Sungwon Kim

I am Sungwon Kim (pronounced “Sung-won”), a Ph.D. candidate in the Graduate School of Data Science (GSDS) at KAIST, where I am advised by Prof. Chanyoung Park. I hold a B.S. degree in Civil, Environmental and Architectural Engineering from Korea University.

I am currently a Visiting Researcher at Caltech, hosted by Prof. Anima Anandkumar.

I am actively engaged in research with my colleagues at the Data Science and Artificial Intelligence Lab.

---

🔬 Core Research Focus

Generalizable Geometry Representation for AI4Engineering / SciML

I work on how geometry should be represented so that AI surrogates for 3D simulation generalize beyond the conditions they were trained on — unseen boundary conditions, unfamiliar shape families, and arbitrary orientations, without retraining.

Keywords: Physics AI (Engineering), Geometry Representation, 3D Simulation, Neural Operators

Key Focus:

• Geometry-Generalizability: Coordinate-free, frame-invariant representations that transfer across unseen geometries and boundary conditions.
• Scalability: Surrogates that scale to industrial-level 3D problems with high resolution and geometric complexity.
• Usability: Surrogates that fit into practical engineering workflows.