Dr. Xianyuan Zhan is a research assistant professor at the Institute for AI Industry Research (AIR), Tsinghua University. Before joining AIR, Dr. Zhan was a data scientist at JD Technology and also a researcher at Microsoft Research Asia (MSRA). Dr. Zhan previously led the research and development of AI-driven industrial system optimization products at JD Technology. He has published more than 40 papers in top international journals and conferences, and applied more than 20 patents. Dr. Zhan is also a reviewer for many top transportation and computer science journals and conferences. He is currently a committee member of China Computer Federation-Artificial Intelligence & Pattern Recognition (CCF-AI) Committee.
Education
2013-2017 Purdue University Transportation Systems PhD
2014-2016 Purdue University Computer Science M.S
2011-2012 Purdue University Transportation Systems M.S.E.
2007-2011 Tsinghua University Civil Engineering B.E.
Work experience
2021-present Institute for AI Industry Research, Tsinghua University Research Assistant Professor
2018-2021 JD Technology Data Scientist/Senior Researcher
2017-2018 Microsoft Research Asia Associate Researcher
Personal website
http://zhanxianyuan.xyz/
Email address
zhanxianyuan@air.tsinghua.edu.cn
Research interest
Offline deep reinforcement learning
Complex system optimization
Urban computing
Big data analytics in transportation
Publications
1. Xu, H., Li, J., Li, J., Zhan, X. A Policy-Guided Imitation Approach for Offline Reinforcement Learning. NeurIPS 2022.
2. Niu, H., Sharma, S., Qiu, Y., Li, M, Zhou G., Hu, J., Zhan, X. When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning. NeurIPS 2022.
3. Zhang, W., Xu, H., Niu, H., Cheng, P, Li, M., Zhang, H., Zhou G., Zhan, X. Discriminator-Guided Model-Based Offline Imitation Learning. CoRL 2022.
4. Xu, H., Zhan, X., Yin, H. and Qin, H. Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations. ICML 2022.
5. Liu, S., Weng, D., Tian, Y., Deng, Z., Xu, H., Zhu, X., Yin, H., Zhan, X., Wu, Y. ECoalVis: Visual Analysis of Control Strategies in Coal-fired Power Plants. IEEE VIS 2022.
6. Yu, Q., Lou, J., Zhan, X., Li, Q., Liu, J., Zuo W. and Liu, Y. Adversarial Contrastive Learning via Asymmetric InfoNCE. ECCV 2022.
7. Zhan, X., Zhu, X. and Xu, H. Model-Based Offline Planning with Trajectory Pruning. IJCAI 2022.
8. Zhan, X., Xu, H., Zhang, Y., Zhu, X. and Yin, H. DeepThermal: Combustion Optimization for Thermal Power Generating Units Using Offline Reinforcement Learning. AAAI 2022.
9. Xu, H., Zhan, X., and Zhu, X. Constraints Penalized Q-Learning for Safe Offline Reinforcement Learning. AAAI 2022.
10. Qin, H., Zhan, X., and Zheng, Y. CSCAD: Correlation Structure-based Collective Anomaly Detection in Complex System. IEEE TKDE, 2022.
11. Qin, H., Zhan, X., Li, Y., Yang, X. and Zheng, Y. Network-Wide Traffic States Imputation Using Self-interested Coalitional Learning. KDD 2021.
12. Qin, H., Ke, S., Yang, X., Xu, H., Zhan, X. and Zheng, Y. Robust Spatio-Temporal Purchase Prediction via Deep Meta Learning. AAAI 2021.
Honors & Awards
Selected in Baidu's "AI Chinese Young Scholars List"
2020: 2019 Synced Machine Intelligence Awards: 30 Best AI Use Cases of the Year, SYNCED
2018: Artificial Intelligence Innovation Award, CAIS 2018
2016: James S. McDonnell Foundation (JSMF) Postdoctoral Fellowship Award in Studying Complex Systems, James S. McDonnell Foundation
