71 citations · 198 across the 14 of their papers we have counts for
14 papers
On conditional diffusion models for PDE simulations
Aliaksandra Shysheya, Cristiana Diaconu, Federico Bergamin +4
Modelling partial differential equations (PDEs) is of crucial importance in science and engineering, and it includes tasks ranging from forecasting to inverse problems, such as dat…
SE(3) Equivariant Augmented Coupling Flows
Laurence I. Midgley, Vincent Stimper, Javier Antorán +3
Coupling normalizing flows allow for fast sampling and density evaluation, making them the tool of choice for probabilistic modeling of physical systems. However, the standard coup…
Geometric Neural Diffusion Processes
Emile Mathieu, Vincent Dutordoir, Michael J. Hutchinson +3
Denoising diffusion models have proven to be a flexible and effective paradigm for generative modelling. Their recent extension to infinite dimensional Euclidean spaces has allowed…
Metropolis Sampling for Constrained Diffusion Models
Nic Fishman, Leo Klarner, Emile Mathieu +2
Denoising diffusion models have recently emerged as the predominant paradigm for generative modelling on image domains. In addition, their extension to Riemannian manifolds has fac…
Diffusion Models for Constrained Domains
Nic Fishman, Leo Klarner, Valentin De Bortoli +2
Denoising diffusion models are a novel class of generative algorithms that achieve state-of-the-art performance across a range of domains, including image generation and text-to-im…
SE(3) diffusion model with application to protein backbone generation
Jason Yim, Brian L. Trippe, Valentin De Bortoli +4
The design of novel protein structures remains a challenge in protein engineering for applications across biomedicine and chemistry. In this line of work, a diffusion model over ri…
Spectral Diffusion Processes
Angus Phillips, Thomas Seror, Michael Hutchinson +3
Diffusion models have proven to be a flexible and effective framework for modelling probability distributions on finite-dimensional spaces. However, many physical modelling problem…
Riemannian Diffusion Schrödinger Bridge
James Thornton, Michael Hutchinson, Emile Mathieu +3
Score-based generative models exhibit state of the art performance on density estimation and generative modeling tasks. These models typically assume that the data geometry is flat…
Learning Instance-Specific Augmentations by Capturing Local Invariances
Ning Miao, Tom Rainforth, Emile Mathieu +4
We introduce InstaAug, a method for automatically learning input-specific augmentations from data. Previous methods for learning augmentations have typically assumed independence b…
Riemannian Score-Based Generative Modelling
Valentin De Bortoli, Emile Mathieu, Michael Hutchinson +3
Score-based generative models (SGMs) are a powerful class of generative models that exhibit remarkable empirical performance. Score-based generative modelling (SGM) consists of a `…
On Incorporating Inductive Biases into VAEs
Ning Miao, Emile Mathieu, N. Siddharth +2
We explain why directly changing the prior can be a surprisingly ineffective mechanism for incorporating inductive biases into VAEs, and introduce a simple and effective alternativ…
On Contrastive Representations of Stochastic Processes
Emile Mathieu, Adam Foster, Yee Whye Teh
Learning representations of stochastic processes is an emerging problem in machine learning with applications from meta-learning to physical object models to time series. Typical m…
Riemannian Continuous Normalizing Flows
Emile Mathieu, Maximilian Nickel
Normalizing flows have shown great promise for modelling flexible probability distributions in a computationally tractable way. However, whilst data is often naturally described on…
Continuous Hierarchical Representations with Poincaré Variational Auto-Encoders
Emile Mathieu, Charline Le Lan, Chris J. Maddison +2
The variational auto-encoder (VAE) is a popular method for learning a generative model and embeddings of the data. Many real datasets are hierarchically structured. However, tradit…