arXivImage AI
MGFlow: Unifying Distributional Training for High-Quality One-Step Visual Generation
統一分佈訓練框架 MGFlow：實現高品質單步視覺生成
This paper presents a unified theoretical framework for distributional training and introduces MGFlow, which uses Gaussian mixtures and Wasserstein gradient flows to achieve state-of-the-art one-step visual generation.
2 min read