I am a Master’s Student in KAIST Visual AI Group led by Prof. Minhyuk Sung, affiliated with Graduate School of Metaverse at the Korea Advanced Institute of Science and Technology (KAIST).
My research aims to advance Spatial Intelligence by studying how multimodal models perceive, represent, and reason about the physical world. My recent work focuses on understanding the internal mechanisms of vision-language models, particularly how they internally retrieve, transform, and utilize visual information for spatial reasoning. In the long term, I am interested in building multimodal systems that can support perception, reasoning, and interaction in real-world environments, spanning vision-language models, robotics, world models, and embodied AI.
My Erdős number is 3 (Chanho Park → Leonidas Guibas → Frances Yao → Paul Erdős).
Rm. 510, Bldg. E3-5 (KRAFTON Building),
291 Daehak-ro, Yuseong-gu,
Daejeon, South Korea 34141
Office: E3-5, 510