Eunho Yang

Eunho Yang is a faculty member in the Department of Computer Science at KAIST. Their research focuses on the Kim Jaechul Graduate School of AI, with an emphasis on machine learning algorithms, multi-modal learning, large language models, computer vision, and machine learning for healthcare. They lead the MLILAB, which has recently published multiple papers at top conferences such as ICML, ACL, ICLR, EMNLP, and TPAMI. The lab is actively seeking undergraduate interns and graduate students for research opportunities.

Eunho Yang is a researcher specializing in Machine Learning and Statistics. His work focuses on advancing machine learning techniques through continual learning, federated learning, and semi-supervised learning. He explores methods for improving model performance in dynamic and imbalanced data scenarios, such as lifelong learning with dynamically expandable networks and federated continual learning with weighted inter-client transfer. His research also addresses challenges in graph-based learning, including class-imbalanced node classification and graphical models via exponential families. Additionally, he investigates uncertainty-aware attention mechanisms and multi-task learning strategies to enhance model reliability and adaptability.