Byung-Kwan Lee is a Research Scientist at NVIDIA, focusing on developing high-performing and efficiently sized vision-language models through techniques such as distillation, pruning, and compression to maintain or enhance model performance while reducing model size. Before joining NVIDIA as a Research Scientist, he worked as a Research Intern in the same group, and he received his Ph.D. in School of Electrical Engineering from KAIST, South Korea. For more details about his research and background, please visit his personal homepage.