Zelin Zang

Zelin Zang

Postdoctoral Researcher at HK Institute of Innovation, CAS. Focusing on AI for Science, Medical Foundation Models, and Deep Manifold Learning.

Hi, I am Zelin Zang (臧泽林).

I am currently a Postdoctoral Researcher at the Hong Kong Institute of Innovation, Chinese Academy of Sciences, working with Prof. Zhen Lei and Prof. Jiebo Luo.

My research lies at the intersection of AI Foundation Models and AI for Science, with a particular focus on Life Sciences and Medicine. I aim to develop interpretable, scalable, and robust AI systems to solve complex problems in single-cell biology, molecular modeling, and clinical diagnosis.

Previously, I obtained my Ph.D. from Zhejiang University (jointly trained with Westlake University), supervised by Prof. Stan Z. Li (IEEE Fellow). I was also a CSC Visiting Scholar at the National University of Singapore (NUS), advised by Prof. Yang You.

📢 Openings

I am actively recruiting Interns and PhD Students (Jointly trained with Institute of Automation-CAS, Zhejiang University, or Westlake University).

We are looking for self-motivated students interested in:

  • Fundamental AI (Foundation Models, Representation Learning)
  • AI for Life Science (Single-cell, Molecular Biology)
  • Medical AI & AI Agents
  • AI + X (Interdisciplinary Research)

If you are interested, please send your CV to zangzelin@gmail.com.

Research Interests

  • AI for Life Sciences: Single-cell foundation models, molecular biology, and phylogenetic inference (BioTree).
  • Medical AI: Medical foundation models, RAG-based diagnostic reasoning, and multi-agent systems.
  • Fundamental AI: Deep manifold learning, interpretable representation learning, and geometric deep learning.

🔥 News

  • [Nov 2025] Our paper “MDTree” (Phylogenetic Inference) has been accepted by TMLR.
  • [Nov 2025] Two papers (MedLA & Cell-Aware) accepted to AAAI 2026 (Both Oral!).
  • [Sep 2025] “CellScout” accepted by IEEE TVCG.
  • [Sep 2025] One paper on 3D Hand-Instrument Interaction accepted by MIICAI 2025
  • [Mar 2025] One paper on Time Series Fault Detection accepted by IEEE TNNLS.
  • [Feb 2025] Three Papers (MUST, FGeneBERT, PoincareDMT) accepted by BIB.
  • [Jan 2025] `DaCapo’ accepted by CVPR 2025.
  • [Jul 2024] “Boosting Unsupervised Contrastive Learning” accepted by ICML 2024. –>

For a full list of publications, please refer to my Publications page.