Saved in:
Bibliographic Details
Main Author: Ma, Chenrui
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.15689
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910055112114176
author Ma, Chenrui
author_facet Ma, Chenrui
contents Mainstream flow matching methods typically focus on learning the local velocity field, which inherently requires multiple integration steps during generation. In contrast, Mean Velocity Flow models establish a relationship between the local velocity field and the global mean velocity, enabling the latter to be learned through a mathematically grounded formulation and allowing generation to be transferred to arbitrary future time points. In this work, we propose a new paradigm that directly learns the transition flow. As a global quantity, the transition flow naturally supports generation in a single step or at arbitrary time points. Furthermore, we demonstrate the connection between our approach and Mean Velocity Flow, establishing a unified theoretical perspective. Extensive experiments validate the effectiveness of our method and support our theoretical claims.
format Preprint
id arxiv_https___arxiv_org_abs_2603_15689
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Transition Flow Matching
Ma, Chenrui
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Mainstream flow matching methods typically focus on learning the local velocity field, which inherently requires multiple integration steps during generation. In contrast, Mean Velocity Flow models establish a relationship between the local velocity field and the global mean velocity, enabling the latter to be learned through a mathematically grounded formulation and allowing generation to be transferred to arbitrary future time points. In this work, we propose a new paradigm that directly learns the transition flow. As a global quantity, the transition flow naturally supports generation in a single step or at arbitrary time points. Furthermore, we demonstrate the connection between our approach and Mean Velocity Flow, establishing a unified theoretical perspective. Extensive experiments validate the effectiveness of our method and support our theoretical claims.
title Transition Flow Matching
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.15689