A few-shot generative model should be able to generate data from a distribution by only observing a limited set of examples. In few-shot learning the model is trained on data from many sets from diffe

Counterfactuals can explain classification decisions of neural networks in a human interpretable way. We propose a simple but effective method to generate such counterfactuals. More specifically, we p

We explore methods of producing adversarial examples on deep generative models such as the variational autoencoder (VAE) and the VAE-GAN. Deep learning architectures are known to be vulnerable to adve

Counterfactual instances offer human-interpretable insight into the local behaviour of machine learning models. We propose a general framework to generate sparse, in-distribution counterfactual model

Score-based models generate samples by mapping noise to data (and vice versa) via a high-dimensional diffusion process. We question whether it is necessary to run this entire process at high dimension

In recent years fully-parametric fast simulation methods based on generative models have been proposed for a variety of high-energy physics detectors. By their nature, the quality of data-driven model

Users have the right to have their data deleted by third-party learned systems, as codified by recent legislation such as the General Data Protection Regulation (GDPR) and the California Consumer Priv

Generative networks are fundamentally different in their aim and methods compared to CNNs for classification, segmentation, or object detection. They have initially not been meant to be an image analy

We propose a new "Poisson flow" generative model (PFGM) that maps a uniform distribution on a high-dimensional hemisphere into any data distribution. We interpret the data points as electrical charges

Generative Adversarial Networks have shown remarkable success in learning a distribution that faithfully recovers a reference distribution in its entirety. However, in some cases, we may want to only

Machine learning approaches now achieve impressive generation capabilities in numerous domains such as image, audio or video. However, most training \& evaluation frameworks revolve around the idea of

Existing Score-based Generative Models (SGMs) can be categorized into constrained SGMs (CSGMs) or unconstrained SGMs (USGMs) according to their parameterization approaches. CSGMs model the probability

We deal with Bayesian generative and discriminative classifiers. Given a model distribution $p(x, y)$, with the observation $y$ and the target $x$, one computes generative classifiers by firstly consi

Generative models estimate the underlying distribution of a dataset to generate realistic samples according to that distribution. In this paper, we present the first membership inference attacks again

Diffusion generative models have recently been applied to domains where the available data can be seen as a discretization of an underlying function, such as audio signals or time series. However, the

We present a generative model to synthesize 3D shapes as sets of handles -- lightweight proxies that approximate the original 3D shape -- for applications in interactive editing, shape parsing, and bu

Capsule networks are a neural network architecture specialized for visual scene recognition. Features and pose information are extracted from a scene and then dynamically routed through a hierarchy of

The goal of compressed sensing is to estimate a vector from an underdetermined system of noisy linear measurements, by making use of prior knowledge on the structure of vectors in the relevant domain.

The ability to compare two degenerate probability distributions (i.e. two probability distributions supported on two distinct low-dimensional manifolds living in a much higher-dimensional space) is a