Tao Li

Tao Li

Assistant Professor

City University of Hong Kong

Research Interests

Game Theory
Control & Optimization
Reinforcement Learning

About

I am an assistant professor in the Department of Systems Engineering at City University of Hong Kong. I was a visiting researcher at the IBM Thomas J. Watson Research Center, collaborating with the Mathematical Sciences and Quantum Computing divisions in the summer of 2025. I earned my Ph.D. in Electrical and Computer Engineering from New York University, advised by Prof. Quanyan Zhu, where I also worked closely with Prof. Kaan Ozbay and Prof. Sundeep Rangan. My dissertation examines the triad of information, decision, and uncertainty in multi-agent learning. Prior to my doctoral studies, I conducted research in computational harmonic analysis under the supervision of Prof. Bin Han at the University of Alberta. I hold a B.S. in Mathematics, graduating summa cum laude from Xiamen University.

Research Overview

My research develops computational foundations of mulit-agent learning under complex information structures to achieve certified robustness and resilience in AI-integrated network systems across cyber, physical, and huamn layers. My recent research efforts focus on Agentic AI for Cyber-Physical Security and Resilience in Smart City.

My Erdős Number is 3

Paul Erdős (0) coauthored "On chagnes of signs in infinite series" (1978) with Charles K. Chui (1), who coauthored "A dual-chain approach for bottom–up construction of wavelet filters with any integer dilation" (2012) with Bin Han (2), who coauthored "Directional compactly supported box spline tight framelets with simple geometric structure" (2019) with me (3).

Selected Publications

View All →

Model-Agnostic Hessian-Free Meta-Policy Optimization via Zeroth-Order Estimation: A Linear Quadratic Regulator Perspective

Yunian Pan, Tao Li, Quanyan Zhu

Dynamic Games and Applications

A Hessian-free meta-learning algorithm for ergodic Linear Quadratic Regulator (LQR) tasks is introduced, which directly approximates the meta-policy gradient with zeroth-order information via Gaussian smoothing and Stein’s identity.

Digital twin-based driver risk-aware predictive mobility analytics for real-time situational awareness through cooperative sensing

Tao Li, Zilin Bian, Haozhe Lei, Fan Zuo, Ya-Ting Yang, Quanyan Zhu, Zhenning Li, Zhibin Chen, Kaan Ozbay

IEEE Transactions on Intelligent Transportation Systems

An urban traffic digital twin system that includes AI-powered traffic sensing and event-triggered adaptive calibration, which provides driver-centric situational awareness and predicts network-wide mobility and safety risks in real time.

Transparent tagging for strategic social nudges on user-generated misinformation

Ya-Ting Yang, Tao Li, Quanyan Zhu

IEEE Transactions on Network Science and Engineering

This paper establishes a Bayesian persuaded branching process to study social network platforms' (SNP) tagging policy design under misdetection of misinformation.

Adaptive security response strategies through conjectural online learning

Kim Hammar, Tao Li, Rolf Stadler, Quanyan Zhu

IEEE Transactions on Information Forensics and Security

A novel Conjectural Online Learning (COL) method for adaptive security response strategies in IT infrastructures, addressing model misspecification and uncertainty through Bayesian learning and rollout.

Multi-level traffic-responsive tilt camera surveillance through predictive correlated online learning

Tao Li, Zilin Bian, Haozhe Lei, Fan Zuo, Ya-Ting Yang, Quanyan Zhu, Zhenning Li, Kaan Ozbay

Transportation Research Part C: Emerging Technologies

An AI-powered pan-tilt camera-based traffic sensing system, composed of spatial-temporal graph transformer for real-time traffic estimation and camera control through distributed online convex optimization.

News

2026-01

🏆 Call for Nominations! We are accepting nominations for IEEE Control Systems Society Security & Privacy Rising Star.