RiLM: Parameter-Efficient Language Modeling via Geodesic Decoding
Penn Treebank and a 10k-vocabulary stress test confirm that geodesic decoding transfers across corpora and larger |V|, while hyperbolic curvature helps selectively, and characterize boundary collapse in naive hyperbolic recurrence and show how Mobius stabilization restores trainability.
Fang Li
· 0 citations