The fields of neuroscience and artificial intelligence (AI) have a long and intertwined history.
In more recent times, however, communication and collaboration between the two fields has …

The ability to predict, anticipate and reason about future outcomes is a key component of
intelligent decision-making systems. In light of the success of deep learning in computer …

How does one adapt a pre-trained visual model to novel downstream tasks without task-
specific finetuning or any model modification? Inspired by prompting in NLP, this paper …

In this paper we tackle the problem of Generalized Category Discovery (GCD). Specifically,
given a dataset with labelled and unlabelled images, the task is to cluster all images in the …

The key idea behind the unsupervised learning of disentangled representations is that real-
world data is generated by a few explanatory factors of variation which can be recovered by …

Intelligent agents should be able to learn useful representations by observing changes in
their environment. We model such observations as pairs of non-iid images sharing at least …

Synthesizing high-quality images from text descriptions is a challenging problem in
computer vision and has many practical applications. Samples generated by existing text-to …

We propose the coupled generative adversarial nets (CoGAN) framework for generating
pairs of corresponding images in two different domains. The framework consists of a pair of …

Automatic synthesis of realistic images from text would be interesting and useful, but current
AI systems are still far from this goal. However, in recent years generic and powerful …

We present a new model DRNET that learns disentangled image representations from
video. Our approach leverages the temporal coherence of video and a novel adversarial …