I am an assistant professor in School of Computing and Augmented Intelligence at Arizona State University. My research focuses on scientific machine learning, including data-driven surrogate modeling for fluid dynamics and plasma physics, neural representations of scientific fields, and physics-informed and structure-preserving modeling of dynamical systems. My work has been supported by the National Science Foundation (NSF), Sandia National Laboratories, Salt River Project (SRP), Honeywell, Applied Materials, and Meta. I received the NSF CAREER Award in 2024 and the KOCSEA Young Faculty Award (K-YFA) in 2026.

Research Highlights

Structure-preserving dynamics modeling: Develop machine learning models that embed physical laws, such as energy conservation and entropy production, directly into their architecture for stable and reliable long-term prediction. [NeurIPS 2021,MSML 2022,NeurIPS 2023,ICLR 2025,TMLR 2026,ICML 2026] Learn more →

Implicit neural representations (INRs)/physics-informed neural networks (PINNs): Develop continuous neural function representations for complex and structured signals, enabling resolution-independent modeling and principled learning under known constraints. [AAAI 2021,NeurIPS 2023,ICML 2024,ICLR 2025,NeurIPS 2025]
Learn more →

Reduced-order models (ROMs)/Neural operators (NOs): Develop data-driven surrogate modeling of complex dynamics, NOs: [AAAI 2024,ICLR 2024,ICLR 2026]

Recent News