# Score-of-Mixture Training: Training One-Step Generative Models Made Simple via Score Estimation of Mixture Distributions Source: [Score-of-Mixture Training: Training One-Step Generative Models Made Simple via Score Estimation of Mixture Distributions]() Collection index: [llms.txt]() Data updated: 2025-10-26T05:11:23.415Z Authors: Tejas Jayashankar, J. Jon Ryu, Gregory Wornell Published: 2025-02-13T18:57:20.000Z ## Abstract We propose Score-of-Mixture Training (SMT), a novel framework for training one-step generative models by minimizing a class of divergences called the $\\alpha$-skew Jensen--Shannon divergence. At its core, SMT estimates the score of mixture distributions between real and fake samples across multiple noise levels. Similar to consistency models, our approach supports both training from scratch (SMT) and distillation using a pretrained diffusion model, which we call Score-of-Mixture Distillation (SMD). It is simple to implement, requires minimal hyperparameter tuning, and ensures stable training. Experiments on CIFAR-10 and ImageNet 64x64 show that SMT/SMD are competitive with and can even outperform existing methods. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()