Deep neural networks have reached human-level performance on many comput...
Transformer models can use two fundamentally different kinds of informat...
Abstract reasoning is a key ability for an intelligent system. Large lan...
Effective communication requires adapting to the idiosyncratic common gr...
Continuous first-person 3D environments pose unique exploration challeng...
Large language models can perform new tasks by adapting to a few in-cont...
As humans and animals learn in the natural world, they encounter
distrib...
Explanations play a considerable role in human learning, especially in a...
In naturalistic learning problems, a model's input contains a wide range...
An important aspect of intelligence is the ability to adapt to a novel t...
Reinforcement learning algorithms use correlations between policies and
...
How can deep learning systems flexibly reuse their knowledge? Toward thi...
Much attention has been devoted recently to the generalization puzzle in...
Standard deep learning systems require thousands or millions of examples...