理工学研究科 李 澤昊

Task-Oriented Segmentation via Implicit User Guidance: Applications in 2D and 3D Scene Understanding

My research focuses on developing multimodal AI systems that can infer user intent from implicit behavioral cues such as gaze, voice, and interaction history. Specifically, I explore segmentation frameworks in 2D and 3D environments that enable AI to naturally interpret human attention and goals. This work has broad applications in fields such as medical image analysis, robotics, and human–computer interaction.
In the future, I aim to develop technologies that foster intuitive and collaborative interaction between humans and AI, enhancing both safety and productivity in society. During my doctoral studies, I seek to strengthen my international research presence and translate my findings into real-world applications, pursuing a career as a researcher contributing to the advancement of science and technology.