Working and Preprints

• Non-Asymptotic Learning of Koopman Observables with Process Noise
  Xiong Zeng, Hyunjae Kim, and Necmiye Ozay. In preparation.

• From World Models to World Action Models: A Concise Tutorial for Robotics
  Xiaoxiong Zhang, Xiong Zeng, and Wei Zhang. ArXiv 2026.

Journal

• Noise Sensitivity of the Semidefinite Programs for Direct Data-Driven LQR
  [Slides], [Poster], [Thread on X]
  Xiong Zeng, Laurent Bako, and Necmiye Ozay. IEEE Transactions on Automatic Control (TAC) 2026.

• System Identification Under Bounded Noise: Optimal Rates Beyond Least Squares
  [Code], [Slides], [Poster]
  Xiong Zeng, Jing Yu, and Necmiye Ozay. IEEE Control Systems Letters (L-CSS) 2025, with presentation at CDC 2025.

Conference

• Benefits of Linear Dynamic State Feedback in Co-stabilization
  Xiong Zeng, Necmiye Ozay, and Mario Sznaier. IEEE Conference on Decision and Control (CDC) 2026.

• Noise Sensitivity of Direct Data-Driven Linear Quadratic Regulator by Semidefinite Programming
  Xiong Zeng, Laurent Bako, and Necmiye Ozay. American Control Conference (ACC) 2025 (O. Hugo Schuck Best Paper Award).

• On the Hardness of Learning to Stabilize Linear Systems
  [Slides], [Poster], [Video]
  Xiong Zeng, Zexiang Liu, Zhe Du, Necmiye Ozay, and Mario Sznaier. IEEE Conference on Decision and Control (CDC) 2023.