Tao Li received a B.S. in Mathematics with summa cum laude from Xiamen University, Fujian, China, in 2018 and a Ph.D. in Electrical and Computer Engineering from New York University (NYU) in 2025. He was a visiting scholar at IBM Research Thomas J. Watson Research Center before joining City University of Hong Kong, where he is currently an assistant professor in the Department of Systems Engineering.
His research interests include game theory, control and optimization, reinforcement learning, and multi-agent learning with applications to secure and resilient cyber-physical network system design, defense, and management. His continued enthusiasm and efforts have won him the NSERC Mitacs-Globalink Research Award and the NYU Dante Youla Award for research excellence. He is recognized by IEEE ComSoc as a rising star in AI and Machine Learning in Security.
Awards and Achievements
- Oct 2024 “Rising Star in AI and Machine Learning in Security” IEEE Communication Society.
- May 2024 “Dante Youla Award For Research Excellence” New York University.
- Oct 2019 “Best Student Paper Finalist” IEEE International Workshop on Machine Learning for Signal Processing.
- Oct 2017 “Mitacs-Globalink Research Award” Natural Sciences and Engineering Research Council of Canada.
Previous Experience
- May 2025 - Aug 2025, Visiting Scholar, IBM Research.
- Jun 2024 - Sep 2024, Visiting Scholar, Coordinated Science Lab, UIUC.
Journal
- Pan, Yunian. , Li, Tao. & Zhu, Quanyan. (Dec 2025). Model-agnostic Hessian-free meta-policy optimization via zeroth-order estimation: A linear quadratic regulator perspective. Dynamic Games and Applications. doi:10.1007/s13235-025-00693-9
- Li, Tao. et al.,. (Sep 2025). Digital twin-based driver risk-aware predictive mobility analytics for real-time situational awareness through cooperative sensing. IEEE Transactions on Intelligent Transportation Systems. doi:10.1109/TITS.2025.3604569
- Yang, Ya-Ting. , Li, Tao. & Zhu, Quanyan. (Jul 2025). Transparent tagging for strategic social nudges on user-generated misinformation. IEEE Transactions on Network Science and Engineering. doi:10.1109/TNSE.2025.3591983
- Hammar, Kim. , Li, Tao. , Stadler, Rolf. & Zhu, Quanyan. (Apr 2025). Adaptive security response strategies through conjectural online learning. IEEE Transactions on Information Forensics and Security. doi:10.1109/TIFS.2025.3558600
- Li, Tao. et al.,. (Mar 2025). Digital twin-enhanced wireless indoor navigation: Achieving efficient environment sensing with zero-shot reinforcement learning. IEEE Open Journal of the Communications Society. doi:10.1109/OJCOMS.2025.3552277
- Li, Tao. et al.,. (Aug 2024). Multi-level traffic-responsive tilt camera surveillance through predictive correlated online learning. Transportation Research Part C: Emerging Technologies. doi:10.1016/j.trc.2024.104804
- Li, Tao. , Peng, Guanze. , Zhu, Quanyan. & Basar, Tamer. (Aug 2022). The confluence of networks, games, and learning: A game-theoretic framework for multiagent decision making over networks. IEEE Control Systems. doi:10.1109/MCS.2022.3171478
- Li, Tao. , Zhao, Yuhan. & Zhu, Quanyan. (Mar 2022). The role of information structures in game-theoretic multi-agent learning Author links open overlay panel. Annual Reviews in Control. doi:10.1016/j.arcontrol.2022.03.003
- Han, Bin. , Li, Tao. & Zhuang, Xiaosheng. (May 2019). Directional compactly supported box spline tight framelets with simple geometric structure. Applied Mathematics Letters. doi:10.1016/j.aml.2018.12.016
Conference Paper
- Li, Tao. , Lei, Haozhe. , Yin, Mingsheng. & Hu, Yaqi. (Aug 2025). Reinforcement learning with physics-informed symbolic program priors for zero-shot wireless indoor navigation. 2025 Reinforcement Learning Conference (RLC). Edmonton. Canada: Spotlight, Best Paper Award Runner Up.
