Jin Kim

Background

About Jin Kim

I'm Jin, a Ph.D. candidate in Physics and Biology in Medicine at UCLA. I specialize in creating AI systems that interpret both images and text with precision and context-driven accuracy. My research focuses on developing and evaluating Vision-Language and foundation models for medical imaging to advance domains that demand semantic understanding and reliable outcomes. My doctoral research has resulted in multiple publications and conference presentations on topics including autonomous computer vision with Agentic AI, radiology report generation, self-supervised learning for lung segmentation, and enhancing foundation models with deep layer adapters. My work has been recognized with several awards, including 1st place in the SPIE 2024 Live Demonstrations Workshop and the Healthhub Datathon segmentation task. I am also a co-inventor on two patents for an AI-enhanced augmented reality navigation system for surgical procedures. Before my Ph.D, I was a Project Engineer at ABB Korea, where I designed, simulated, and commissioned industrial automation lines for over 20 projects, including a major Samsung production line in Vietnam. This experience in practical, large-scale system implementation informs my current academic research. As an active member of the academic community, I also serve as a peer reviewer for conferences like MICCAI. I thrive in collaborative environments and enjoy connecting with fellow researchers and professionals. My international experience and bilingual abilities (Korean/English) enable me to work effectively in diverse teams! For more information on my work, please visit my personal website!