Paper Accepted to Findings of EMNLP 2026
Our paper, “Do Backdoored LLMs Share Internal Trigger Representations? Evidence from Frozen SAE Feature Banks,” by Minjeong Choi, Jaesin Ahn, and Heechul Jung, has been accepted to…
Safe & Applied
Intelligence Lab
Safe & Applied Intelligence Lab (SAIL) focuses on advancing trustworthy artificial intelligence and developing AI solutions for real-world applications. We explore generative AI (GenAI), natural language processing (NLP), and computer vision (CV). Our specific research interests include image enhancement, machine unlearning, and mechanistic interpretability. We aim to understand and improve how AI systems learn and behave while developing effective technologies that can address practical problems across diverse domains. Our research is not limited to these areas, and we continuously explore new and meaningful problems in artificial intelligence.
Latest News
View All NewsSAIL Laboratory Website Is Now Online
The Safe & Applied Intelligence Lab website is now online. This site will document our research, publications, people, lectures, challenges, and collaboration opportunities as the…
Join SAIL
SAIL is recruiting graduate students and undergraduate research interns interested in trustworthy AI, generative AI, natural language processing, computer vision, and real-world AI applications. If you are interested in joining SAIL, please do not hesitate to contact Prof. Jaesin Ahn at ajs0420@hanbat.ac.kr.
Contact Us