no code implementations • 28 May 2024 • Gefan Yang, Elizabeth Louise Baker, Michael L. Severinsen, Christy Anna Hipsley, Stefan Sommer
However, simulating the diffusion bridge for natural data can be challenging due to both the intractability of the drift term and continuous representations of the data.
no code implementations • 2 Feb 2024 • Elizabeth Louise Baker, Gefan Yang, Michael L. Severinsen, Christy Anna Hipsley, Stefan Sommer
Generative diffusion models and many stochastic models in science and engineering naturally live in infinite dimensions before discretisation.
no code implementations • 27 Jan 2023 • Gefan Yang, Stefan Sommer
We propose a novel denoising diffusion generative model for predicting nonlinear fluid fields named FluidDiff.