Marcelo Fiori

A flexible hyperbolic optimization framework unlocks 46-74% loss reduction on hierarchical graphs by decoupling embedding and optimization curvatures.

Achieving optimal small-set expanders could revolutionize key exchange protocols in a post-quantum world by maximizing neighbor connections in bipartite graphs.

Hyperbolic embeddings are powerful, but a fragmented ecosystem makes them hard to use—this framework finally puts them all in one place.