Jonghyun Park

I'm a M.S./Ph.D. student in Interdisciplinary Program in Artificial Intelligence, Machine Perception and Reasoning Lab. at Seoul National University advised by Prof. Jonghyun Choi. My research focuses on enhancing safe reasoning in multimodal large language models (MLLMs) through efficient methods, with the goal of creating helpful and reliable multimodal AI systems.

I received B.S. from Yonsei University under the supervision of Prof. Jong-Seok Lee.

CV  /  Email  /  Google Scholar  /  Github  /  LinkedIn

profile photo

    Publications
Risk-adaptive Activation Steering for Safe Multimodal Large Language Models
Jonghyun Park, Minhyuk Seo, Jonghyun Choi
arXiv [pdf]
Impact of Regularization on Calibration and Robustness: from the Representation Space Perspective
Jonghyun Park, Juyeop Kim, Jong-Seok Lee
arXiv [pdf]


This template is from Jon Barron.