Intelligence / Representation and Inference

How internal structure is learned, inferred, and made useful.

Representation and Inference is the topic program focused on embeddings, latent-variable models, self-supervision, approximate inference, and the technical logic of internal model spaces. It sits inside the Intelligence pillar as the program most directly concerned with learned structure and uncertainty-aware reasoning.

Scope
Representations

Contrastive objectives, self-supervision, multimodal embeddings, and geometry of learned spaces.

Inference

Variational methods, latent variables, amortization, and approximate Bayesian reasoning.

Transfer

Generalization across tasks, modalities, and settings through reusable internal structure.

Featured Notes