Sampling from known probability distributions is a ubiquitous task in
co...
Applications of normalizing flows to the sampling of field configuration...
NeRF provides unparalleled fidelity of novel view synthesis: rendering a...
Recent applications of machine-learned normalizing flows to sampling in
...
This work presents gauge-equivariant architectures for flow-based sampli...
Recent results suggest that flow-based algorithms may provide efficient
...
We propose Continual Repeated Annealed Flow Transport Monte Carlo (CRAFT...
We are interested in the challenging problem of modelling densities on
R...
Algorithms based on normalizing flows are emerging as promising machine
...
We propose NeRF-VAE, a 3D scene generative model that incorporates geome...
Causal models can compactly and efficiently encode the data-generating
p...
A set is an unordered collection of unique elements–and yet many machine...
In reinforcement learning, we can learn a model of future observations a...
Inspired by recent work in attention models for image captioning and que...
Stochastic video prediction is usually framed as an extrapolation proble...
We propose a formulation of visual localization that does not require
co...
A neural network (NN) is a parameterised function that can be tuned via
...
Deep neural networks excel at function approximation, yet they are typic...
The slate recommendation problem aims to find the "optimal" ordering of ...
We consider the general problem of modeling temporal data with long-rang...
Recent progress in deep latent variable models has largely been driven b...