Menglin Yang

About

Background. I am currently an assistant professor at Thrust of Artificial Intelligence at Hong Kong University of Science and Technology (Guangzhou), HKUSTGZ. I am also affiliated with The Hong Kong University of Science and Technology (HKUST). I was a Postdoc Research at Yale University. Before that, I obtained my Ph.D. from The Chinese University of Hong Kong.

Information about PhD student recruitment can be found on pages in Chinese Version, or English Version.

If you represent a company and seek collaboration, kindly e-mail me.

Research Interests. My research is primarily focused on exploring the connection and alignment between the learning space, especially the hyperbolic space, and the underlying geometries, structures, and patterns in different types of data.

Recently, I have been working on the following topics:

(1) Multi-modal LLMs & LLMs(Peft, RAG, Agent, Reasoning) and non-Euclidean LLMs

(2) Recommender Systems, Personalization, Knowledge graph, and Network sciences

(3) Hyperbolic Representation Learning, Differential Geometry, Hierarchical Modeling, Graph Learning and AI4SCI

(4) Applications of LLMs and Multimodal LLMs in PCB Layout Routing and Personalized AI Copilot.

🔥 I am looking for self-motivated (visiting) Ph.D. students / (remote) research assistants to work with me on the above topics. GPUs and Salaries are provided to qualified candidates. Any interested applicants can directly send me your CV and a brief introduction to your research interest to my email: menglinyang[at]hkust-gz.edu.cn

To 港科大（广州）红鸟硕士：欢迎与我联系, 讨论以上研究方向，选作学术导师。联系方式：邮件（menglinyang[at]hkust-gz.edu.cn）、微信(sshyang2048)，工作日Walk in W4-540。可选（1）大模型（微调，RAG, Implicit Reasoning等），（2）个性化/推荐/搜索/广告以及（3）几何机器学习、双曲机器学习（4）大模型在PCB布局布线以及AI个性化应用等方向。

Update: 2025-10-17

🌊 New papers, blogs, and books on hyperbolic representation and deep learning topics are shared in the following slack channel and GitHub repo. Welcome to join and share more on this fascinating research:
Slack Channel: Hyperbolic Representation and Deep Learning
Github Repo: Awesome Hyperbolic Representation and Deep Learning GitHub Repository
Hyperbolic Learning Website: Hyperbolic Deep Learning in the Age of LLMs

News

Oct 01, 2025	HOVER: Hyperbolic Video-Text Retrieval Accepted by TIP
Sep 29, 2025	Will give a talk at Duke Kunshan University - DKU
Sep 27, 2025	Redbird graduate students are welcome to contact me about AS
Sep 18, 2025	Three NeurIPS papers are accepted and one first-author paper was selected as spotlight

Selected Publications

NeurIPS ’25

Hyperbolic Fine-tuning for Large Language Models (Spotlight)

Menglin Yang, Aosong Feng, Bo Xiong, Jiahong Liu, Irwin King, and Rex Ying

NeurIPS, 2025

PDF Code
WWW ’25

Towards Non-Euclidean Foundation Models: Advancing AI Beyond Euclidean Frameworks

Menglin Yang, Yifei Zhang, Jialin Chen, Melanie Weber, and Rex Ying

In WWW(Companion), 2025

PDF
KDD ’24

Hypformer: Exploring Efficient Transformer in Hyperbolic space

Menglin Yang, Harshit Verma, Delvin Ce Zhang, Jiahong Liu, Irwin King, and Rex Ying

KDD, 2024

Abs PDF Code

Hyperbolic geometry have shown significant potential in modeling complex structured data, particularly those with underlying tree-like and hierarchical structures. Despite the impressive performance of various hyperbolic neural networks across numerous domains, research on adapting the Transformer to hyperbolic space remains limited. Previous attempts have mainly focused on modifying self-attention modules in the Transformer. However, these efforts have fallen short of developing a complete hyperbolic Transformer. This stems primarily from: (i) the absence of well-defined modules in hyperbolic space, including linear transformation layers, LayerNorm layers, activation functions, dropout operations, etc. (ii) the quadratic time complexity of the existing hyperbolic self-attention module w.r.t the number of input tokens, which hinders its scalability. To address these challenges, we propose, Hypformer, a novel hyperbolic Transformer based on the Lorentz model of hyperbolic geometry. In Hypformer, we introduce two foundational blocks that define the essential modules of the Transformer in hyperbolic space. Furthermore, we develop a linear self-attention mechanism in hyperbolic space, enabling hyperbolic Transformer to process billion-scale graph data and long-sequence inputs for the first time. Our experimental results confirm the effectiveness and efficiency of Hypformer across various datasets, demonstrating its potential as an effective and scalable solution for large-scale data representation and large models.
KDD ’23

κHGCN: Tree-likeness modeling via continuous and discrete curvature

Menglin Yang, Min Zhou, Lujia Pan, and Irwin King

KDD, 2023

PDF Code
ICML ’23

Hierarchical Learning in Hyperbolic Space: Revisit and Beyond

Menglin Yang, Min Zhou, Rex Ying, Yankai Chen, and Irwin King

ICML, 2023

PDF Code
TKDE ’22

Hyperbolic Temporal Network Embedding

Menglin Yang, Min Zhou, Hui Xiong, and Irwin King

TKDE, 2022

PDF Code
KDD ’22

HICF: Hyperbolic Informative Collaborative Filtering

Menglin Yang, Zhihao Li, Min Zhou, Jiahong Liu, and Irwin King

KDD, 2022

PDF Code
WWW ’22

HRCF: Enhancing Collaborative Filtering via Hyperbolic Geometric Regularization

Menglin Yang, Min Zhou, Jiahong Liu, Defu Lian, and Irwin King

WWW, 2022

PDF Code
Survey ’22

Hyperbolic Graph Neural Networks: A Review of Methods and Application

Menglin Yang, Min Zhou, Tong Zhang, Jiahong Liu, Zhihao Li, Lujia Pan, Hui Xiong, and Irwin King

Survey, 2022

PDF Code
KDD ’21

Discrete-time Temporal Network Embedding via Implicit Hierarchical Learning in Hyperbolic Space

Menglin Yang, Min Zhou, Marcus Kalander, Zengfeng Huang, and Irwin King

KDD, 2021

PDF Code
ICDM ’20

FeatureNorm: L2 Feature Normalization for Dynamic Graph Embedding

Menglin Yang, Ziqiao Meng, and Irwin King

ICDM, 2020

PDF Code
GRAM@ICML ’24

UHCone: Universal Hyperbolic Entailment Cone

Menglin Yang, Jiahong Liu, Irwin King, and Rex Ying

ICML GRAM Workshop, 2024

PDF
KDD ’25

Hyperbolic Deep Learning for Foundation Models: A Survey

Neil He, Hiren Madhu, Ngoc Bui, Menglin Yang^*, and Rex Ying

KDD, 2025

PDF Code
KDD ’25

Lorentzian Residual Neural Networks

Neil He, Menglin Yang^*, and Rex Ying

KDD, 2025

PDF Code
arxiv ’25

HMamba: Hyperbolic Mamba for Sequential Recommendation

Qianru Zhang, Honggang Wen, Wei Yuan, Crystal Chen, Menglin Yang^*, Siu-Ming Yiu^*, and Hongzhi Yin^*

arXiv preprint, 2025

PDF
NeurIPS ’25

HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Experts

Neil He, Rishabh Anand, Hiren Madhu, Ali Maatouk, Smita Krishnaswamy, Leandros Tassiulas, Menglin Yang, and Rex Ying

NeurIPS, 2025

PDF