Neural samplers such as variational autoencoders (VAEs) or generative adversarial
networks (GANs) approximate distributions by transforming samples from a simple random …

Deep generative models provide a systematic way to learn nonlinear data distributions,
through a set of latent variables and a nonlinear" generator" function that maps latent points …

Implicit generative models, which do not return likelihood values, such as generative
adversarial networks and diffusion models, have become prevalent in recent years. While it …

We introduce several techniques for sampling and visualizing the latent spaces of
generative models. Replacing linear interpolation with spherical linear interpolation …

Abstract Generative Adversarial Networks have shown remarkable success in learning a
distribution that faithfully recovers a reference distribution in its entirety. However, in some …

Several recent papers have treated the latent space of deep generative models, eg, GANs or
VAEs, as Riemannian manifolds. The argument is that operations such as interpolation are …

With the increasingly widespread deployment of generative models, there is a mounting
need for a deeper understanding of their behaviors and limitations. In this paper, we expose …

Modern generative models are usually designed to match target distributions directly in the
data space, where the intrinsic dimension of data can be much lower than the ambient …

Deep generative models (DGM) are neural networks with many hidden layers trained to
approximate complicated, high‐dimensional probability distributions using samples. When …

Generative adversarial networks (GANs) have emerged as a powerful unsupervised method
to model the statistical patterns of real-world data sets, such as natural images. These …