#machine learning
Aug 2025
Sig-DEG for Distillation: Making Diffusion Models Faster and Lighter
Sig-DEG (Signature-based Differential Equation Generator), a generator for distilling pre-trained diffusion models, combines partial signatures that summarize Brownian motion over subintervals with a recurrent structure to approximate stochastic differential equation solutions to achieve universality.
Wen-Hang Ge, Lei Jiang, Ling-Yi Yang et al.
· arXiv.org · 4 citations