Jun Xia

Jun Xia Signature

Assistant Professor
Data Science and Analytics Thrust (DSA Thrust)
Information Hub
HKUST(GZ) & HKUST

Email: junxia@hkust-gz.edu.cn
Tel: (020) 88333858
Office: W4-535, HKUST(GZ)

Profile

Jun Xia is an Assistant Professor at the Hong Kong University of Science and Technology (Guangzhou), leading the AI for Multimodality and Science Lab (AIMS Lab) with research focused on Multimodal Large Models and AI for Sciences. He also holds an affiliated appointment at The Hong Kong University of Science and Technology (Clear Water Bay, Hong Kong). He received his Ph.D. from a joint program between Westlake University and Zhejiang University, advised by Chair Prof. Stan Z. Li.

🌟 Hiring: We are actively seeking visiting students, research assistant and self-motivated Ph.D. and M.Phil students. Since July 2022, almost every visiting student who worked with me has published papers at top conferences such as ICML, NeurIPS, and ICLR during their visit. If you are interested, please don't hesitate to contact me via Email.

News New

  • (2025.08) Invited to serve as Area Chairs for ICLR 2026 and AI4Science Workshop at NeurIPS 2025.
  • (2025.05) Four papers are accepted by IJCAI 2025.
  • (2025.04) Invited to serve as an Area Chair for NeurIPS 2025.
  • (2025.01) Four papers on AI for Life Science are accepted in ICLR 2025.
  • (2024.12) A paper on AIDD is accepted in Bioinformatics.

View all news →

Selected Awards & Honors

  • 2024: CIE-Tencent Doctoral Research Incentive Project ((首届)中国电子学会—腾讯博士生科研激励计划).

  • 2024: Fundamental Research Project for Young Ph.D. students from NSFC (首批国家自然科学基金青年学生基础研究项目(博士生)).

  • 2024: DAAD AINet Fellowship.

  • 2023: Rising Star in AI (awarded by KAUST AI Initiative headed by Prof. Jürgen Schmidhuber)

  • 2023: Apple AI/ML Scholar Finalist

  • 2023: NeurIPS Scholar Award.

  • 2023: Suwu Scholarship.

  • 2023: Westlake Presidential Awards (The highest honor at Westlake Univ.).

  • 2022: National Scholarship. 2017: National Scholarship.

Professional Service

  • Area Chair:
    • ICLR 2026
    • NeurIPS 2025
    • AI4Science@NeurIPS 2025
  • Program Committee Member or Reviewer:
    • Conferences: ICLR, ICML, NeurIPS, CVPR, KDD, ACL, SDM, ECML, ICASSP, etc.
  • Journal Reviewer: Nature Communications, IEEE TPAMI, IEEE TIP, ACM TKDD, IEEE TNNLS, Neural Networks, etc.

AIMS Lab

The AI for Multimodality and Science (AIMS) Lab focuses on cutting-edge research in multimodal AI and its applications in scientific discovery (AI for Science).

Ph.D. Students

Zheng Fang
Zheng Fang
MS from NUS
Yifan Li
Yifan Li
MS from SJTU
Haitao Yu
Haitao Yu
MS from SEU

M.Phil. Students

Yusen Tan
Yusen Tan
BE from SWU
Hongyu Zhan
Hongyu Zhan
BE from XJTU

Visiting Students and RA

PhD:

  • Yunhua Zhong (Ph.D. Student from HKU)
  • Taoyong Cui (Ph.D. Student from CUHK)
  • Dongxin Lv (Ph.D. Student from Westlake)
  • Jie Yang (Ph.D. Student from FDU)

MD:

  • Zhijin Dong (MS Student from PKU)
  • Yuniang Jiang (MS Student from THU)
  • ChuangXin Zhao (MS Student from CAS)
  • Pan Liu (MS Student from CSU)

BD:

  • Chenming Xu (BE Student from NJU)
  • Bo Liu (BE Student from JLU)
  • Zhuoli Ouyang (BE Student from SUSTech)
  • Ziyi Liu (BE Student from BUPT)
  • Yiran Zhu (BE Student from NCEPU)

Alumni

Research Focus

The AIMS Lab focuses on advancing research in Multimodal AI and SpectraAI (AI for Spectral Data Analysis).

