Seojeong Park

I am a Ph.D. student at the Graduate School of AI at KAIST, advised by Prof. Hyunjung Shim.

My research primarily focuses on Multimodal Large Language Models (MLLMs), Evaluation of LLM, and Agentic AI. More recently, I am particularly interested in applying reinforcement learning and memory mechanisms to optimize agentic AI systems. Please feel free to reach out if you’d like to discuss anything.

Selected Publications

ICML

Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling

Seojeong Park*, Jiho Choi*, Junyong Kang, Seonho Lee, Jaeyo Shin, and Hyunjung Shim

ICML, 2026

PDF Website
ACL

PosterForest: Hierarchical Multi-Agent Collaboration for Scientific Poster Generation

Jiho Choi*, Seojeong Park*, Seongjong Song, and Hyunjung Shim

ACL, 2026

PDF Code
WACV

MomentMix Augmentation with Length-Aware DETR for Temporally Robust Moment Retrieval

Seojeong Park, Jiho Choi, Kyungjune Baek, and Hyunjung Shim

WACV, 2026

PDF Code

Education

Ph.D. in Graduate School of AI, KAIST, Seoul, Republic of Korea
- Advisor: Prof. Hyunjung Shim
- 2024.02 - Present
B.S. in Computer Science, Yonsei University, Seoul, Republic of Korea
- 2020.03 - 2024.02

Research Experiences

AI Scientist Intern, EXAONE Lab, LG AI Research, Seoul, Republic of Korea
- 2026.03 - 2026.06 (Expected)
Research Intern, Center for Artificial Intelligence, KIST, Seoul, Republic of Korea
- 2022.03 - 2022.08

Award

National Excellence Scholarship (Natural Sciences and Engineering), The Government of the Republic of Korea
1st Prize in Food Image Classification, KT Genielabs Dev-Challenge
1st Prize in Software Capstone Design, Yonsei University