About Me

I am a Ph.D. student at Yonsei University Machine Learning Lab, under the guidance of Prof. Kibok Lee. My research focuses on adapting vision–language models to real-world downstream tasks, with an emphasis on transfer learning, representation learning, and model reliability. Recently, I have been extending my work to the video domain.

Contact: jhyeonseo715@yonsei.ac.kr
More info: CV

💼 Employment

KRAFTON (Seoul, Republic of Korea)
Research Intern, AI Research Center
Jan 2026 - Present

📝 Publications

AgentVidBench: A Multi-Hop Video Question Answering Benchmark for Evaluating MLLM Agents
Seoyeon An*, Hyeonseo Jang*, Minsu Kim*, Chanho Lee, Younghan Park, Kangwook Lee (*equal contribution)
ICMLW, 2026.

Improving Calibration in Test-Time Prompt Tuning for Vision-Language Models via Data-Free Flatness-Aware Prompt Pretraining
Hyeonseo Jang, Jaebyeong Jeon, Joong-Won Hwang, Kibok Lee
CVPR, 2026. [arXiv:2604.27715]

Enhancing Continual Learning of Vision-Language Models via Dynamic Prefix Weighting
Hyeonseo Jang, Hyuk Kwon, Kibok Lee
CVPR, 2026. [arXiv:2604.18075]

Soft Task-Aware Routing of Experts for Equivariant Representation Learning
Jaebyeong Jeon, Hyeonseo Jang, Jy-yong Sohn, Kibok Lee
NeurIPS, 2025. [arXiv:2510.27222]

📖 Education

Ph.D. in Statistics and Data Science
Yonsei University
Advisor: Kibok Lee
Mar 2024 - now

B.S. in Electrical and Electronics Engineering
Konkuk University
GPA 4.05/4.50, Major GPA 4.18/4.50
Mar 2018 - Feb 2024

💻 Professional Service

Conference Reviewer
ML: NeurIPS, ICMLW
CV: CVPR, ECCV

🎖 Honors and Awards

Dean’s List, Konkuk University   Jan 2024
Academic Scholarship, Konkuk University   Mar 2023