Jinsu Kim

About

I am a PhD student at Korea University, advised by Prof. Jongheon Jeong. My research focuses on AI safety and efficiency for generative models, especially large language models and diffusion models. I am interested in designing trustworthy AI systems that remain reliable and aligned with human values.

Publications

[C3]Persona-Pruner: Sculpting Lightweight Models for Role-Playing

Jinsu Kim, Jihoon Tack, Noah Lee, Jongheon Jeong

ICML 2026

arXiv Code

[C2]BlurGuard: A Simple Approach for Robustifying Image Protection Against AI-Powered Editing

Jinsu Kim*, Yunhun Nam*, Minseon Kim, Sangpil Kim, Jongheon Jeong

NeurIPS 2025

arXiv Code

[C1]ECoRAG: Evidentiality-guided Compression for Long Context RAG

Yeonseok Jeong, Jinsu Kim, Dohyeon Lee, Seung-won Hwang

ACL 2025 Findings

arXiv

Education

Korea University

PhD Student in Artificial Intelligence