이남훈 연구실

As AI models become larger and more computationally demanding, compression is essential for making them practical and sustainable. We develop optimization methods that reduce training and inference costs while preserving model performance.

The shift toward massive-scale models has made distributed training essential for workloads that no single machine can support. Our research develops robust algorithms for decentralized and high-latency training environments.

Optimization is not only a subject of study in itself, but also a versatile lens through which we tackle challenges in interpretability, uncertainty quantification, continual learning, and other real-world deep learning systems.

Optimization has long been a source of crucial ideas that drastically enhance all corners of deep neural network training. Our research investigates these questions and develops optimization principles and algorithms for modern deep learning systems.