Multimodal AI

Core Focus: Pre-training and Post-training techniques for multimodal large models, such as preference optimization and reasoning ablities improvements. Multimodal AI research serve as a foundational support for the advancement of SpectraAI.

SpectraAI (AI for Spectral Data Analysis)

Core Focus: Developing advanced AI models for analyzing spectral data (e.g., Mass Spectrometry, Infrared Spectroscopy, Nuclear Magnetic Resonance). As an application and extension of Multimodal AI in the field of spectral data, SpectraAI places strong emphasis on translating algorithms and models into practical use cases. The ultimate goal is to drive real-world impacts through the deployment of these technical solutions.

Below are our team's Publications

View All Publications

Publications

Listed by categories in reversed chronological order, where ∗ indicates equal contribution and † denotes the corresponding author.

SpectraAI
Bridging the Gap between Database Search and De Novo Peptide Sequencing with SearchNovo
Jun Xia, Sizhe Liu, Jingbo Zhou, Shaorong Chen, hongxin xiang, Zicheng Liu, Yue Liu, Stan Z. Li.
ICLR 2025; AI4DrugX@NeurIPS 2024, Spotlight
[PDF] [Bib] [Code]
SpectraAI
ReNovo: Retrieval-Based De Novo Mass Spectrometry Peptide Sequencing
Shaorong Chen∗, Jun Xia∗† (Corresponding & Co-first Author), Jingbo Zhou, Lecheng Zhang, Zhangyang Gao, Bozhen Hu, Cheng Tan, Wenjie Du, Stan Z. Li.
ICLR 2025
[PDF] [Bib] [Code]
SpectraAI
A comprehensive and systematic review for deep learning-based de novo peptide sequencing
Jun Xia, Jingbo Zhou, Shaorong Chen, Tianze Ling, Stan Z. Li.
IJCAI 2025
[PDF] [Bib]
AIDD (AI for Drug Discovery)
Electron Density-enhanced Molecular Geometry Learning
Hongxin Xiang∗, Jun Xia∗ (Co-first Author), Xin Jin, Wenjie Du, Li Zeng, Xiangxiang Zeng.
IJCAI 2025
[PDF] [Bib] [Code]
AIVC (AI for Virtual Cell)
GRAPE: Heterogeneous Graph Representation Learning for Genetic Perturbation with Coding and Non-Coding Biotype
Changxi Chi∗, Jun Xia∗ (Co-first Author), Jingbo Zhou, Jiabei Chen, Stan Z. Li.
IJCAI 2025
[PDF] [Bib] [Code]
AIDD (AI for Drug Discovery)
Iterative Substructure Extraction for Molecular Relational Learning with Interactive Graph Information Bottleneck
Shuai Zhang, Junfeng Fang, hongxin xiang, Xuqiang Li, Jun Xia† (Corresponding Author), Ye Wei, Wenjie Du, Yang Wang.
ICLR 2025
[PDF] [Bib] [Code]
AIDD (AI for Drug Discovery)
MeToken: Uniform Micro-environment Token Boosts Post-Translational Modification Prediction
Cheng Tan, Zhenxiao Cao, Zhangyang Gao, Lirong Wu, Siyuan Li, Yufei Huang, Jun Xia, Bozhen Hu, Stan Z. Li.
ICLR 2025
[PDF] [Bib] [Code]
SpectraAI
AdaNovo: Towards Robust De Novo Peptide Sequencing in Proteomics against Data Biases
Jun Xia∗, Shaorong Chen∗, Jingbo Zhou, Tianze Ling, Wenjie Du, Sizhe Liu, Stan Z. Li.
NeurIPS 2024
[PDF] [Bib] [Code]
AIDD (AI for Drug Discovery)
FlexMol: A Flexible Toolkit for Benchmarking Molecular Relational Learning
Sizhe Liu∗, Jun Xia∗† (Corresponding & Co-first Author), Lecheng Zhang, Yuchen Liu, Yue Liu, Wenjie Du, Zhangyang Gao, Bozhen Hu, Cheng Tan, hongxin xiang, Stan Z. Li.
NeurIPS 2024
[PDF] [Bib] [Code]
SpectraAI
NovoBench: Benchmarking Deep Learning-based De Novo Sequencing Methods in Proteomics
