Synthetic image datasets offer unmatched advantages for designing and
ev...
For more than a decade, researchers have measured progress in object
rec...
Large language models based on transformers have achieved great empirica...
Despite impressive advances in object-recognition, deep learning systems...
Deep learning vision systems are widely deployed across applications whe...
Recent state-of-the-art vision models introduced new architectures, lear...
Deep learning has led to remarkable advances in computer vision. Even so...
A grand goal in deep learning research is to learn representations capab...
As learning machines increase their influence on decisions concerning hu...
To perform well on unseen and potentially out-of-distribution samples, i...
A core challenge in Machine Learning is to learn to disentangle natural
...
Contrarily to humans who have the ability to recombine familiar expressi...
Natural language allows us to refer to novel composite concepts by combi...
Human language users easily interpret expressions that describe unfamili...
Research in multi-agent cooperation has shown that artificial agents are...
To cooperate with humans effectively, virtual agents need to be able to
...
There is renewed interest in simulating language emergence among deep ne...
There is a growing interest in studying the languages emerging when neur...
Recent research studies communication emergence in communities of deep
n...
With the advent of deep neural networks, some research focuses towards
u...
There is growing interest in the language developed by agents interactin...
We would like to learn a representation of the data which decomposes an
...
We present a new type of probabilistic model which we call DISsimilarity...