English

Hyperbolic Deep Learning for Foundation Models: A Survey

Machine Learning 2025-07-25 v1 Artificial Intelligence

Abstract

Foundation models pre-trained on massive datasets, including large language models (LLMs), vision-language models (VLMs), and large multimodal models, have demonstrated remarkable success in diverse downstream tasks. However, recent studies have shown fundamental limitations of these models: (1) limited representational capacity, (2) lower adaptability, and (3) diminishing scalability. These shortcomings raise a critical question: is Euclidean geometry truly the optimal inductive bias for all foundation models, or could incorporating alternative geometric spaces enable models to better align with the intrinsic structure of real-world data and improve reasoning processes? Hyperbolic spaces, a class of non-Euclidean manifolds characterized by exponential volume growth with respect to distance, offer a mathematically grounded solution. These spaces enable low-distortion embeddings of hierarchical structures (e.g., trees, taxonomies) and power-law distributions with substantially fewer dimensions compared to Euclidean counterparts. Recent advances have leveraged these properties to enhance foundation models, including improving LLMs' complex reasoning ability, VLMs' zero-shot generalization, and cross-modal semantic alignment, while maintaining parameter efficiency. This paper provides a comprehensive review of hyperbolic neural networks and their recent development for foundation models. We further outline key challenges and research directions to advance the field.

Keywords

Cite

@article{arxiv.2507.17787,
  title  = {Hyperbolic Deep Learning for Foundation Models: A Survey},
  author = {Neil He and Hiren Madhu and Ngoc Bui and Menglin Yang and Rex Ying},
  journal= {arXiv preprint arXiv:2507.17787},
  year   = {2025}
}

Comments

11 Pages, SIGKDD 2025

R2 v1 2026-07-01T04:15:49.523Z