Physics-Guided Generative Surrogates for Parametric Rarefied Flows with Neural-Field Auto-Decoders: A Pipeline-Level Study of Flow Matching and Diffusion

Yiming Qi, Guan Zhang, Xu Wang +2

We present a conditional latent generative framework for parametric rarefied flows that separates neural-field representation, latent transport, and frozen physics adaptation. Neur…