Jun Seong Kim

Hello! I am a first-year master's student at KAIST's School of Computing, advised by Professor Alice Oh in the U&I Lab.

My research focuses on benchmarking AI models and measuring their robustness to identify failure modes, with the broader goal of making AI systems more transparent and reliable. More recently, I have become interested in mechanistic interpretability as a way to look beyond model outputs and better understand the internal representations and computations that drive model behavior.

I am always open to new collaborations. Please feel free to reach out at [email protected].