Drift Flow Matching

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ma, Chenrui, Xiao, Xi, Zhao, Lin, Wang, Tianyang, Fioretto, Ferdinando, Shen, Yanning
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914574861598720
author Ma, Chenrui
Xiao, Xi
Zhao, Lin
Wang, Tianyang
Fioretto, Ferdinando
Shen, Yanning
author_facet Ma, Chenrui
Xiao, Xi
Zhao, Lin
Wang, Tianyang
Fioretto, Ferdinando
Shen, Yanning
contents Iterative generative models such as Flow Matching and Diffusion models have demonstrated strong test-time scaling behavior, where additional inference computation can improve generation quality. In contrast, Drift Models offer efficient one-step generation, but their direct generation paradigm limits such flexibility. In this work, we propose Drift Flow Matching (DFM), a framework that connects drifting generative modeling with flow-based iterative generation. DFM preserves the efficiency of direct transport maps while enabling generation to be refined through multiple inference steps when desired. This bridges the gap between one-step Drift Models and multi-step Flow Matching methods, and provides a novel generative paradigm that can adapt sampling computation to different quality--efficiency requirements. Extensive experiments across different tasks and datasets demonstrate the effectiveness and generality of the proposed framework.
format Preprint
id arxiv_https___arxiv_org_abs_2605_17244
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Drift Flow Matching
Ma, Chenrui
Xiao, Xi
Zhao, Lin
Wang, Tianyang
Fioretto, Ferdinando
Shen, Yanning
Machine Learning
Artificial Intelligence
Iterative generative models such as Flow Matching and Diffusion models have demonstrated strong test-time scaling behavior, where additional inference computation can improve generation quality. In contrast, Drift Models offer efficient one-step generation, but their direct generation paradigm limits such flexibility. In this work, we propose Drift Flow Matching (DFM), a framework that connects drifting generative modeling with flow-based iterative generation. DFM preserves the efficiency of direct transport maps while enabling generation to be refined through multiple inference steps when desired. This bridges the gap between one-step Drift Models and multi-step Flow Matching methods, and provides a novel generative paradigm that can adapt sampling computation to different quality--efficiency requirements. Extensive experiments across different tasks and datasets demonstrate the effectiveness and generality of the proposed framework.
title Drift Flow Matching
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2605.17244