Kwanhee Lee

Hi, I’m a second-year Master’s student at Graduate School of Artificial Intelligence, POSTECH, where I’m fortunate to be advised by Prof. Namhoon Lee. Previously, I was an Academic Visitor in DASLab at ISTA, hosted by Prof. Dan Alistarh.

My goal is to make foundation models more efficient through the lens of optimization. Broadly, my research interests lie in 1. Optimization-based model compression (pruning, quantization, distillation), 2. Systematic optimization for efficient model inference (writing CUDA kernels, profiling/optimizing inference systems–vLLM), and 3. Optimization for deep learning (Muon/shampoo/soap and it’s friends!).

For more details, please take a look at my CV