Contrastive Learning has recently received interest due to its success in self-supervised
representation learning in the computer vision domain. However, the origins of Contrastive …

Deep neural networks are generally designed as a stack of differentiable layers, in which a
prediction is obtained only after running the full stack. Recently, some contributions have …

The aim of this paper is to introduce a new learning procedure for neural networks and to
demonstrate that it works well enough on a few small problems to be worth further …

Contrastive learning has become a key component of self-supervised learning approaches
for computer vision. By learning to embed two augmented versions of the same image close …

In image-to-image translation, each patch in the output should reflect the content of the
corresponding patch in the input, independent of domain. We propose a straightforward …

Aligning distributions of view representations is a core component of today's state of the art
models for deep multi-view clustering. However, we identify several drawbacks with naively …

Abstract Masked Image Modeling (MIM) achieves outstanding success in self-supervised
representation learning. Unfortunately, MIM models typically have huge computational …

A video prediction model that generalizes to diverse scenes would enable intelligent agents
such as robots to perform a variety of tasks via planning with the model. However, while …

Some autoregressive models exhibit in-context learning capabilities: being able to learn as
an input sequence is processed, without undergoing any parameter changes, and without …

Deep embedding learning plays a key role in learning discriminative feature
representations, where the visually similar samples are pulled closer and dissimilar samples …