets. To address this shortcoming, we introduce LOOM-CFM (Looking Out Of Minibatch-CFM), a novel method to extend the scope of minibatch OT by preserving and optimizing these assignments across minibatches over training time. Our approach demonstrates consistent improvements in the sampling speed-quality trade-off across multiple datasets. LOOM-CFM also enhances distillation initialization and supports high-resolution synthesis in latent space training.

Related papers

• Path-Guided Flow Matching for Dataset Distillation [9.761850986508895]
  We propose the first flow matching-based framework for generative distillation, which enables fast deterministic synthesis by solving an ODE in a few steps.<n>We develop a continuous path-to-prototype guidance algorithm for ODE-consistent path control, which allows trajectories to reliably land on assigned prototypes.
  arXiv  Detail & Related papers  (2026-02-05T12:52:32Z)
• AlignFlow: Improving Flow-based Generative Models with Semi-Discrete Optimal Transport [32.58223362864546]
  Flow-based Generative Models (FGMs) transform noise into complex data distributions.<n>Existing OT-based methods estimate the OT plan using (mini-)batches of sampled noise and data points.<n>This paper introduces AlignFlow, a novel approach to enhance the training of FGMs by establishing an explicit, optimal alignment between noise distribution and data points.
  arXiv  Detail & Related papers  (2025-10-16T18:00:43Z)
• Weighted Conditional Flow Matching [26.88652399504886]
  Conditional flow matching (CFM) has emerged as a powerful framework for training continuous normalizing flows.<n>We propose weighted Conditional Flow Matching (W-CFM), a novel approach that modifies the classical CFM loss by weighting each training pair $(x, y)$ with a Gibbs kernel.
  arXiv  Detail & Related papers  (2025-07-29T22:42:51Z)
• Taming Flow Matching with Unbalanced Optimal Transport into Fast Pansharpening [10.23957420290553]
  We propose the Optimal Transport Flow Matching framework to achieve one-step, high-quality pansharpening.<n>The OTFM framework enables simulation-free training and single-step inference while maintaining strict adherence to pansharpening constraints.
  arXiv  Detail & Related papers  (2025-03-19T08:10:49Z)
• Over-the-Air Fair Federated Learning via Multi-Objective Optimization [52.295563400314094]
  We propose an over-the-air fair federated learning algorithm (OTA-FFL) to train fair FL models.<n>Experiments demonstrate the superiority of OTA-FFL in achieving fairness and robust performance.
  arXiv  Detail & Related papers  (2025-01-06T21:16:51Z)
• Local Flow Matching Generative Models [19.859984725284896]
  Flow Matching (FM) is a simulation-free method for learning a continuous and invertible flow to interpolate between two distributions.<n>We introduce a stepwise FM model called Local Flow Matching (LFM), which consecutively learns a sequence of FM sub-models.<n>We empirically demonstrate improved training efficiency and competitive generative performance of LFM compared to FM.
  arXiv  Detail & Related papers  (2024-10-03T14:53:10Z)
• Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization [87.21285093582446]
  Diffusion Generative Flow Samplers (DGFS) is a sampling-based framework where the learning process can be tractably broken down into short partial trajectory segments. Our method takes inspiration from the theory developed for generative flow networks (GFlowNets)
  arXiv  Detail & Related papers  (2023-10-04T09:39:05Z)
• Improved Distribution Matching for Dataset Condensation [91.55972945798531]
  We propose a novel dataset condensation method based on distribution matching. Our simple yet effective method outperforms most previous optimization-oriented methods with much fewer computational resources.
  arXiv  Detail & Related papers  (2023-07-19T04:07:33Z)
• Improving and generalizing flow-based generative models with minibatch optimal transport [90.01613198337833]
  We introduce the generalized conditional flow matching (CFM) technique for continuous normalizing flows (CNFs) CFM features a stable regression objective like that used to train the flow in diffusion models but enjoys the efficient inference of deterministic flow models. A variant of our objective is optimal transport CFM (OT-CFM), which creates simpler flows that are more stable to train and lead to faster inference.
  arXiv  Detail & Related papers  (2023-02-01T14:47:17Z)
• Stochastic Optimization with Laggard Data Pipelines [65.20044914532221]
  We show that "dataechoed" extensions of common optimization methods exhibit provable improvements over their synchronous counterparts. Specifically, we show that in convex optimization with minibatches, data echoing affords speedups on the curvature-dominated part of the convergence rate, while maintaining the optimal statistical rate.
  arXiv  Detail & Related papers  (2020-10-26T14:55:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.