Papers

* denotes equal contribution

Preprints

• Resolvent-Type Data-Driven Learning of Generators for Unknown Continuous-Time Dynamical Systems
  Yiming Meng*, Ruikun Zhou*, Melkior Ornik, and Jun Liu
  Submitted to IEEE Transactions on Automatic Control, under review.

PhD Thesis

• Learning-Based Stability Certification and System Identification of Nonlinear Dynamical Systems
  Ruikun Zhou
  PhD thesis, University of Waterloo, 2025.

Journal Papers

• Learning Regions of Attraction in Unknown Dynamical Systems via Zubov-Koopman Lifting: Regularities and Convergence
  Yiming Meng, Ruikun Zhou, and Jun Liu
  IEEE Transactions on Automatic Control, 2025.

• Physics-informed neural network Lyapunov functions: PDE characterization, learning, and verification
  Jun Liu, Yiming Meng, Maxwell Fitzsimmons, and Ruikun Zhou
  Automatica, Vol. 175: 112193, 2025.

• Physics-Informed Extreme Learning Machine Lyapunov Functions
  Ruikun Zhou, Maxwell Fitzsimmons, Yiming Meng, and Jun Liu
  IEEE Control Systems Letters, Vol. 8: 1763–1768, 2024.

• A Model-Free Kullback-Leibler Divergence Filter for Anomaly Detection in Noisy Data Series
  Ruikun Zhou, Wail Gueaieb, and Davide Spinello
  Journal of Dynamic Systems, Measurement, and Control, 145(2), 2023.

Machine Learning Conference Papers

• Data-driven optimal control of unknown nonlinear dynamical systems using the Koopman operator
  Zhexuan Zeng, Ruikun Zhou, Yiming Meng, and Jun Liu
  7th Annual Learning for Dynamics & Control Conference (L4DC), 2025.

• Physics-Informed Neural Network Policy Iteration: Algorithms, Convergence, and Verification
  Yiming Meng*, Ruikun Zhou*, Amartya Mukherjee, Maxwell Fitzsimmons, Christopher Song, and Jun Liu
  International Conference on Machine Learning (ICML), 2024.

• Neural Lyapunov Control of Unknown Nonlinear Systems with Stability Guarantees
  Ruikun Zhou, Thanin Quartz, Hans De Sterck, and Jun Liu
  Advances in Neural Information Processing Systems (NeurIPS), 2022.

Control Conference Papers

• Learning Koopman-based Stability Certificates for Unknown Nonlinear Systems
  Ruikun Zhou, Yiming Meng, Zhexuan Zeng, and Jun Liu
  2025 64th IEEE Conference on Decision and Control (CDC), 2025.

• Safe Domains of Attraction for Discrete-Time Nonlinear Systems: Characterization and Verifiable Neural Network Estimation
  Mohamed Serry*, Haoyu Li*, Ruikun Zhou*, Huan Zhang, and Jun Liu
  2025 64th IEEE Conference on Decision and Control (CDC), 2025.

• Stochastic reinforcement learning with stability guarantees for control of unknown nonlinear systems
  Thanin Quartz, Ruikun Zhou, Hans De Sterck, and Jun Liu
  2025 64th IEEE Conference on Decision and Control (CDC), 2025.

• Formally Verified Physics-Informed Neural Control Lyapunov Functions
  Jun Liu, Maxwell Fitzsimmons, Ruikun Zhou, and Yiming Meng
  2025 American Control Conference (ACC), pages 1347-1354, 2025.

• Zubov-Koopman Learning of Maximal Lyapunov Functions
  Yiming Meng, Ruikun Zhou, and Jun Liu
  2024 American Control Conference (ACC), pages 4020–4025, 2024.

• Compositionally verifiable vector neural Lyapunov functions for stability analysis of interconnected nonlinear systems
  Jun Liu, Yiming Meng, Maxwell Fitzsimmons, and Ruikun Zhou
  2024 American Control Conference (ACC), pages 4789–4794, 2024.

• Physics-informed neural networks for stability analysis and control with formal guarantees
  Jun Liu, Yiming Meng, Maxwell Fitzsimmons, and Ruikun Zhou
  27th ACM International Conference on Hybrid Systems: Computation and Control (HSCC), pages 1–2, 2024.

• Tool LyZNet: A lightweight Python tool for learning and verifying neural Lyapunov functions and regions of attraction
  Jun Liu, Yiming Meng, Maxwell Fitzsimmons, and Ruikun Zhou
  27th ACM International Conference on Hybrid Systems: Computation and Control (HSCC), pages 1–8, 2024.

• Koopman-based learning of infinitesimal generators without operator logarithm
  Yiming Meng, Ruikun Zhou, Melkior Ornik, and Jun Liu
  2024 63rd IEEE Conference on Decision and Control (CDC), 2024.

• LyZNet with Control: Physics-Informed Neural Network Control of Nonlinear Systems with Formal Guarantees
  Jun Liu, Yiming Meng, and Ruikun Zhou
  8th IFAC Conference on Analysis and Design of Hybrid Systems (ADHS), 2024.

• Towards learning and verifying maximal neural Lyapunov functions
  Jun Liu, Yiming Meng, Maxwell Fitzsimmons, and Ruikun Zhou
  2023 62nd IEEE Conference on Decision and Control (CDC), pages 8012–8019, 2023.