Qi Wang

Title:Associate Professor

Education:Macquarie University

Email:qiwang@jlu.edu.cn

Homepage:

Research Areas:LLM Agent; Data Mining

About Me

Wang Qi is a tenure-track Associate Professor (Research Fellow), doctoral supervisor, and Jilin Province High-level Talent at the College of Artificial Intelligence, Jilin University. She received her Ph.D. from Macquarie University, Australia (Top 200), and her bachelor's and master's degrees from the College of Computer Science and Technology, Jilin University. She has published more than 20 papers in core journals and conferences in the field of artificial intelligence, including IEEE TNNLS, IEEE TITS, AAAI, EMNLP, and IJCAI. In terms of research projects, she has served as the principal investigator of one Youth Program of the National Natural Science Foundation of China, one Technical Field Fund of the Science and Technology Commission of the Central Military Commission, one sub-project of the National Key R&D Program of the Ministry of Science and Technology, one Jilin Province Excellent Youth Fund, one Technical Field Fund of the 102nd Institute of the China Academy of Launch Vehicle Technology, one OPPO industry-university-research collaboration project, and one key project of the Jilin University Faculty Development Center. As a key technical member, she has participated in one Discipline Pilot Program project of the Ministry of Education and one General Program project of the National Natural Science Foundation of China. She served as Publication Chair of WWW 2025, a CCF-A class conference, and Chair of the Organizing Committee of CCIR 2026. She also serves as a reviewer for top journals and conferences in the field of artificial intelligence, such as TPAMI, TKDE, TNNLS, and NeurIPS. She led her team to propose the world's first end-to-end large-model GUI interaction agent, which enables autonomous decision-making of visual large models in real computer environments through the introduction of an adaptive evolutionary architecture. The project has received over 600 stars on GitHub.

Research

[1]Zhiyi Duan, Zixing Shi, Hongyu Yuan, Qi Wang*. HISE-KT: Synergizing Heterogeneous Information Networks and LLMs for Explainable Knowledge Tracing with Meta-Path Optimization. Association for the Advancement of Artificial Intelligence (AAAI’26), Singapore, January 20-27, (CCF A)

[2]. Yongguang Li, Jindong Li, Qi Wang*, Qianli Xing, Runliang Niu, Shengsheng Wang, Menglin Yang. Beyond Retraining:Training-Free Unknown Class Filtering for Source-Free Open Set Domain Adaptation of Vision–Language Models. Association for the Advancement of Artificial Intelligence (AAAI’26), Singapore, January 20-27,(CCF A)

[3]. He Kong, Qianli Xing, Qi Wang*, Hechang Chen, Runliang Niu, Zhiyi Duan, Shiqi Wang, Yi Chang, Irwin King. Learning Optimal Policies with Local Observations for Cooperative Multiagent Reinforcement Learning. IEEE Transactions on Neural Networks and Learning Systems,2026.(中科院一区Top, IF=8.9)

[4]. Runliang Niu, Jindong Li, Shiqi Wang, Yali Fu, Xiyu Hu, Xueyuan Leng, He Kong, Yi Chang, Qi Wang*. Screenagent: A vision language model-driven computer control agent. Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence (IJCAI’24). Korea, August 3-9, 2024: 6433-6441. (CCF A)

[5]. Shiqi Wang, Qi Wang*, Runliang Niu, He Kong, Yi Chang. MicroEdit: Neuron-level Knowledge Disentanglement and Localization in Lifelong Model Editing. In proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP’25), China, November 4-9, 2025: 33870-33884. (清华A)

[6]. Jindong Li, Qianli Xing, Qi Wang*, Yi Chang. CVTGAD: Simplified transformer with crossview attention for unsupervised graph-level anomaly detection. In proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD’23), Italy, September 18-22, 2023: 185-200. (CCF B)

[7]. Yali Fu, Jindong Li, Qi Wang*, Qianli Xing. GLADMamba: Unsupervised Graph-LevelAnomaly Detection Powered by Selective State Space Model. In proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD’25), Portugal, September 15-19, 2025: 37-54. (CCF B)

[8]. He Kong, Qianli Xing*, Qi Wang, Runliang Niu, Hechang Chen, Yu Wang, Shiqi Wang, Zhiyi Duan, Yi Chang. ADAC: Actor-Double-Attention-Critic for Multi-Agent Cooperation in Mixed Cooperative-Competitive Environments. IEEE Transactions on Intelligent Transportation Systems, 2025, 26(7): 9579-9592. (中科院一区Top, IF=8.4)

[9]. Runliang Niu, Qi Wang*, He Kong, Qianli Xing, Yi Chang, Philip S Yu. Learn to explain transformer via interpretation path by reinforcement learning. Neural Networks, 2025, 188: 107496. (CCF B, IF=6.3)

[10]. Qingquan Zhao, Qi Wang*. Contrastive learning for extracting transferable user profiles in cross-domain recommendation system. In proceedings of the 2024 International Joint Conference on Neural Networks (IJCNN’24), Japan, June 30-July 5, 2024: 1-8. (CCF C)

[11]. Rui Cao, Shijie Xue, Qi Wang*, He Kong, Runliang Niu, Qianli Xing, Deyang Zhang. CCSGAD: A Collaborative Contrastive Self-Supervised Learning Model for Graph Anomaly Detection. In proceedings of the 2025 International Joint Conference on Neural Networks(IJCNN’25), Italy, June 30-July 5, 2025: 1-8. (CCF C)

[12]. Shijie Xue, He Kong, Qi Wang*. Dual contrastive learning for anomaly detection in attributed networks. In proceedings of the International Conference on Intelligent Information Processing, China, May 3–6, 2024: 3-18.

return