Complex networks, ranging from biological systems to technological and social infrastructures, have long intrigued researchers with their intricate connectivity and emergent behaviours. Recent ...

In mathematics, hyperbolic geometry is a non-Euclidean geometry, meaning that the parallel postulate of Euclidean geometry is rejected. The parallel postulate in Euclidean geometry states, for two ...

Reducing redundant information to find simplifying patterns in data sets and complex networks is a scientific challenge in many knowledge fields. Moreover, detecting the dimensionality of the data is ...

We have built a world of largely straight lines – the houses we live in, the skyscrapers we work in and the streets we drive on our daily commutes. Yet outside our boxes, nature teams with frilly, ...

Geometry boasts a rich and captivating history within the realm of mathematics. In its early development, it was deeply rooted in practical observation used to describe essential concepts such as ...

A comprehensive PyTorch implementation of Lobachevsky's hyperbolic geometry for modern deep learning applications. This library provides mathematically rigorous hyperbolic neural networks, specialized ...

description [NeurIPS 2025][LLM Evaluation][hyperbolic geometry] This work identifies that LLM token embeddings follow power-law distributions and exhibit tree-like hyperbolic structure, and proposes ...