A Quantitative Approximation Framework for Flow Distillation in Diffusion Models

Excerpt

arXiv:2606.03820v2 Announce Type: replace-cross Abstract: We develop a quantitative framework for diffusion distillation by viewing few step sampling as approximation through compositions of learned flow maps. For trajectory distillation of the probability flow ODE, we show that low noise multimodal regimes separate score approximability from dynamical stability: the score remains efficiently approximable, while small local errors may be strongly amplified by stiff flow dynamics. In a Gaussian m