Zhaobin Mo - 莫钊镔

I am currently a final-year Ph.D. student in Civil Engineering at Columbia University advised by Prof. Xuan Di (Ditect Lab). I was recognized as a President Fellow and Mindlin Scholar at CU. Before joining CU, I received a B.E. from Tsinghua University in 2017.

My research focuses on physics-informed deep learning that facilitates the integration of domain knowledge and deep learning models. I am passionate about exploring how prior knowledge can foster safe, robust, and explainable AI. I have also worked on other topics like reinforcement learning, graph neural networks, and probabilistic graphical models.

Email  /  CV (last updated: July 2023)  /  Google Scholar  /  Github

Robust Data Sampling in Machine Learning: A Game-Theoretic Framework for Training and Validation Data Selection

Longitudinal Control Strategy for Connected Electric Vehicle with Regenerative Braking in Eco-approach and Departure

Detecting Mild Cognitive Impairment and Dementia in Older Adults using Naturalistic Driving Data and Interaction-based Classification from Influence Score

TrafficFlowGAN: Physics-Informed Flow Based Generative Adversarial Network for Uncertainty Quantification

Uncertainty Quantification of Car-following Behaviors: Physics-informed Generative Adversarial Networks

Quantifying Uncertainty in Traffic State Estimation using Generative Adversarial Networks

CVLight: Decentralized Learning for Adaptive Traffic Signal Control with Connected Vehicles

Physics-informed Deep Learning for Traffic State Estimation: A Hybrid Paradigm Informed by Second-order Traffic Models

A Physics-informed Deep Learning Paradigm for Car-following Models

A Physics-informed Deep Learning Paradigm for Traffic State and Fundamental Diagram Estimation

Multimedia Fusion at Semantic Level in Vehicle Cooperative Perception