How does the genome encode the form of the organism? What is the nature of this genomic
code? Inspired by recent work in machine learning and neuroscience, we propose that the …

Deep generative models allow for photorealistic image synthesis at high resolutions. But for
many applications, this is not enough: content creation also needs to be controllable. While …

The latent spaces of GAN models often have semantically meaningful directions. Moving in
these directions corresponds to human-interpretable image transformations, such as …

Thompson Sampling (TS) is one of the most effective algorithms for solving contextual multi-
armed bandit problems. In this paper, we propose a new algorithm, called Neural Thompson …

Abstract 3D-aware generative models have shown that the introduction of 3D information
can lead to more controllable image generation. In particular, the current state-of-the-art …

Generative adversarial networks (GANs) are deep generative models (GMs) that have
recently attracted attention owing to their impressive performance in generating completely …

While 2D generative adversarial networks have enabled high-resolution image synthesis,
they largely lack an understanding of the 3D world and the image formation process. Thus …

In order to better understand how the brain perceives faces, it is important to know what
objective drives learning in the ventral visual stream. To answer this question, we model …

Many convolutional neural networks (CNNs) for single image deblurring employ a U-Net
structure to estimate latent sharp images. Having long been proven to be effective in image …

This work addresses the problem of discovering, in an unsupervised manner, interpretable
paths in the latent space of pretrained GANs, so as to provide an intuitive and easy way of …