Yiming Meng

I am an incoming Assistant Professor in the AI Thrust at the Information Hub, HKUST(GZ). I received my Ph.D. in Applied Mathematics from the University of Waterloo in October 2022, advised by Dr. Jun Liu and Dr. N. Sri Namachchivaya, with research in control and dynamical systems (including partial differential equations). I have held multiple postdoctoral research positions at the Coordinated Science Laboratory, University of Illinois Urbana-Champaign (UIUC), where I worked with Dr. Melkior Ornik, as well as at the Department of Applied Mathematics, University of Waterloo, where I worked with Dr. Jun Liu.

My research addresses “intelligent” control synthesis for nonlinear dynamical systems operating in uncertain environments from a bottom-up perspective, with applications in diverse fields such as robotics, cyber-physical systems, mechanics, and other physical sciences.

• 2026/03 Our work ‘Online Learning and Control Synthesis for Reachable Paths of Unknown Nonlinear Systems’ and its derived algorithm for underactuated systems ‘Reachable Predictive Control: A Novel Control Algorithm for Nonlinear Systems with Unknown Dynamics and its Practical Applications’ have been accepted to IEEE TAC and ICRA 2026, respectively.

• 2026/01 Our work ‘Resolvent-Type Data-Driven Learning of Generators for Unknown Continuous-Time Dynamical Systems’ on Koopman generator learning is accepted to IEEE TAC.

• 2025/10 Our work ‘Learning Regions of Attraction in Unknown Dynamical Systems via Zubov–Koopman Lifting: Regularities and Convergence’, accepted to IEEE TAC, is now available online.

• 2025/07 One paper accepted to CDC 2025.

• 2025/06 Work ‘Data-driven Optimal Control of Unknown Nonlinear Dynamical Systems Using the Koopman Operator’ presented at L4DC 2025.

• 2025/06 Our work on PINNs with formal verification for Lyapunov functions is now online in Automatica and was selected as the Editor’s Choice for May.

• 2025/05 A talk ‘Towards Intelligent Data-Driven Verification of Stability and Safety for Unknown Nonlinear Systems’ was given at Polytechnique Montréal, invited by Prof. Bowen Yi and hosted by GERAD.
  

See all posts

• Resolvent-Type Data-Driven Learning of Generators for Unknown Continuous-Time Dynamical Systems.
  Y. Meng\(^\star\), R. Zhou\(^\star\), M. Ornik, J. Liu.
  IEEE Transactions on Automatic Control, 2026. (DOI)

• Learning Regions of Attraction in Unknown Dynamical Systems via Zubov- Koopman Lifting: Regularities and Convergence.
  Y. Meng, R. Zhou, J. Liu.
  IEEE Transactions on Automatic Control, 2025. (DOI)(PDF)

• Physics-Informed Neural Network Lyapunov Functions: PDE Characterization, Learning, and Verification.
  J. Liu, Y. Meng, M. Fitzsimmons, R. Zhou.
  Automatica, 2025. (DOI)(PDF) Editor’s Choice for May 2025

• Physics-Informed Neural Network Policy Iteration: Algorithms, Convergence, and Verification.
  Y. Meng\(^\star\), R. Zhou\(^\star\), A. Mukherjee, M. Fitzsimmons, C. Song, J. Liu.
  International Conference on Machine Learning (ICML). @ Vienna, Austria, 2024. (DOI)(PDF)

• Stochastic Lyapunov-Barrier Functions for Robust Probabilistic Reach-Avoid-Stay Specifications.
  Y. Meng, J. Liu.
  IEEE Transactions on Automatic Control, 2024. (DOI)(PDF)

• Hopf Bifurcations of Moore-Greitzer PDE Model with Additive Noise.
  Y. Meng, N.S. Namachchivaya, N. Perkowski.
  Journal of Nonlinear Science, 2023. (DOI)(PDF)

• Smooth Converse Lyapunov-Barrier Theorems for Asymptotic Stability wit Safety Constraints and Reach-Avoid-Stay Specifications.
  Y. Meng, Y. Li, M. Fitzzsimmons, J. Liu.
  Automatica, 2022. (DOI)(PDF)
  

See all publications