I am currently a postdoctoral associate in the Department of Mathematics at Hong Kong University of Science and Technology, jointly advised by Prof. Can Yang and Prof. Jianping Gan. I completed my Ph.D. at the University of Electronic Science and Technology of China, under the supervision of Prof. Wenyu Chen and Prof. Hong Qu. I received my Bachelor degree at the University of Electronic Science and Technology of China, advised by Prof. Hancong Duan.

My research interests include:

1. AI for Scientific Discovery: discover scientific concept from noisy observational data, with application in Ocean and life science.
2. Reinforcement Learning: offline reinforcement learning, multi-agent reinforcement learning.

🔥 News

• 2025.09: 🎉 One paper was accepted by IEEE Transactions on Neural Networks and Learning Systems.
• 2025.08: 🎉 One paper was accepted by Nature Communications.
• 2023.10: 🎉 Join YangLab@HKUST as Postdoctoral Associate.

📝 Publications

Selected Publications

• AI-powered Spatiotemporal Imputation and Prediction of Chlorophyll-a Concentration in Coastal Oceans [Paper][Code]

  Fan Zhang, Hiusuet Kung, Fa Zhang, Can Yang#, Jianping Gan#.

  Nature Communications, 2025, 16(1): 7656.

• Inhibiting Error Exacerbation in Offline Reinforcement Learning with Data Sparsity. [Paper]

  Fan Zhang, Malu Zhang#, Wenyu Chen, Siying Wang, Xin Zhang, Jiayin Li, Yang Yang.

  IEEE Transactions on Neural Networks and Learning Systems, doi:10.1109/TNNLS.2025.3615982

• An Attention-Based Interactive Learning-to-Rank Model for Document Retrieval. [Paper][Code]

  Fan Zhang, Wenyu Chen, Mingsheng Fu, Fan Li, Hong Qu#, Zhang Yi.

  IEEE Transactions on Systems, Man, and Cybernetics: Systems. 2022, 52(9): 5770-5782.

Publications

• GPAS: Accelerating Convergence of LLM Pretraining via Gradient-Preserving Activation Scaling [Paper]

  Tianhao Chen, Xin Xu, Zijing Liu, Pengxiang Li, Xinyuan Song, Ajay Kumar Jaiswal, Fan Zhang, Jishan Hu, Yang Wang, Hao Chen, Shizhe Diao, Shiwei Liu, Yu Li, Lu Yin, Can Yang

  The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeuIPS 2025)

• Toward Energy-Efficient Spike-Based Deep Reinforcement Learning With Temporal Coding [Paper]

  Malu Zhang, Shuai Wang, Jibin Wu, Wenjie Wei, Dehao Zhang, Zijian Zhou, Siying Wang, Fan Zhang, Yang Yang

  IEEE Computational Intelligence Magazine, 2025, 20(2): 45-57

• Sequence value decomposition transformer for cooperative multi-agent reinforcement learning [Paper]

  Zhitong Zhao, Ya Zhang, Wenyu Chen, Fan Zhang, Siying Wang, Yang Zhou

  Information Science, 2025, 122514

• Decoupled Feature Matching for Few-shot Counting and Localization. [Paper]

  Chao Zhai, Fan Zhang, Wenyu Chen#, Malu Zhang, Fan Li, Xuanting Xie.

  2025 International Conference on Acoustics, Speech, and Signal Processing

• Class-Agnostic Counting and Localization with Feature Augmentation and Scale-Adaptive Aggregation. [Paper]

  Chao Zhai, Yuhui Du, Hong Qu, Tianlei Wang, Fan Zhang, Mingsheng Fu, Wenyu Chen#.

  Knowledge-Based Systems, 2024, 112104

• QDAP: Downsizing adaptive policy for cooperative multi-agent reinforcement learning. [Paper]

  Zhitong Zhao, Ya Zhang, Siying Wang, Fan Zhang, Malu Zhang, Wenyu Chen.

  Knowledge-Based Systems, 2024, 294: 111719

• A novel self-supervised representation learning framework based on time-frequency alignment and interaction for mechanical fault diagnosis. [Paper]

  Daxing Fu, Jie Liu, Hao Zhong, Xin Zhang#, Fan Zhang.

  Knowledge-Based Systems, 2024: 111846

• A pruned-optimized weighted graph convolutional network for axial flow pump fault diagnosis with hydrophone signals. [Paper]

  Xin Zhang, Li Jiang, Lei Wang, Tianao Zhang, Fan Zhang.

  Advanced Engineering Informatics, 2024, 60: 102365

• Regularization-Adapted Anderson Acceleration for multi-agent reinforcement learning. [Paper]

  Siying Wang, Wenyu Chen, Liwei Huang, Fan Zhang, Zhitong Zhao, Hong Qu#.

  Knowledge-Based Systems. 2023, 275: 110709.

• Neural Reranking-Based Collaborative Filtering by Leveraging Listwise Relative Ranking Information. [Paper]

  Fan Li, Hong Qu#, Mingsheng Fu, Liyan Zhang, Fan Zhang, Wenyu Chen, Ruixuan Sun, Haixian Zhang.

  IEEE Transactions on Systems, Man, and Cybernetics: Systems. 2023, 53(2): 882-896.

• Improving Exploration in Actor-Critic with Weakly-pessimistic Value Estimation and Optimistic Policy Optimization. [Paper]

  Fan Li, Mingsheng Fu#, Wenyu Chen, Fan Zhang, Haixian Zhang, Hong Qu#, Zhang Yi.

  IEEE Transactions on Neural Networks and Learning Systems, doi: 10.1109/TNNLS.2022.3215596.

Preprints

• GraphKAN: Enhancing Feature Extraction with Graph Kolmogorov Arnold Networks. [Paper]

  Fan Zhang, Xin Zhang#.

• A Heterogeneous Value Decomposition Policy Fusion Scheme for Multi-Agent Cooperation [Under review]

  Siying Wang, Yang Zhou, Ruoning Zhang, Zhitong Zhao, Fan Zhang#, Jinliang Shao, Yuhua Cheng

• Pessimistic Auxiliary Policy for Offline Reinforcement Learning. [Under review]

  Fan Zhang , Hongrui Wang, Baoru Huang, Xin Zhang#

• Taming the heterogeneous dynamics in ocean chlorophyll-a concentration prediction with a deep learning model.

  Fa Zhang, Hiusuet Kung, Fan Zhang, Zhiwei Wang, Can Yang#, Jianping Gan#.

💻 Professional Experience

• 2023.10 - Now, Postdoctoral Associate, The Hong Kong University of Science and Technology.

🎓 Education

• 2017.09 - 2023.08, Ph.D. in Computer Science and Technology, The University of Electronic Science and Technology of China.
• 2013.09 - 2017.06, B.Sc. in Computer Science and Technology, The University of Electronic Science and Technology of China.

💬 Service

Invited Journal Reviewer:

• IEEE Transactions on Cybernetics, Knowledge-based System, Advanced Engineering Informatics, Neurocomputing, Information Science, IEEE/CAA Journal of Automatica Sinica, Engineering Applications of Artificial Intelligence

Invited Conference Reviewer:

• IJCNN (2021, 2022)
• AAAI (2026)
• ICLR (2026)

📖 Teaching

• 2019.09-2020.06, Finite Automata Theory, Teaching Assistant, UESTC.