Determining whether inputs are out-of-distribution (OOD) is an essential building block for
safely deploying machine learning models in the open world. However, previous methods …

We present high quality image synthesis results using diffusion probabilistic models, a class
of latent variable models inspired by considerations from nonequilibrium thermodynamics …

Visual signals in a video can be divided into content and motion. While content specifies
which objects are in the video, motion describes their dynamics. Based on this prior, we …

Vision transformer networks have shown superiority in many computer vision tasks. In this
paper, we take a step further by proposing a novel generative vision transformer with latent …

Neural networks suffer from catastrophic forgetting when sequentially learning tasks phase-
by-phase, making them inapplicable in dynamically updated systems. Class-incremental …

Contrastive divergence is a popular method of training energy-based models, but is known
to have difficulties with training stability. We propose an adaptation to improve contrastive …

We propose an energy-based model (EBM) in the latent space of a generator model, so that
the EBM serves as a prior model that stands on the top-down network of the generator …

This study investigates the effects of Markov chain Monte Carlo (MCMC) sampling in
unsupervised Maximum Likelihood (ML) learning. Our attention is restricted to the family of …

We introduce the Generalized Energy Based Model (GEBM) for generative modelling. These
models combine two trained components: a base distribution (generally an implicit model) …

Text generation is ubiquitous in many NLP tasks, from summarization, to dialogue and
machine translation. The dominant parametric approach is based on locally normalized …