Abstract Flat minima, known to enhance generalization and robustness in supervised learning, remain largely unexplored in generative models. In this work, we systematically investigate the role of loss surface flatness in generative models,... Read More
UNIST has been selected to participate in the ‘AI Star Fellowship‘ project, a key initiative supported by the Ministry of Science and ICT (MSIT) and the Institute for Info & communication Tech Planning & evaluation (IITP... Read More
Abstract Learning with multiple modalities has recently demonstrated significant gains in many domains by maximizing the shared information across modalities. However, the current approaches strongly rely on high-quality paired datasets, wh... Read More
Abstract Investigating flat minima on loss surfaces in parameter space is well-documented in the supervised learning context, highlighting its advantages for model generalization. However, limited attention has been paid to the reinforcemen... Read More
Abstract Albeit the success of federated learning (FL) in decentralized training, bolstering the generalization of models by overcoming heterogeneity across clients still remains a huge challenge. To aim at improved generalization of FL, a... Read More
![[UNIST Webinar] AI enabled Computational Imaging for Biomedical Applications](https://news.unist.ac.kr/wp-content/uploads/2022/10/Session-13.18-296x166.jpg)