Jingbo Zhou∗, Shaorong Chen∗, Jun Xia∗† (Corresponding & Co-first Author), Sizhe Liu, Tianze Ling, Wenjie Du, Yue Liu, Jianwei Yin, Stan Z. Li.
NeurIPS 2024
[PDF] [Bib] [Code]
AIDD (AI for Drug Discovery)
SP-DTI: Subpocket-Informed Transformer for Drug-Target Interaction Prediction
Sizhe Liu, Yuchen Liu, Haofeng Xu, Jun Xia† (Corresponding Author), Stan Z. Li.
Bioinformatics 2024
[PDF] [Bib] [Code]
Graph Neural Networks
DiscoGNN: A Sample-Efficient Framework for Graph Self-supervised Representation Learning
Jun Xia∗, Shaorong Chen∗, Yue Liu, Zhangyang Gao, Jiangbing Zheng, Xihong Yang, Stan Z. Li.
IEEE ICDE 2024
[PDF] [Bib] [Code]
Graph Neural Networks
GNN Cleaner: Label Cleaner for Graph Structured Data
Jun Xia, Student Member, IEEE, Haitao Lin, Yongjie Xu, Cheng Tan, Lirong Wu, Siyuan Li, and Stan Z. Li.
IEEE TKDE 2024
[PDF] [Bib] [Code]
AIDD (AI for Drug Discovery)
Cross-Gate MLP with Protein Complex Invariant Embedding is A One-Shot Antibody Designer
Cheng Tan, Zhangyang Gao, Lirong Wu, Jun Xia, Jiangbin Zheng, Xihong Yang, Yue Liu, Bozhen Hu, Stan Z. Li.
AAAI 2024, Oral Presentation
[PDF] [Bib] [Code]
AIDD (AI for Drug Discovery)
Learning Complete Protein Representation by Dynamically Coupling of Sequence and Structure
Bozhen Hu, Cheng Tan, Jun Xia, Yue Liu, Lirong Wu, Jiangbin Zheng, Yongjie Xu, Yufei Huang, Stan Z. Li.
NeurIPS 2024
[PDF] [Bib] [Code]
AIDD (AI for Drug Discovery)
KW-Design: Pushing the Limit of Protein Design via Knowledge Refinement
Zhangyang Gao, Cheng Tan, Xingran Chen, Yijie Zhang, Jun Xia, Siyuan Li, Stan Z. Li.
ICLR 2024
[PDF] [Bib] [Code]
Graph Neural Networks
A Graph is Worth K Words: Euclideanizing Graph using Pure Transformer
Zhangyang Gao, Daize Dong, Cheng Tan, Jun Xia, Bozhen Hu, Stan Z. Li.
ICML 2024
[PDF] [Bib] [Code]
AIDD (AI for Drug Discovery)
ProtGO: Function-Guided Protein Modeling for Unified Representation Learning
Bozhen Hu, Cheng Tan, Yongjie Xu, Zhangyang Gao, Jun Xia, Lirong Wu, Stan Z. Li.
NeurIPS 2024
[PDF] [Bib] [Code]
Graph Neural Networks
Deep Graph Neural Networks via Posteriori-Sampling-based Node-Adaptative Residual Module
Jingbo Zhou, Yixuan Du, Ruqiong Zhang, Jun Xia, Zhizhi Yu, Zelin Zang, Di Jin, Carl Yang, Rui Zhang, Stan Z. Li.
NeurIPS 2024
[PDF] [Bib] [Code]
AIDD (AI for Drug Discovery)
An Image-enhanced Molecular Graph Representation Learning Framework
Hongxin Xiang, Shuting Jin, Jun Xia, Man Zhou, Jianmin Wang, Li Zeng, Xiangxiang Zeng.
IJCAI 2024
[PDF] [Bib] [Code]
AIDD (AI for Drug Discovery)
MMGNN: A Molecular Merged Graph Neural Network for Explainable Solvation Free Energy Prediction
Wenjie Du, Junfeng Fang, Jun Xia, Ziyuan Zhao, Yang Wang, Shuai Zhang, Di Wu.
IJCAI 2024
[PDF] [Bib] [Code]
AIDD (AI for Drug Discovery)
Deciphering RNA Secondary Structure Prediction: A Probabilistic K-Rook Matching Perspective
Cheng Tan, Zhangyang Gao, Hanqun Cao, Xingran Chen, Ge Wang, Lirong Wu, Jun Xia, Jiangbin Zheng, Stan Z. Li.
ICML 2024
[PDF] [Bib] [Code]
AIDD (AI for Drug Discovery)
Mole-BERT: Rethinking Pre-training Graph Neural Networks for Molecules
Jun Xia∗, Chengshuai Zhao∗, Bozhen Hu, Zhangyang Gao, Stan Z. Li.
ICLR 2023
[PDF] [Bib] [Code]
AIDD (AI for Drug Discovery)
Understanding the Limitations of Deep Models for Molecular Property Prediction: Insights and Solutions
Jun Xia∗, Lecheng Zhang∗, Xiao Zhu, Stan Z. Li.
NeurIPS 2023; Combio@ICML 2023, Spotlight Talk
