Ke Liu

Ph.D. Candidate

State Key Lab of CAD & CG
Center for Data Science
College of Computer Science and Technology
Zhejiang University
Hangzhou, China. 310058.

Github: zjuKeLiu & Gitee
Scholar: Google scholar
Email: kliu ατ zju δατ edu δατ cn

Job Market 2026: I am actively seeking research scientist, faculty, and postdoc opportunities in machine learning for science, materials, and healthcare. Contact me

Biography

I'm currently a final year Ph.D candidate of the College of Computer Science and Technology at Zhejiang University, fortunately advised by Prof. Chunhua Shen. Before that I got my bachelor's degree from Zhejiang University in July 2021 majoring in Automation and minoring in Advanced-honor Class of Engineering Education, Chu Kochen honors College. I also worked as a visiting researcher with Prof. Ajitha Rajan from Oct 2024 to Oct 2025 at the School of Informatics, University of Edinburgh, UK.

Research Interests

Machine Learning and its application in Science, including but not limited to computer vision, molecule design, material discovery, and medical image analysis. Please feel free to drop me an e-mail if you are interested in our work. More research can be found here.
Research Interests

Selected Publications

NeurIPS'25
    Towards Generalizable Retina Vessel Segmentation with Deformable Graph Priors
    Ke Liu [...]
    Proc. Advances in Neural Information Processing Systems (NeurIPS'25), 2025.
    [paper] [code] [bib]

IJCAI'25
    Mat-Instructions: A Large-Scale Inorganic Material Instruction Dataset for Large Language Models
    Ke Liu [...]
    Proc. International Joint Conference on Artificial Intelligence (IJCAI'25), 2025.
    [paper] [code] [bib] [Project Page]

AAAI'25
    A Denoising Pre-training Framework for Accelerating Novel Material Discovery
    Shuaike Shen*, Ke Liu*✉ [...]
    Proc. Annual AAAI Conference on Artificial Intelligence. (AAAI'25), 2025.
    [code] [paper] [bib] [Project Page]

ICML'24

Information Sciences
    Collaborative knowledge amalgamation: Preserving discriminability and transferability in unsupervised learning
    Shangde Gao*, Yichao Fu*, Ke Liu* [...]
    Information Sciences, 2024.
    [paper] [bib]

KDD'23
    Empowering General-purpose User Representation with Full-life Cycle Behavior Modeling.
    Bei Yang, Jie Gu, Ke Liu [...]
    Proc. Knowledge Discovery and Data Mining (KDD'23), 2023.
    [paper] [bib]

UAI'23
    Group Equivariant Vision Transformer
    Rux Xu*, Kaifan Yang*, Ke Liu*✉ [...]
    Proc. Conference on Uncertainty in Artificial Intelligence (UAI'23), 2023.
    [code] [paper] [bib]

IJCNN'23
    PCVAE: a Physics-Informed Neural Network for Determining the Symmetry and Geometry of Crystals
    Ke Liu [...]
    Proc. International Joint Conference on Neural Networks (IJCNN'23), 2023.
    (Oral presentation)
    [code] [paper] [bib]

MM'22
    Learning Interest-oriented Universal User Representation via Self-supervision
    ..., Ke Liu, ... [...]
    Proc. ACM International Conference on Multimedia (MM'22), 2022.
    [paper] [bib]

IJCAI'22
    S2SNet: A Pretrained Neural Network for Superconductivity Discovery
    Ke Liu [...]
    Proc. International Joint Conference on Artificial Intelligence (IJCAI'22), 2022.
    [code] [paper] [bib]

Full publication list

Academic Service

Reviewer

Conference: ICML 2025, ICLR 2025-2026, NeurIPS 2025, AAAI 2024-2026, ACM MM 2023-2024, MICCAI 2025, IJCNN 2024-2025

Journal: Neural Networks, Computer Vision and Image Understanding, Philosophical Transactions of the Royal Society A

News

Useful Links