SeminarMachine Learning
A Riemannian Geometry Perspective on Foundation Models
Rex Ying
Oden Institute for Computational Engineering and Sciences, UT Austin
Oct 20, 2026
Oden Institute Seminar by Rex Ying (Yale University) on how non-Euclidean geometries, particularly hyperbolic geometry, can enhance foundation models by better capturing hierarchies and symmetries in real-world data, with applications across Transformers, language model training, multimodal systems, and recommender systems.
ePoster
Towards Discovering the Hierarchy of the Olfactory Perceptual Space via Hyperbolic Embeddings
Farzaneh Taleb, Aniss Aiman Medbouhi, Giovanni Luca Marchetti, Danica Kragic
COSYNE 2025