Search Results for author:
Found 15 papers, 11 papers with code
Improved motif-scaffolding with SE(3) flow matching
The first is motif amortization, in which FrameFlow is trained with the motif as input using a data augmentation strategy.
A framework for conditional diffusion modelling with applications in motif scaffolding for protein design
Many protein design applications, such as binder or enzyme design, require scaffolding a structural motif with high precision.
SE(3) Equivariant Augmented Coupling Flows
Coupling normalizing flows allow for fast sampling and density evaluation, making them the tool of choice for probabilistic modeling of physical systems.
Diffusion Models for Constrained Domains
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-image tasks.
SE(3) diffusion model with application to protein backbone generation
The design of novel protein structures remains a challenge in protein engineering for applications across biomedicine and chemistry.
Spectral Diffusion Processes
Score-based generative modelling (SGM) has proven to be a very effective method for modelling densities on finite-dimensional spaces.
Riemannian Diffusion Schrödinger Bridge
Our proposed method generalizes Diffusion Schr\"odinger Bridge introduced in \cite{debortoli2021neurips} to the non-Euclidean setting and extends Riemannian score-based models beyond the first time reversal.
Learning Instance-Specific Augmentations by Capturing Local Invariances
We introduce InstaAug, a method for automatically learning input-specific augmentations from data.
Riemannian Score-Based Generative Modelling
Score-based generative models (SGMs) are a powerful class of generative models that exhibit remarkable empirical performance.
On Incorporating Inductive Biases into VAEs
InteL-VAEs use an intermediary set of latent variables to control the stochasticity of the encoding process, before mapping these in turn to the latent representation using a parametric function that encapsulates our desired inductive bias(es).
On Contrastive Representations of Stochastic Processes
Learning representations of stochastic processes is an emerging problem in machine learning with applications from meta-learning to physical object models to time series.
Riemannian Continuous Normalizing Flows
Normalizing flows have shown great promise for modelling flexible probability distributions in a computationally tractable way.
Continuous Hierarchical Representations with Poincaré Variational Auto-Encoders
We therefore endow VAEs with a Poincar\'e ball model of hyperbolic geometry as a latent space and rigorously derive the necessary methods to work with two main Gaussian generalisations on that space.
Disentangling Disentanglement in Variational Autoencoders
We develop a generalisation of disentanglement in VAEs---decomposition of the latent representation---characterising it as the fulfilment of two factors: a) the latent encodings of the data having an appropriate level of overlap, and b) the aggregate encoding of the data conforming to a desired structure, represented through the prior.
Sampling and Inference for Beta Neutral-to-the-Left Models of Sparse Networks
Empirical evidence suggests that heavy-tailed degree distributions occurring in many real networks are well-approximated by power laws with exponents $\eta$ that may take values either less than and greater than two.
