Sinong (Simon) Zhan
I am a 3rd year PhD student in the ECE department at Northwestern University, advised by Qi Zhu. Before Northwestern, I did my undergrad in Applied Math and Computer Science at UC Berkeley, where I was advised by Sanjit A. Seshia. I am currently a Research Intern at Google Research, working with Maryam Karimzadehgan and Benny Schlesinger. Previously, I spent a great time as a research intern at Amazon SFAI.
Research
My research lies at the intersection of reinforcement learning, formal methods, and AI safety. I design safe and delay-robust RL algorithms that integrate formal verification — barrier certificates, constraint satisfaction — with learning-based control to provide provable guarantees for autonomous systems. More recently, I have been developing specification-guided frameworks that leverage formal specifications (temporal logics, program contracts) to systematically evaluate, steer, and explain foundation-model-based agents, addressing the challenge of bridging informal human safety intent and provably correct agent behavior. This agenda has led to publications in venues such as ICML, NeurIPS, ICLR, CVPR, CCS, ICCPS, L4DC, FM, RV, and IROS.
News
- 07/2026 Started my research internship at Google Research, working with Maryam Karimzadehgan and Benny Schlesinger.
- 06/2026 Token Buncher has been accepted to CCS 2026.
- 02/2026 One paper has been accepted to CVPR 2026.
- 01/2026 DT-CORL and Shop-R1 have been accepted to ICLR 2026.
- 01/2026 “Enhancing Inverse Reinforcement Learning through Encoding Dynamic Information in Reward Shaping” has been accepted to L4DC 2026.
- 10/2025 2 papers have been accepted to SEA@NeurIPS 2025.
- 05/2025 I will start my summer internship at Amazon as Applied Scientist in Palo Alto office. Happy to connect!
- 05/2025 Our paper “Directly Forecasting Belief for Reinforcement Learning with Delays” is accepted to ICML 2025.
- 10/2024 Our paper “Variational Policy Delayed Optimization” is accepted to NeurIPS 2024 (Spotlight!).
- 06/2024 Our paper “Kinematics-aware Trajectory Generation and Prediction with Latent SDE” is accepted to IROS 2024.
- 06/2024 Our paper “Case Study: Runtime Safety Verification of Neural Network Controlled System” is accepted to RV 2024.
- 06/2024 Our paper “Switching Controller Synthesis for Hybrid Systems Against STL Formulas” is accepted to FM 2024.
- 05/2024 Our paper “Boosting long delayed RL with auxiliary short delay” is accepted to ICML 2024.
- 05/2024 I will attend SSFT 2024. Please feel free to reach out if you are interested in my research.
- 04/2024 Our paper “State-wise Safe RL With Pixel Observations” is accepted to L4DC 2024.
- 03/2024 One paper accepted to LLMAgent@ICLR 2024.
- 09/2023 I will start my PhD journey at ECE department, Northwestern University.
Education
Experience
Selected Publications
Academic Service
- Conference reviewer: NeurIPS, ICML, ICLR, AAAI, CVPR, ECCV, L4DC, ASP-DAC, ECC
- Journal reviewer: Machine Learning (Springer), IEEE Internet of Things Journal
- Program committee: ICCPS Artifact Evaluation Committee