Skip to content
Preprint

Energy-Guided Flow Matching

Aug 2026 · 0 citations · 31 references
Computer Science

TL;DR

Energy-Guided Flow Matching is introduced that explicitly models a coarse-to-fine generative trajectory by moving endpoint that evolves smoothly from low-frequency image to clean image and requires no adaptation of the backbone and training data.

Abstract

Pixel-space generative models bypass lossy latent compression, yet necessitate joint learning of global structure and fine-grained details in a high-dimensional space. Standard flow matching interpolates noise toward a fixed clean-image endpoint, leaving the spectral evolution to be learned implicitly. In this paper, we introduce Energy-Guided Flow Matching(EG-FM) that explicitly models a coarse-to-fine generative trajectory by moving endpoint. Specifically, EG-FM replaces the fixed endpoint with a heat-kernel-filtered endpoint that evolves smoothly from low-frequency image to clean image. The fraction of high-frequency signal in moving endpoint is released by an image-specific energy-guided scheduling, leading to the re-targeting of velocity in flow matching. Our framework requires no adaptation of the backbone and training data, bringing negligible cost on the training and inference stages. In our experiment, EG-FM consistently achieves lower FID on the ImageNet class-conditional image generation task at $256 \times 256$ with fewer epochs, reaching an FID of 1.55 at 200 epochs and 1.45 at 600 epochs. We continue training the generation task on the setting of $512 \times 512$ resolution, yielding a FID of 1.58 after only 40 high-resolution adaptation epochs. Furthermore, we transfer EG-FM on text-to-image generation and achieve 0.85 on GenEval score and 83.9 on DPG-Bench. Code is available at https://github.com/ysng123/EG-FM.

View source

Similar papers

Preprint Jul 2026

RFMSR: Residual Flow Matching for Image Super-Resolution

Residual Flow Matching for Image Super-Resolution (RFMSR) is proposed, a vision-only framework that centers the source distribution at the LQ latent, reducing transport distance and preserving structural priors throughout the flow trajectory.

Shuwei Huang, Tianyao Luo, Jicheng Liu et al. · 1 citation
Preprint Jul 2026

Projected Energy Matching for Generative 3D Priors

This work proposes Projected Energy Matching, a scalable framework that resolves structural and computational bottlenecks in energy matching, and introduces Helmholtz Distillation, a structural relaxation that leverages a Hutchinson trace estimator to explicitly absorb rotational noise into an auxiliary residual network.

Daniel Barco, M. Balcerak, Suprosanna Shit et al. · 0 citations
Preprint Aug 2026

Rethinking Pixel Mean Flows via Interval Denoiser

The Interval Denoiser, a theoretically rigorous framework for latent-free generation, derived directly from the flow matching ODE, establishes an exact analytical mapping for intermediate trajectory states and is shown to reside on a low-dimensional manifold across any time interval.

A.M. Zaytsev, Dmitry Baranchuk, Alexander Korotin et al. · 0 citations
Preprint Jul 2026

Perceptual Flow Matching for Few-Step Generative Modeling

We propose Perceptual Flow Matching (PFM), a simple yet effective framework for few-step generation in flow-matching models. Rather than performing velocity regression in the conventional VAE latent space, PFM supervises flow matching in a perceptual feature space using pretrained perceptual models. This simple change substantially improves the few-step generation capability of flow-matching models, reducing the number of sampling steps from 35-50 to 4-8 while preserving generation quality. Unlike existing acceleration and distillation approaches, PFM requires neither teacher models nor auxiliary score networks and can be integrated into standard flow-matching training pipelines with minimal modifications. Extensive experiments on image generation, video generation, and image editing tasks demonstrate that PFM consistently produces high-quality results while producing fewer artifacts than existing distillation-based methods. We further show that perceptual supervision shifts the regression minimizer from mean-seeking to mode-seeking, biasing predictions toward on-manifold modes that remain accurate under coarse few-step integration. Our results reveal that standard flow-matching training can naturally yield high-quality few-step generators when supervised in an appropriate representation space. We hope this insight inspires future research into representation-aware objectives for efficient generative modeling.

Chuyang Zhao, Yifei Song, Hongfa Wang et al. · 1 citation
#machine learning Preprint Aug 2026

Composing Flow-Matching Energies with Known Physics: Generation, OOD Detection, and Inversion on PDE Fields

It is shown in this work that flow matching models with a potential-induced velocity yield an explicit scalar energy at all transport times, whose gradient is exactly the converted learned score and which recovers the marginal negative log-density at the population optimum.

Yixuan Sun, A. Samaddar, Sandeep Madireddy · 0 citations