MintFlow：面向约束流匹配的最小轨迹干预

AI 摘要

论文提出 MintFlow，一种无需训练的约束采样框架，将约束满足建模为对预训练流轨迹的最小干预。它通过伴随方程得到闭式最小范数扰动，避免高维雅可比矩阵和迭代优化，并自适应选择干预时间。在图像逆问题、图像编辑和物理信息生成等任务上，MintFlow 在满足约束的同时比现有方法更好地保持预训练生成分布。

正文节选

MintFlow: Minimal Trajectory Intervention for Constrained Flow Matching Abstract Flow matching models excel at generative modeling, and many downstream applications require their samples to satisfy prescribed constraints, such as observed measurements and physical laws. However, existing constrained samplers often face a trade-off: enforcing constraints can substantially displace samples from the pretrained data distribution. To address this trade-off, we introduce MintFlow, a training-free cons

发布时间：2026-10-06 12:00

抓取时间：2026-10-05 12:04

来源机构：arXiv