A fully hyperbolic attention model using Busemann energy in Poincaré discs produces emotion predictions from text that generalize well even at low embedding dimensions.
A group-theoretic framework for machine learning in hyperbolic spaces
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Two IGO flows on spheres are designed with natural gradients from Poincaré and Bergman hyperbolic geometries, realized via Kuramoto oscillator ensembles, with a noted link to quantum decision making.
citing papers explorer
-
Busemann energy-based attention for emotion analysis in Poincar\'e discs
A fully hyperbolic attention model using Busemann energy in Poincaré discs produces emotion predictions from text that generalize well even at low embedding dimensions.