Sungwon Kim

I’m a Ph.D. candidate in Graduate School of Data Science at KAIST, where I am fortunate to be advised by Prof. Chanyoung Park.

I’m actively on research with my best colleagues at Data Science and Artificial Intelligence Lab.

My research is largely data-driven, aiming to solve challenging problems in real-world scenarios.

• Physics-AI, Learning-based 3D Simulation (Collaboration with LG Electronics)
  • How can we create a learning-based alternative to the FEM for 3D inputs with highly complex geometries, given the initial and boundary conditions? (Point-cloud based)
  • How can we efficiently interact with opposing surfaces while maintaining computational efficiency? (Mesh based)
• Data-driven AI (Federated Learning)
  • What distributed knowledge truly helps improve other clients?
  • How can we generate synthetic data without compromising privacy?
  • How can we personalize local models without forgetting global knowledge?
• Data-Efficient Deep Learning
  • How can we generalize underlying semantics with extremely limited training data?

I actively seek practical challenges from the real world, regardless of domain. Recently, I’ve been especially focused on 3D analysis and scientific problems.