Menglin Yang

Assistant Professor@HKUST(GZ) | Postdoc@Yale University | PhD@CUHK

photo.png

About

Background. I am currently an assistant professor in the 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 postdoctoral researcher 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.

Recently, I have been working on data-centric AI and geometric learning for AI (DIGAI), including the following topics:

  • LLM and Agent. LLMs(Pretraining, CPT), PEFT, RAG, agents, reasoning, memory, multimodal learning, and non-Euclidean foundation models.
  • Information Retrieval and Personalization. Recommender systems, personalization, knowledge graphs, data mining, and network sciences.
  • Hyperbolic and Riemannian Geometric Representation Learning. Hyperbolic representation learning, differential geometry, hierarchical modeling, and AI for science.

LLM and Agent

  1. ICML 2026 Tree-RAG: Hierarchical Abstract Tree for Cross-Document Retrieval-Augmented Generation
  2. ACL 2026 HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents
  3. NeurIPS 2025 HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Experts

Information Retrieval and Personalization

  1. KDD 2026 HARec: Hyperbolic Graph-LLM Alignment for Exploration and Exploitation in Recommender Systems
  2. ICLR 2026 PerFit: Exploring Personalization Shifts in Representation Space of LLMs
  3. KDD 2026 Expand More, Shrink Less: Shaping Effective-Rank Dynamics for Dense Scaling in Recommendation

Hyperbolic and Riemannian Geometric Representation Learning

  1. ICML 2026 FlatLand: Personalized Graph Federated Learning via Tailored Lorentz Space (Spotlight)
  2. NeurIPS 2025 HypLoRA: Hyperbolic Fine-tuning for Large Language Models (Spotlight)
  3. KDD 2024 Hypformer: Exploring Efficient Transformer in Hyperbolic Space

Update: 2026-05-21

🔥 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 Wechat(微信)：mlyang2026

🌊 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 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

May 21, 2026 Two papers were accepted by KDD 2026. Congrats to all coauthors!
May 03, 2026 Five papers were accepted by ICML 2026. Congrats to all coauthors!
Apr 07, 2026 Two papers accepted by the ACL main conference.
Mar 22, 2026 One paper on Multimodal LLM was accepted by TPAMI.
Feb 26, 2026 KDD 2026 Workshop on Geometric Foundation Models was accepted.