Seojeong Park
I am a Ph.D. student at the Graduate School of AI at KAIST, advised by Prof. Hyunjung Shim.
My research interests lie in reliable multimodal and agentic AI. I study evidence-grounded evaluation for LLM-based judges, focusing on how evaluators use visual and contextual evidence when assessing model outputs. I am also interested in extending this perspective to trajectory-aware evaluation for agentic systems and scalable oversight.
Education
- Ph.D. in Graduate School of AI, KAIST, Seoul, Republic of Korea
- Advisor: Hyunjung Shim
- 2024.02 - Present
- B.S. in Computer Science, Yonsei University, Seoul, Republic of Korea
- 2020.03 - 2024.02
Research Experience
- AI Scientist Intern, EXAONE Lab, LG AI Research, Seoul, Republic of Korea
- 2026.03 - 2026.06
- Research Intern, Center for Artificial Intelligence, KIST, Seoul, Republic of Korea
- 2022.03 - 2022.08
Publications
- ECCV
Dense Reward for Multi-View 3D Reasoning with Global Maps and Local ViewsThe 19th European Conference on Computer Vision , 2026
Honors and Awards
- 2020.03 - 2024.02: National Excellence Scholarship (Natural Sciences and Engineering), The Government of the Republic of Korea
- Spring 2020, Fall 2020, Spring 2023 : Academic Excellence Award (Highest honors, Honors, Honors), Yonsei University
- Spring 2023, Fall 2023: Software Capstone Design (1st Prize, 1st Prize), Yonsei University