Jiajun Yu

Jiajun Yu
jiajunyu@zju.edu.cn | +86 13031180113 | Google Scholar | Hangzhou, China

Summary

I am a second-year Ph.D. student jointly trained by Zhejiang University and Shanghai Innovation Institute. My research focuses on AI for drug discovery, large language models (LLMs), and graph neural networks (GNNs). I work on key problems including LLM agents, idea generation, virtual screening, molecular property prediction, molecular optimization, and structure prediction. I also have strong large-scale data engineering experience, including building TB-scale datasets from scratch and training on billion-scale data.

Professional Experience

2024.08 - 2024.12

Ant Group / Alipay

Algorithm Intern · Shanghai

Fine-tuned Llama3.1, Qwen2.5, GLM4, and DeepSeek for QA extraction in the employee assistant scenario and shipped the system online.
Designed a graph-based RAG (GraphRAG) algorithm, significantly improving base model performance in multi-task settings.

2023.06 - 2023.12

CUHK-Shenzhen / Shenzhen Institute of Big Data

Research Intern

Improved readout functions for molecular property prediction from a kernel-method perspective.

2021.03 - 2021.09

Kuaishou Technology

Algorithm Intern · Beijing

Led data collection and maintenance for multimodal video retrieval algorithms.
Built a news short-video generation pipeline from scratch; won 2nd place in the TRECVID 2021 video retrieval track.

Education

2024.09 - 2028.03

Zhejiang University & Shanghai Innovation Institute

Ph.D. in Software Engineering

Advisors: Prof. Haishuai Wang and Associate Prof. Yu Kang.

2021.09 - 2024.06

China Agricultural University

M.Sc. in Computer Science and Technology

Recipient of National Scholarship twice (top 0.2%).

2017.08 - 2021.05

China Agricultural University

B.Sc. in Computer Science and Technology

Team leader of the university's first MCM/ICM Finalist team in 2020.

Publications

* and + denote co-first author and corresponding author, respectively.

LLM Track

SIGIR Industry TrackCORE A*2026

Code-Based English Models Surprising Performance on Chinese QA Pair Extraction Task.

Jiajun Yu*, Linghan Zheng*, Hui Liu+, Xiaojun Lin, Jiayuan Dong, Yue Sheng, Gang Shi, Zhiwei Liu, Hongwei Chen, Haishuai Wang+

ACLCORE A*2025

EXPLAIN: Enhancing Retrieval-Augmented Generation with Entity Summary.

Yaozhen Liang, Xiao Liu, Jiajun Yu, Zhouhua Fang, Qunsheng Zou, Linghan Zheng, Yong Li, Zhiwei Liu, Haishuai Wang+

AI for Science Track

KDDCORE A*2026

Is Sequence Generation Optimal for Molecular Editing? A Graph-based MoE Alternative.

Jiajun Yu*, Zhihao Wu, Yizhen Zheng, Shirui Pan, Jiajun Bu, Haishuai Wang+

arXivPreprint2025

Collaborative expert LLMs guided multi-objective molecular optimization.

Jiajun Yu*, Yizhen Zheng*, Huan Yee Koh*, Shirui Pan, Haishuai Wang+

Under Review2025

Systematic discovery of single-cell protein networks in cancer with Shusi.

Tianyun Zhang*, Jiajun Yu*, Shang Lou*, Yaozhen Liang, Yue Liang, Zhekai Li, Haishuai Wang+, Shanshan Pei+, Ning Shen+

IJCAICORE A*2026

PCEvo: Path-Consistent Molecular Representation via Virtual Evolutionary.

Kun Li, Longtao Hu, Yida Xiong, Jiajun Yu, Hongzhi Zhang, Jiameng Chen, Xiantao Cai, Jia Wu, Wenbin Hu

Graph-learning Track

Under Review2026

Retrieval-Augmented Graph Neural Networks for Hard Graph Classification.

Jiajun Yu, Zhihao Wu, Jielong Lu, Qianqian Shen, Lele Fu, Haishuai Wang+

IJCAICORE A*2025

A Centrality-based Graph Learning Framework.

Jiajun Yu*, Zhihao Wu*, Jielong Lu, Haishuai Wang+

Knowledge-Based SystemsQ12025

Relation-aware multiplex heterogeneous graph neural network.

Mingxia Zhao*, Jiajun Yu*, Suiyuan Zhang, Adele Lu Jia+

IJCAICORE A*2024

Kernel Readout for Graph Neural Networks.

Jiajun Yu*, Zhihao Wu*, Jinyu Cai, Adele Lu Jia+, Jicong Fan+

NeurocomputingQ1, IF~6.52024

AGCL: Adaptive Graph Contrastive Learning for graph representation learning.

Jiajun Yu, Adele Lu Jia+

Knowledge-Based SystemsQ1, IF~7.62023

MLGAL: Multi-level Label Graph Adaptive Learning for node clustering in the attributed graph.

Jiajun Yu, Adele Lu Jia+

AAAICORE A*2026

Beyond Local Patterns: Multiscale Inconsistency Learning for Graph Anomaly Detection.

Jin Lian, Zhihao Wu, Jielong Lu, Jiajun Yu, Qianqian Shen, Haishuai Wang

AAAI 2026, 40(18): 15216-15224

IJCAICORE A*2025

Divide and Conquer: Coordinating Multiplex Mixture of Graph Learners to Handle Multi-Omics Analysis.

Zhihao Wu, Jielong Lu, Jiajun Yu, Sheng Zhou, Yueyang Pi, Haishuai Wang+

ACM MMCORE A*2025

Where Views Meet Curves: Virtual Anchors for Hyperbolic Multi-View Graph Diffusion.

Jielong Lu, Zhihao Wu, Jiajun Yu, Qianqian Shen, Jiajun Bu, Haishuai Wang

IJCAICORE A*2025

Multi-Omics Analysis for Cancer Subtype Inference via Unrolling Graph Smoothness Priors.

Jielong Lu, Zhihao Wu, Jiajun Yu, Jiajun Bu, Haishuai Wang+

Others

WWWCORE A*2022

User donations in online social game streaming: The case of paid subscription in twitch.tv.

Jiajun Yu, Adele Lu Jia+

ICMLCORE A*2025

MetricEmbedding: Accelerate Metric Nearness by Tropical Inner Product.

Muyang Cao, Jiajun Yu, Xin Du, Gang Pan, Wei Wang

Engineering Applications of Artificial IntelligenceQ1, IF~8.02021

Multi-task support vector machine with pinball loss.

Yunhao Zhang, Jiajun Yu, Xinyi Dong, Ping Zhong+

Honors and Awards

Young Science and Technology Talent Development Program (Ph.D. Track), CAST, 2025
Kaggle-Bronze Award, Stanford RNA 3D Folding Competition 2025
National Scholarship (2022, 2023)
Outstanding Student Award, China Agricultural University (2022, 2023)
First-Class Graduate Scholarship (2022, 2023)
Finalist, MCM/ICM 2020
First Prize, Minsheng Cup Mathematical Modeling Competition 2019
First Prize (Beijing Division), National Undergraduate Mathematical Contest in Modeling 2019
2019 MCM/ICM Honorable Mention

Academic Service

Reviewer: WWW 2025-2026, AAAI 2026, ICML 2024-2025, IJCAI 2025, ICLR 2025-2026, NeurIPS 2024-2025, ACM MM 2024-2025, Pattern Recognition, Neural Networks, Knowledge-Based Systems, Neurocomputing.

Visitor Stats: This page views | Site total views | visitors

Visitor Info: IP loading... | Location loading... | Timezone loading...
Browser loading...