Conservative Flows: A New Paradigm of Generative Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gal, Eshed, Siddiqui, Md Shahriar Rahim, Eliasof, Moshe, Haber, Eldad
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914542408171520
author Gal, Eshed
Siddiqui, Md Shahriar Rahim
Eliasof, Moshe
Haber, Eldad
author_facet Gal, Eshed
Siddiqui, Md Shahriar Rahim
Eliasof, Moshe
Haber, Eldad
contents Modern generative modeling is dominated by transport from a noise prior to data. We propose an alternative paradigm in which generation is performed by a discrete stochastic dynamics that leaves the data distribution invariant, initialized from data-supported states rather than from noise. The framework can utilize any pretrained flow model. We develop two probability-preserving sampling mechanisms, a corrected Langevin dynamics with a Metropolis adjustment and a predictor-corrector flow, that operate directly on existing checkpoints. We validate the framework on a synthetic Swiss-roll target, ImageNet-256 and Oxford Flowers-102, where our samplers consistently improve over the original generation procedures.
format Preprint
id arxiv_https___arxiv_org_abs_2605_06905
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Conservative Flows: A New Paradigm of Generative Models
Gal, Eshed
Siddiqui, Md Shahriar Rahim
Eliasof, Moshe
Haber, Eldad
Machine Learning
Modern generative modeling is dominated by transport from a noise prior to data. We propose an alternative paradigm in which generation is performed by a discrete stochastic dynamics that leaves the data distribution invariant, initialized from data-supported states rather than from noise. The framework can utilize any pretrained flow model. We develop two probability-preserving sampling mechanisms, a corrected Langevin dynamics with a Metropolis adjustment and a predictor-corrector flow, that operate directly on existing checkpoints. We validate the framework on a synthetic Swiss-roll target, ImageNet-256 and Oxford Flowers-102, where our samplers consistently improve over the original generation procedures.
title Conservative Flows: A New Paradigm of Generative Models
topic Machine Learning
url https://arxiv.org/abs/2605.06905