Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Multi-Fidelity Flow Matching: Cascaded Refinement of PDE Solutions

About

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. Conditioning makes the residual refinement problem substantially easier than unconditional field generation, while residual-calibrated source noise improves the flow-matching training geometry. A multi-resolution cascade applies the same construction independently between adjacent fidelities. After level-wise flow-matching pretraining, we fine-tune the composed cascade end-to-end with a deterministic one-step rollout, which makes one velocity evaluation per cascade level the optimized operating point at inference. The result is a learned analog of multigrid refinement that reaches the finest grid in $L$ deterministic network evaluations per query. We validate MFFM on eight benchmarks: two super-resolution problems and six spatiotemporal forecasting tasks from PDEBench, The Well, and the FNO Navier--Stokes dataset.

Sipeng Chen, Junliang Liu, Hewei Tang, Shibo Li• 2026

Related benchmarks

TaskDatasetResultRank
Spatial super-resolutionBurgers spatial super-resolution (test)
NRMSE2.488
9
Spatio-temporal forecastingDiffusion-Reaction (test)
NRMSE0.2509
9
Spatiotemporal forecastingShallow Water (SW) (test)
NRMSE0.0048
9
Spatiotemporal forecastingShear-T (test)
NRMSE22.53
9
Spatiotemporal forecastingShear-P (test)
NRMSE0.2671
9
Spatiotemporal forecastingActive Matter (AM) (test)
NRMSE0.3162
9
Spatiotemporal forecastingNavier-Stokes (NS) (test)
NRMSE0.0478
9
Spatial super-resolutionDarcy spatial super-resolution (test)
NRMSE0.062
9
Showing 8 of 8 rows

Other info

Follow for update