MFFM chains residual-calibrated flow matching steps across fidelity levels, conditioning each on the low-fidelity input so that L deterministic network evaluations produce a fine-grid PDE solution.
International Conference on Learning Representations (ICLR) , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Cumulative flow maps unify few-step generative modeling for diffusion and flow models via cumulative transport and parameterization with minimal changes to time embeddings and objectives.
citing papers explorer
-
Multi-Fidelity Flow Matching: Cascaded Refinement of PDE Solutions
MFFM chains residual-calibrated flow matching steps across fidelity levels, conditioning each on the low-fidelity input so that L deterministic network evaluations produce a fine-grid PDE solution.
-
A Few-Step Generative Model on Cumulative Flow Maps
Cumulative flow maps unify few-step generative modeling for diffusion and flow models via cumulative transport and parameterization with minimal changes to time embeddings and objectives.