Hyuk Kwon

I am a Ph.D. student at Yonsei University Machine Learning Lab, under the guidance of Prof. Kibok Lee. My research focuses on how visual models learn and adapt across diverse tasks and settings, and how to evaluate their performance and reliability. Since real-world data rarely matches what a model was trained on, I am especially interested in how models handle this gap and how we can tell whether they will still work. Recently, my interests have expanded to world models and physical AI.

Research interests: Open-world learning · Vision-language models · (Automatic) model evaluation · World models · Physical AI

Email  /  GitHub  /  LinkedIn  /  Google Scholar  /  CV