Diffusion models have emerged as a powerful new family of deep generative models with
record-breaking performance in many applications, including image synthesis, video …

Normalizing flows provide a general mechanism for defining expressive probability
distributions, only requiring the specification of a (usually simple) base distribution and a …

Inspired by progress in unsupervised representation learning for natural language, we
examine whether similar models can learn useful representations for images. We train a …

“Any AI smart enough to pass a Turing test is smart enough to know to fail it.”–*** Ian
McDonald Neural networks were developed to simulate the human nervous system for …

Categorical variables are a natural choice for representing discrete structure in the world.
However, stochastic neural networks rarely use categorical latent variables due to the …

With the growing volume of online information, recommender systems have been an
effective strategy to overcome information overload. The utility of recommender systems …

We explore the use of Vector Quantized Variational AutoEncoder (VQ-VAE) models for large
scale image generation. To this end, we scale and enhance the autoregressive priors used …

An introduction to a broad range of topics in deep learning, covering mathematical and
conceptual background, deep learning techniques used in industry, and research …

Deep generative models are a class of techniques that train deep neural networks to model
the distribution of training samples. Research has fragmented into various interconnected …

Image generation has been successfully cast as an autoregressive sequence generation or
transformation problem. Recent work has shown that self-attention is an effective way of …