- Li, Tao. , Guevara, Juan. , Xie, Xinhong. & Zhu, Quanyan. (May 2025). Self-confirming transformer for belief-conditioned adaptation in offline multi-agent reinforcement learning. The 24th International Conference on Autonomous Agents and Multiagent Systems (AAMAS). Detriot, MI. USA: Best Paper Runner Up.
- Li, Tao. , Hammar, Kim. , Stadler, Rolf. & Zhu, Quanyan. (Dec 2024). Conjectural online learning with first-order beliefs in asymmetric information stochastic games. 2024 IEEE 63rd Conference on Decision and Control (CDC). Milan. Italy: doi:https://doi.org/10.1109/CDC56724.2024.10886479
- Pan, Yunian. , Li, Tao. & Zhu, Quanyan. (Dec 2023). Is stochastic mirror descent vulnerable to adversarial delay attacks? A traffic assignment resilience study. 2023 62nd IEEE Conference on Decision and Control (CDC). Singapore. doi:https://doi.org/10.1109/CDC49753.2023.10384003
- Li, Tao. & Zhu, Quanyan. (Dec 2023). On the price of transparency: A comparison between overt persuasion and covert signaling. 2023 62nd IEEE Conference on Decision and Control (CDC). Singapore. doi:https://doi.org/10.1109/CDC49753.2023.10383897
- Li, Tao. , Lei, Haozhe. & Zhu, Quanyan. (Jun 2023). Self-adaptive driving in nonstationary environments through conjectural online lookahead adaptation. 2023 IEEE International Conference on Robotics and Automation (ICRA). London. UK: doi:https://doi.org/10.1109/ICRA48891.2023.10161368
- Ge, Yunfei. , Li, Tao. & Zhu, Quanyan. (May 2023). Scenario-agnostic zero-trust defense with explainable threshold policy: A meta-learning approach. 2023 IEEE Conference on Computer Communications (INFOCOM)). Hoboken, NJ. USA: doi:https://doi.org/10.1109/INFOCOMWKSHPS57453.2023.10225816
- Li, Tao. , Peng, Guanze. & Zhu, Quanyan. (Apr 2021). Blackwell online learning for Markov decision processes. 2021 55th Annual Conference on Information Sciences and Systems (CISS). Baltimore, MD. USA: doi:https://doi.org/10.1109/CISS50987.2021.9400319
- Li, Tao. & Zhu, Quanyan. (Oct 2019). On convergence rate of adaptive multiscale value function approximation for reinforcement learning. 2019 IEEE 29th International Workshop on Machine Learning for Signal Processing (MLSP). Pittsburgh, PA. USA: Best Student Paper Award Runner Up. doi:https://doi.org/10.1109/MLSP.2019.8918816
Book Chapter
- Li, Tao. & Zhu, Quanyan. (Aug 2025). Symbiotic game and foundation models for cyber deception operations in strategic cyber warfare. Foundations of Cyber Deception. Springer Cham. 978-3-031-93866-5.
- Li, Tao. , Pan, Yunian. & Zhu, Quanyan. (Feb 2024). Decision-dominant strategic defense against lateral movement for 5G zero-trust multi-domain networks. Network Security Empowered by Artificial Intelligence. Springer Cham. 978-3-031-53509-3. doi:10.1007/978-3-031-53510-9_2
External Services
Professional Activity
- Mar 2024 - Now, IEEE Control Systems Society Security and Privacy Early Career Committee Chair.
Service in CityUHK
Teaching Service
- Sep 2025 - Now, SYE2010 Fundamental Engineering Analysis and Design for Manufacturing Engineers.
Openings
- I am always actively looking for self-motivated students to join my research group as PhD students, research assistants (long/short-term/remote), and interns. We welcome applicants with
-
strong mathematical backgrounds in reinforcement learning, control and optimization, and game theory and/or
-
practical experience with RL algorithms, large language models (foundation models), and simulation platforms in cybersecurity (e.g., those included in this repo), vehicular, and traffic simulation (e.g., CARLA and SUMO).
For more information, please check out the openings listed on my personal website.
Due to the high volume of messages I receive at my school email, to ensure I see your message, please send all inquiries to my personal email address: taoli.cityuhk@gmail.com
Last update date :
09 Jan 2026
