I am an M.S. student at Efficient Computing Lab and Machine Learning Lab at POSTECH.

I am currently working on large model optimization, advised by Eunhyeok Park. My recent research interests include developing more effective methods for Parameter-Efficient Fine-Tuning (PEFT), as well as improving the efficiency of large model inference. More broadly, I am interested in understanding and exploiting low-dimensional structures in large language models to make both training and inference more efficient. I am particularly interested in methods that reduce computational and memory costs while preserving model performance.