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 Despite recent advancements in federated learning (FL), the integration of generative models into FL has been limited due to challenges such as high communication costs and unstable training in heterogeneous data environments. To a... Read More
Abstract Significant advancements have been achieved in the realm of understanding poses and interactions of two hands manipulating an object. The emergence of augmented reality (AR) and virtual reality (VR) technologies has heightened the... Read More
Dean Jae-Young Sim of the UNIST Graduate School of Artificial Intelligence (AIGS) has been honored with a commendation from the Minister of Science and ICT (MSIT) for his significant contributions to the development of the AI field by culti... Read More
Yonghun Lee, a student in Professor Jimin Lee’s Laboratory (UNIST Artificial Intelligence Graduate School and Department of Nuclear Engineering), has been honored with the Paul Dudley White International Scholar Award at the American... Read More
As concerns regarding financial safety and fraud involving manipulated videos escalate, Professor Saerom Park’s team in the Department of Industrial Engineering at UNIST has developed an innovative deepfake prevention technology that... Read More
Abstract Nuclear microreactors (MRs) have attracted significant attention for their versatility in installation locations, especially with the growing demand for sustainable green energy in large data processing facilities. However, ensurin... Read More
Abstract Recent advances in the diffusion models have significantly improved text-to-image generation. However, generating videos from text is a more challenging task than generating images from text, due to the much larger dataset and high... 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
Abstract We propose a novel concept of dual and integrated latent topologies (DITTO in short) for implicit 3D reconstruction from noisy and sparse point clouds. Most existing methods predominantly focus on single latent type, such as point... 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)