Preprint · 2025 · Open access
Hierarchical Mamba Meets Hyperbolic Geometry: A New Paradigm for Structured Language Embeddings
arXiv (Cornell University) · Published 25 May 2025 · DOI 10.48550/arxiv.2505.18973
In brief
“Hierarchical Mamba Meets Hyperbolic Geometry: A New Paradigm for Structured Language Embeddings” is a 2025 preprint by Sarang Rajendra Patil and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 5 citations as of 18 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 5
- Most cited in
- 2026 (5)
- References
- 33
- Authors
- 4
Abstract
Selective state-space models excel at long-sequence modeling, but their capacity for language representation -- in complex hierarchical reasoning -- remains underexplored. Most large language models rely on \textit{flat} Euclidean embeddings, limiting their ability to capture latent hierarchies. To address this, we propose {\it Hierarchical Mamba (HiM)}, integrating efficient Mamba2 with hyperbolic geometry to learn hierarchy-aware language embeddings for deeper linguistic understanding. Mamba2-processed sequences are projected to the Poincaré ball or Lorentzian manifold with ``learnable'' curvature, optimized with a hyperbolic loss. Our HiM model facilitates the capture of relational distances across varying hierarchical levels, enabling effective long-range reasoning for tasks like mixed-hop prediction and multi-hop inference in hierarchical classification. Experimental results show both HiM variants effectively capture hierarchical relationships across four linguistic and medical datasets, surpassing Euclidean baselines, with HiM-Poincaré providing fine-grained distinctions with higher h-norms, while HiM-Lorentz offers more stable, compact, and hierarchy-preserving embeddings-favoring robustness. The source code is publicly available at https://github.com/BerryByte/HiM.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Patil, S. R., Parmanand, P. A., Koutis, I., & Xu, M. (2025). Hierarchical Mamba Meets Hyperbolic Geometry: A New Paradigm for Structured Language Embeddings. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2505.18973
MLA 9
Patil, Sarang Rajendra, et al. “Hierarchical Mamba Meets Hyperbolic Geometry: A New Paradigm for Structured Language Embeddings.” arXiv (Cornell University), 2025. https://doi.org/10.48550/arxiv.2505.18973.
Chicago
Patil, Sarang Rajendra, Pandey, Ashish Parmanand, Ioannis Koutis, and Mengjia Xu. 2025. “Hierarchical Mamba Meets Hyperbolic Geometry: A New Paradigm for Structured Language Embeddings.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2505.18973.
Harvard
Patil, S. R. et al. (2025) ‘Hierarchical Mamba Meets Hyperbolic Geometry: A New Paradigm for Structured Language Embeddings’, arXiv (Cornell University). doi:10.48550/arxiv.2505.18973.
IEEE
S. R. Patil, P. A. Parmanand, I. Koutis, and M. Xu, “Hierarchical Mamba Meets Hyperbolic Geometry: A New Paradigm for Structured Language Embeddings,” arXiv (Cornell University), 2025, doi: 10.48550/arxiv.2505.18973.
BibTeX
@misc{patil2025hierarchical,
title = {{Hierarchical Mamba Meets Hyperbolic Geometry: A New Paradigm for Structured Language Embeddings}},
author = {Patil, Sarang Rajendra and Parmanand, Pandey, Ashish and Koutis, Ioannis and Xu, Mengjia},
howpublished = {arXiv (Cornell University)},
year = {2025},
doi = {10.48550/arxiv.2505.18973},
url = {https://doi.org/10.48550/arxiv.2505.18973}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Mamba-2
- hyperbolic geometry
- hyperbolic embeddings
- Poincaré ball
- Lorentzian manifolds
- state-space model
- long sequence modeling
- multi-hop reasoning
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Patil, S. R., Parmanand, P. A., Koutis, I., & Xu, M. (2025). Hierarchical Mamba Meets Hyperbolic Geometry: A New Paradigm for Structured Language Embeddings. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2505.18973
How many times has this paper been cited?
5 times, according to OpenAlex on 18 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Sarang Rajendra Patil, Pandey, Ashish Parmanand, Ioannis Koutis, Mengjia Xu.
What is the DOI of this paper?
10.48550/arxiv.2505.18973, permanently at https://doi.org/10.48550/arxiv.2505.18973. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.