Augmented Algorithm
Period: 2025/5-2025/9 Advisor: Prof. Bryan (Arizona State University)
Abstract: Learning data structures and algorithms is a fundamental activity in computer science education, but this is challenging due to their abstract and dynamic nature. While algorithm visualization tools have shown pedagogical benefits, they remain underutilized in educational settings due to creation or integration difficulties. We introduce Augmented Algorithm, a novel LLM-powered algorithm visualization tool that transforms static textbook pseudocode into embedded, interactive algorithm visualizations. Our web-based system combines computer vision with LLMs to automatically generate synchronized, step-by-step algorithm animations from pseudocode directly within scanned textbook pages.
Visualization and Visual Cognition
Period: 2017/4-2019/3 Advisor: Prof. Koyamada, Prof. Natsukawa (Kyoto University)
Abstract: Seeing data does not mean seeing things as they are. The light from the monitor is converted into electrical signals in the retina, and then travels through the optic nerve to the visual cortex via the lateral geniculate nucleus, where it is processed for visual information, allowing us to see what it is. While many studies on visual cognition and neuroscience have revealed some aspects of human visual characteristics, the effects of visual complexity on cognitive load in information visualization, such as graph drawing and interactive visualization have not yet been elucidated.
Modeling Machine Manipuration from Video Recording
Period: 2016/4-2017/3 Advisor: Prof. Nakamura (Kyoto University)
Abstract: The development of wearable devices makes us able to easily record a wide range of daily experiences. However, the video recording itself is pretty redundant and needs great effort to review. Automatically extracting meaningful information from a large amount of experience video is necessary to reuse it in the future.