Samuel J. Gershman

Learning Abstractions for Hierarchical Planning in Program-Synthesis Agents

Variational Agent Discovery

A circuit for predicting hierarchical structure in-context in Large Language Models

Gradient Descent as Loss Landscape Navigation: a Normative Framework for Deriving Learning Rules

Blending Complementary Memory Systems in Hybrid Quadratic-Linear Transformers

Do Mice Grok? Glimpses of Hidden Progress in Sensory Cortex