The Unreasonable Effectiveness of Gaussian Score Approximation for Diffusion Models and its ApplicationsDec 1, 2024·Binxu Wang,John J Vastola· 0 min read PDF Cite CodeTypeJournal articlePublicationTransactions on Machine Learning Research (arXiv:2412.09726)Last updated on Dec 1, 2024Diffusion Science of AI AuthorsBinxu WangResearch Fellow ← Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models Jan 1, 2025Diverse capability and scaling of diffusion and auto-regressive models when learning abstract rules Nov 1, 2024 →
