AI RESEARCH
ODE-free Neural Flow Matching for One-Step Generative Modeling
arXiv CS.LG
•
ArXi:2604.06413v1 Announce Type: new Diffusion and flow matching models generate samples by learning time-dependent vector fields whose integration transports noise to data, requiring tens to hundreds of network evaluations at inference. We instead learn the transport map directly. We propose Optimal Transport Neural Flow Matching (OT-NFM), an ODE-free generative framework that parameterizes the flow map with neural flows, enabling true one-step generation with a single forward pass. We show that naive flow-map.