Ph.D. in Intelligence and Information
Seoul National University
Ph.D. DissertationProjection, Persistence, and Elicitation of Learned Internal Structure

My research aims to understand the internal mechanisms of foundation models and turn these insights into methods for controlling and adapting their behavior. My current work brings this perspective to robot agents, with the goal of enabling reliable interaction across language, vision, and action.
I am currently a postdoctoral researcher at KAIST, working with Prof. Jinwoo Shin. I received my Ph.D. from Seoul National University, where I was advised by Prof. Nojun Kwak.
Seoul National University
Ph.D. DissertationProjection, Persistence, and Elicitation of Learned Internal Structure
Seoul National University
B.S. ThesisImprovement of Elevator Control Algorithm Using Reinforcement Learning
I received the Best Ph.D. Dissertation Award as the representative awardee of the SNU Graduate School of Convergence Science and Technology (1 recipient among 27 Ph.D. graduates).
I will be at ACL 2026 in San Diego, presenting our long paper "Unlocking the Potential of Diffusion Language Models through Template Infilling" as an oral presentation!
I will be at CVPR 2026 in Denver, presenting our "CSF: Black-box Fingerprinting via Compositional Semantics for Text-to-Image Models" paper!
I was selected as an ICML 2026 Gold Reviewer, recognizing top reviewers for this year's conference.
Annual Meeting of the Association for Computational Linguistics (ACL 2026), 2026. Long Paper · Oral Presentation
The Conference on Neural Information Processing Systems (NeurIPS), 2024.
The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
GSCT, Seoul National University · 1 recipient among 27 Ph.D. graduates
USD 1,000
USD 3,500
USD 8,000
USD 3,000
full funded
full funded