Variational autoencoders (VAEs) are powerful deep generative models widely used to
represent high-dimensional complex data through a low-dimensional latent space learned …

Computer scientists have long recognized that naive implementations of algorithms often
result in a paralyzing degree of redundant computation. More sophisticated implementations …

We develop a generalisation of disentanglement in variational autoencoders (VAEs)—
decomposition of the latent representation—characterising it as the fulfilment of two factors …

Many real-world sequential decision making problems are partially observable by nature,
and the environment model is typically unknown. Consequently, there is great need for …

Abstract We present Sequential Attend, Infer, Repeat (SQAIR), an interpretable deep
generative model for image sequences. It can reliably discover and track objects through the …

Data assimilation, in its most comprehensive form, addresses the Bayesian inverse problem
of identifying plausible state trajectories that explain noisy or incomplete observations of …

This book is a graduate-level introduction to probabilistic programming. It not only provides a
thorough background for anyone wishing to use a probabilistic programming system, but …

We provide theoretical and empirical evidence that using tighter evidence lower bounds
(ELBOs) can be detrimental to the process of learning an inference network by reducing the …

Particle Filtering (PF) methods are an established class of procedures for performing
inference in non-linear state-space models. Resampling is a key ingredient of PF necessary …

Knowledge-grounded dialogue is a task of generating an informative response based on
both discourse context and external knowledge. As we focus on better modeling the …