Abstract Single Image Reflection Separation (SIRS) aims to reconstruct both the transmitted and reflected images from a single image that contains a superimposition of both, captured through a glass-like reflective surface. Recent learning-... Read More
Four UNIST graduate students have earned top distinctions at the 32nd Samsung HumanTech Paper Awards, securing one Gold, one Silver, and two Bronze Prizes. The achievement highlights the university’s continued strength in next-generat... Read More
Abstract Model robustness indicates a model’s capability to generalize well on unforeseen distributional shifts, including data corruptions and adversarial attacks. Data augmentation is one of the most prevalent and effective ways to... Read More
HyunKyu Lee, a combined master’s and doctoral student at the UNIST Graduate School of Artificial Intelligence (Advisor: Professor Sung Whan Yoon), has been named a winner of the Qualcomm Innovation Fellowship 2025 Korea. The Qualcomm... Read More
Four faculty members from UNIST have been elected as new members of the National Academy of Engineering of Korea (NAEK), one of Korea’s most prestigious honors related to engineering and technology. On January 11, NAEK announced that... Read More
Abstract Reconstructing object deformation from a single image remains a significant challenge in computer vision and graphics. Existing methods typically rely on multi-view video to recover deformation, limiting their applicability under c... Read More
Abstract Deep learning models have been successful in many areas, but understanding their behavior remains a challenge. Most prior explainable AI (XAI) approaches have focused on interpreting how models make predictions. In contrast, we int... Read More
Abstract Automatically assessing handwritten mathematical solutions is an important problem in educational technology with practical applications, but remains a significant challenge due to the diverse formats, unstructured layouts, and sym... Read More
UNIST is featured in a branded content article published on Nature, in collaboration with Springer Nature, highlighting its research strengths in green hydrogen, AI-driven energy modeling, and industry-based innovation. Titled “How AI... Read More
Abstract Large-scale datasets are usually required to train deep neural networks; however, they increase computational complexity, hindering practical applications. Recently, dataset distillation for images and texts has attracted considera... 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)