I am an M.S. student in the OSI Lab at KAIST AI, advised by Prof. Se-Young Yun. My current research focuses on building fast, cost-efficient, and scalable simulation environments for training agents and improving the transfer of learned capabilities from simulation to the real world. I am also interested in AI safety and AI agents.
Selected Publications
UniSAFE: A Comprehensive Benchmark for Safety Evaluation of Unified Multimodal Models
Segyu Lee*, Boryeong Cho*, Hojung Jung*, Seokhyun An, Juhyeong Kim, Jaehyun Kwak, Yongjin Yang, Sangwon Jang, Youngrok Park, Wonjun Chang, and Se-Young Yun
Preprint, 2026 · * Equal contribution
arXivCode
When and Where to Attack? Stage-wise Attention-Guided Adversarial Attack on Large Vision Language Models
Jaehyun Kwak, Nam Cao, Boryeong Cho, Segyu Lee, Sumyeong Ahn, and Se-Young Yun
Preprint, 2026
arXivCode
Generative Visual Code Mobile World Models
Woosung Koh*, Sungjun Han*, Segyu Lee, Se-Young Yun, and Jamin Shin
ICML 2026 · * Equal contribution
arXivCodeProject
Research Experience
Trillion Labs
KAIST OSI Lab · Advisor: Prof. Se-Young Yun
POSTECH Computer Vision Lab · Advisor: Prof. Suha Kwak
POSTECH Analytics & Information Management Lab · Advisor: Prof. Minseok Song
Education
Korea Advanced Institute of Science and Technology · Advisor: Prof. Se-Young Yun
Pohang University of Science and Technology · Minor in Entrepreneurship
Last updated July 2026.