Score: 0

Saving Foundation Flow-Matching Priors for Inverse Problems

Published: November 20, 2025 | arXiv ID: 2511.16520v1

By: Yuxiang Wan , Ryan Devera , Wenjie Zhang and more

Potential Business Impact:

Makes AI better at fixing blurry pictures.

Business Areas:
Funding Platform Financial Services, Lending and Investments

Foundation flow-matching (FM) models promise a universal prior for solving inverse problems (IPs), yet today they trail behind domain-specific or even untrained priors. How can we unlock their potential? We introduce FMPlug, a plug-in framework that redefines how foundation FMs are used in IPs. FMPlug combines an instance-guided, time-dependent warm-start strategy with a sharp Gaussianity regularization, adding problem-specific guidance while preserving the Gaussian structures. This leads to a significant performance boost across image restoration and scientific IPs. Our results point to a path for making foundation FM models practical, reusable priors for IP solving.

Country of Origin
πŸ‡ΊπŸ‡Έ United States

Page Count
17 pages

Category
Computer Science:
Machine Learning (CS)