Short Bio

[Curriculum Vitæ]

I am Ph.D. student in Computer Science at Yonsei University under the advisement of Prof. Seong Jae Hwang at MICV.

My research interests revolve around deriving impactful insights from Transformers to deliver tangible improvements across multiple applications.

Specifically, I focus on Vision and Language Models (VLMs) and Large Vision-Language Models (LVLMs). For example, I’ve conducted research on enhancing semantic alignment and interpretability in LVLM.

Additionally, I’m deeply interested in exploring and advancing transformer-based generative methods in computer vision, particularly Diffusion Transformers, to further improve their effectiveness and versatility!

News

• [Feb. 2025] The paper Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding was selected as a highlight at CVPR 2025! (acceptance rate = 3.7%)
• [Feb. 2025] The paper Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding is accepted by CVPR 2025!
• [Feb. 2025] The paper See What You Are Told: Visual Attention Sink in Large Multimodal Models is accepted by ICLR 2025!
• [Jul. 2024] The paper Falcon is released!
• [Mar. 2024] The paper WoLF is released!
• [Mar. 2024] The paper CoBra is released!
• Show more
[Nov. 2023] I have transitioned from a M.S. program to an Ph.D. program.
[Mar. 2023] I got admitted at Yonsei College of Computing as a M.S. student. I will continue doing research at MICV Lab.