Language Models (LMs) can perform new tasks by adapting to a few in-context examples.
For humans, explanations that connect examples to task principles can improve learning. We …

Abstract reasoning is a key ability for an intelligent system. Large language models (LMs)
achieve above-chance performance on abstract reasoning tasks, but exhibit many …

Much attention has been devoted recently to the generalization puzzle in deep learning:
large, deep networks can generalize well, but existing theories bounding generalization error …

According to complementary learning systems theory, integrating new memories into the
neocortex of the brain without interfering with what is already known depends on a gradual …

Transformer models can use two fundamentally different kinds of information: information
stored in weights during training, and information provided ``in-context'' at inference time. In …

Inferring the abstract relational and causal structure of the world is a major challenge for
reinforcement-learning (RL) agents. For humans, language {—} particularly in the form of …

Reinforcement learning algorithms use correlations between policies and rewards to improve
agent performance. But in dynamic or sparsely rewarding environments these correlations …

Biological and artificial information processing systems form representations of the world that
they can use to categorize, reason, plan, navigate, and make decisions. To what extent do …

An important aspect of intelligence is the ability to adapt to a novel task without any direct
experience (zero shot), based on its relationship to previous tasks. Humans can exhibit this …

We introduce SODA, a self-supervised diffusion model, designed for representation learning.
The model incorporates an image encoder, which distills a source view into a compact …