[PDF] [Bib] [Code]
AIDD (AI for Drug Discovery)
A Systematic Survey of Chemical Pre-trained Models
Jun Xia∗, Yanqiao Zhu∗, Yuanqi Du∗, Stan Z. Li.
IJCAI 2023
[PDF] [Bib]
Graph Neural Networks
Dink-Net: Neural Clustering on Large Graphs
Yue Liu, Ke Liang, Jun Xia, Sihang Zhou, Xihong Yang, Xingwang Liu, Stan Z. Li.
ICML 2023
[PDF] [Bib] [Code]
Others
CVT-SLR: Contrastive Visual-Textual Transformation for Sign Language Recognition with Variational Alignment
Jiangbin Zheng, Yile Wang, Cheng Tan, Siyuan Li, Ge Wang, Jun Xia, Yidong Chen, Stan Z. Li.
CVPR 2023, Highlight (Oral) Presentation
[PDF] [Bib] [Code]
AIDD (AI for Drug Discovery)
CoSP: Co-supervised pre-training of pocket and ligand
Zhangyang Gao∗, Cheng Tan∗, Jun Xia, Stan Z. Li.
ECML 2023
[PDF] [Bib] [Code]
Others
Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning
Cheng Tan, Zhangyang Gao, Lirong Wu, Jun Xia, Jiangbin Zheng, Stan Z. Li.
CVPR 2023
[PDF] [Bib] [Code]
Graph Neural Networks
Reinforcement Graph Clustering with Unknown Cluster Number
Yue Liu, Ke Liang, Jun Xia, Xihong Yang, sihang zhou, Meng Liu, Xinwang Liu, Stan Z. Li.
ACM MM 2023
[PDF] [Bib] [Code]
Graph Neural Networks
CONVERT: Contrastive Graph Clustering with Reliable Augmentation
Xihong Yang, Cheng Tan, Yue Liu, Ke Liang, Siwei Wang, sihang zhou, Jun Xia, Stan Z. Li, Xinwang Liu, En Zhu.
ACM MM 2023
[PDF] [Bib] [Code]
Graph Neural Networks
SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentation
Jun Xia∗, Lirong Wu∗, Jintao Chen, Bozhen Hu, Stan Z. Li.
WWW 2022, Most Influential Papers
[PDF] [Bib] [Code]
Graph Neural Networks
ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning
Jun Xia, Lirong Wu, Jintao Chen, Ge Wang, Stan Z. Li.
ICML 2022, Spotlight
[PDF] [Bib] [Code]
Graph Neural Networks
GraphMixup: Improving Class-Imbalanced Node Classification on Graphs by Self-supervised Context Prediction
Lirong Wu∗, Jun Xia∗ (Co-first Author), Zhangyang Gao, Stan Z. Li.
ECML 2022, Oral Presentation
[PDF] [Bib] [Code]
Others
Using Context-to-Vector with Graph Retrofitting to Improve Word Embeddings
Jiangbin Zheng, Yile Wang, Ge Wang, Jun Xia, Yue Zhang, Stan Z. Li.
ACL 2022
[PDF] [Bib] [Code]
Others
Generalized Clustering and Multi-Manifold Learning With Geometric Structure Preservation
Lirong Wu, Zicheng Liu, Jun Xia, Zelin Zang, Siyuan Li, Stan Z. Li.
WACV 2022
[PDF] [Bib] [Code]
Others
OT-Cleaner: Label Correction as Optimal Transport
Jun Xia∗, Cheng Tan∗, Lirong Wu, Yongjie Xu, Stan Z. Li.
IEEE ICASSP 2021
[PDF] [Bib] [Code]
Others
Wordreg: Mitigating the Gap between Training and Inference with Worst-Case Drop Regularization
Jun Xia∗, Ge Wang∗, Bozhen Hu, Cheng Tan, Jiangbin Zheng, Yongjie Xu, Stan Z. Li.
IEEE ICASSP 2021
[PDF] [Bib] [Code]
Others
Co-learning: Learning from noisy labels with self-supervision
Cheng Tan, Jun Xia, Lirong Wu, Stan Z. Li.
ACM MM 2021, Oral Presentation
[PDF] [Bib] [Code]
Others
Invertible Manifold Learning for Dimension Reduction
Siyuan Li, Haitao Lin, Zelin Zang, Lirong Wu, Jun Xia, Stan Z. Li.
ECML 2021
[PDF] [Bib] [Code]
AIVC (AI for Virtual Cell)
Structure-Preserving and Batch-Correcting Visualization Using Deep Manifold Transformation for Single-cell RNA-Seq Profiles
Yongjie Xu, Zelin Zang, Jun Xia, Cheng Tan, Stan Z. Li.
Communication Biology
[PDF] [Bib] [Code]

