Patrick Rim is a first-year Ph.D. student in Computer Science at Yale University. Previously, he obtained his B.S. in Computer Science, with a minor in Information and Data Sciences, from the California Institute of Technology (Caltech) in 2024. His research interests span a wide range of 3D computer vision topics and centers on advancing embodied AI with adaptive, efficient, robust ego-centric perception and multimodal capabilities (as in vision + range sensors, language, or audio). Within this broader goal, his current work focuses on sensor fusion—that is, combining inputs from cameras and range sensors (such as lidar or radar)—in challenging and dynamic settings. He is also interested in recognition tasks, such as 3D object detection for applications like AR/VR and autonomous driving, and generation tasks, such as leveraging language priors for improved depth map generation with diffusion models.
Vision Laboratory
at Yale University