Abstract: Three remarkable abilities of brains and machines are to: (1) learn new behaviors from a single example, (2) creatively imagine new possibilities, and (3) perform mathematical reasoning. I will discuss simple analytic yet quantitatively predictive theories of how (1) mice learn to accurately navigate on the first encounter in a new environment; (2) how diffusion models creatively imagine exponentially many new images; and (3) how large language models can conduct mathematical reasoning and theorem proving.
References:
Theory of mouse navigation: https://www.nature.com/articles/s41586-024-08034-3
Theory of creativity in diffusion models (ICML ’25): https://arxiv.org/abs/2412.20292
Theory of mathematical reasoning (NeurIPS ’25): https://arxiv.org/abs/2502.07154
Speaker
Surya GanguliAssociate Professor of Applied Physics, Senior Fellow at the Stanford Institute for Human-Centered AI