Photos

Aug. 2025, HKUST(GZ) Opening Ceremony and Welcome Party Guangzhou, China
HKUST(GZ) Opening Ceremony and Welcome Party - Scene of the ceremony and welcome party
Aug. 2025, DSA Gathering Guangzhou, China
Aug. 2025 DSA Gathering in Guangzhou - Group photo of DSA participants

Openings

We are offering multiple research positions in Multimodal AI and its applications in scientific domains. Positions include PhD, Mphil, Postdoc, RA, and Visiting Scholars.

All admitted postgraduate students receive full scholarships (¥15K/month for PhD, ¥10K/month for MPhil). RAs receive competitive salaries and project bonuses. Students applying for Spring/Fall 2026 can contact us or apply for an RA position first.

中文版
我们提供多个多模态学习及其在科学发现领域应用方向的研究职位,包括博士、硕士、博士后、研究助理和访问学者。

所有录取的研究生均享受全额奖学金(博士每月1.5万元,硕士每月1万元)。研究助理享受有竞争力的薪资和项目奖金。申请2026年春季或秋季入学的学生可以联系我们,或先申请研究助理职位。中文详细信息参见AIMS Lab微信公众号

Contact Info

To apply, email your CV (education, publications, internships, etc.) and representative papers/projects to junxia@hkust-gz.edu.cn. Use the subject format “Year-Position-Your Name-Your Affiliation” (e.g., “23Fall-PhD-Jay Chou-THU”).

We will evaluate all applications promptly. Due to high email volume, we may not respond to every inquiry. If you pass the resume screening, you will receive an email for an interview. If you do not receive any reply within one month, you will not enter the next round. If you remain strongly interested, you may email us again after one month. Thank you for your patience.

PhD & MPhil Applications

PhD student requirements are listed below. For MPhil students, please contact me and sign up for the Redbird Mphil Class, choosing a academic supervisor after 6 months. For Postdoc/RA/Intern applications, we will schedule online meetings individually.

We prioritize individuals with AI and ML backgrounds but also welcome excellent students in biology and chemistry.

General Requirements:

  • Applicants should have a strong interest in AI and ML research, independent thinking, and a desire to produce influential results.
  • Strong math and programming skills, Linux experience, and a willingness to learn are essential.
  • A spirit of scientific research, openness, and collaboration is crucial.
  • Good English writing skills are required, meeting the English admissions requirements of HKUST.

Preferred Qualifications:

Applicants must meet at least one of the following requirements. Priority will be given to those who meet multiple requirements:

  • Have relevant research or project experience in AI and ML, with publications in top conferences or journals as the primary author.
  • Have internship experience in industry or a research institution, with a deep and systematic understanding of AI/ML applications and outstanding achievements during the internship.
  • Have achieved top levels in competitions such as ACM ICPC, MCM/ICM, KDD Cup, or Kaggle.
  • Have extensive experience as a full-stack engineer.

News Archive

This section is under construction. Full news archive will be added soon.

Complete history of news and announcements.