AI RESEARCH
StAD: Stein Amortized Divergence for Fast Likelihoods with Diffusion and Flow
arXiv CS.LG
•
ArXi:2605.16486v1 Announce Type: cross Diffusion and flow-based models are ubiquitously used for generative modelling and density estimation. They admit a deterministic probability flow ordinary differential equation (PF-ODE), analogous to continuous normalizing flows (CNFs), which describes the transport of the probability mass.