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 asks whether multimodal models can actually use the information available to them—and how we can verify that they do. Spatial information may be present in an image yet encoded in a form that a model cannot effectively exploit. In Perspective-Aware Reasoning (./publications) and Token Warping (./publications), I address this by transforming the representations that models reason over rather than the pixels themselves.
But improved accuracy alone does not show that a model relied on the right evidence. In Retrieval Heads Meet Vision (./publications), I identify a small set of attention heads (Visual Retrieval Heads) that carry visual evidence and causally test their role in grounding by masking them. I am now extending this line of inquiry over time: asking what long-horizon models should retain in memory, when stale internal states should be revised, and how these mechanisms can support multimodal agents that perceive, reason, and interact in real-world environments.
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