On the universal structure in deterministic generative diffusion
Organizations: UC Berkeley · Zhejiang University · University at Buffalo
Abstract
Diffusion-based generative modeling has emerged as a general computational framework for simulating high-dimensional, structured data across various domains. Understanding its generative mechanisms is paramount for advancing model training and inference in a principled way. Here, we demonstrate that deterministic sampling trajectories share a universal geometric structure invariant to data modalities and diffusion model implementations. This structure can be largely explained by an exactly solvable model based on the optimal linear denoiser.
Figures & tables
Appendix figures & tables2 assets
Supplementary material from the paper’s appendix.
Appendix
Diffusion Models
Diffusion models learn to reverse gradual data corruption, enabling flexible generation, editing, forecasting, and inference.
See all 1,251 papers