Skip to content
Scalable Trustworthy AI Scalable Trustworthy AI

Interests

  • - Knowledge-Intelligence Separation, Fluid Intelligence
  • - Post-TF Architectures, Neuroscience-inspired AI Architecture
  • - AI Safety, Social Simulation

Biography

I am a PhD student at KAIST, supervised by Prof. Seong Joon Oh.

I design efficient, neuroscience-inspired AI architectures and interpretable, modular AI systems. My research focuses on separating core fluid intelligence from static knowledge to build next-generation architectures. Ultimately, I aim to combine these technical foundations with human-centric modeling to create AI systems that truly understand and align with human intention and emotion.

Before joining KAIST, I obtained my Bachelor’s degree in Biotechnology and Artificial Intelligence from Korea University, and my Master’s degree in Artificial Intelligence from Seoul National University (advised by Prof. MyungJoo Kang at the Department of Mathematical Sciences), where I focused on out-of-distribution reinforcement learning and contrastive learning for fMRI datasets. I also gained research experience as a student researcher at IBS (Institute for Basic Science).