AI RESEARCH
Multi-Fidelity Flow Matching: Cascaded Refinement of PDE Solutions
arXiv CS.LG
•
ArXi:2605.16118v1 Announce Type: new The source distribution in conditional flow matching is a design parameter that can be calibrated to data, not a default isotropic prior. We exploit this in Multi-Fidelity Flow Matching (MFFM), a cascade refinement framework for parametric PDE solutions: the source is calibrated to the empirical low-to-high-fidelity residual scale with local Gaussian-blur correlation, and the velocity network is conditioned on the low-fidelity solution.