I'm Jin, a Ph.D. candidate in Physics and Biology in Medicine at UCLA, specializing in Vision-Language Foundation models and Medical Image Analysis. My research focuses on building AI that can understand and reason about visual information, with applications in computer vision, spatial reasoning, and medical imaging.
With experience spanning from leading automation projects at ABB Korea to conducting cutting-edge research at UCLA, I combine technical expertise with practical problem-solving skills. My recent work at UCLA's Computer Vision and Imaging Biomarkers Lab focuses on self-supervised learning, foundation model adaptation, and Vision-Language models for medical applications.
Research Interests
Vision-Language Models
Vision-language foundation models combining visual and textual understanding for medical applications. Working on parameter-efficient fine-tuning strategies using knowledge distillation and pseudo-labeling techniques validated in challenging segmentation tasks. Recent work includes dual-path radiology report generation accepted at MICCAI 2025 Workshop and textual reasoning for affordance coordinate extraction in multimodal environments. Research direction outlined in PhD dissertation proposal.
Medical Image Analysis
Self-supervised learning and foundation models addressing data scarcity challenges in computer vision. Developing methods to handle limited annotated data through innovative pretraining approaches and domain adaptation techniques. Core expertise demonstrated in PhD qualifying examination on foundation models and knowledge distillation. Recent presentations include foundation models with deep layer adapters at RSNA 2024 and self-supervised learning for chest X-ray segmentation at SPIE 2024.
Agentic AI
Autonomous computer vision development with AI agents for spatial reasoning and multimodal understanding. Focus on spatial precision with articulated reasoning and autonomous system development. Recent work includes autonomous computer vision development published on arXiv.
Foundational Work: Surgical Navigation
Previous research in AR-enhanced navigation systems for precise surgical procedures, particularly in ENT applications. This foundational work includes AI-Enhanced AR Navigation System for Precise Mastoidectomy from my Master's thesis, which established core competencies in medical imaging that inform current Vision-Language model research.
Recent News
- [Aug 2025] 🔬 Two papers submitted to ICCV 2025 Workshops: TRACE and SPAR on multimodal reasoning and spatial understanding
- [Jul 2025] 📄 Paper accepted at MICCAI 2025 Workshop on MLLMs in Clinical Practice - "Dual-path Radiology Report Generation"
- [Sep 2024] 🎤 Oral presentation at RSNA 2024 on foundation models for medical image segmentation
- [Mar 2024] 🏆 Won 1st place at SPIE 2024 Live Demonstrations Workshop for SimpleMind AI software
Education
University of California, Los Angeles
GPA: 3.84/4.0
Qualifier: Leveraging Foundation Models, Knowledge Distillation, and Pseudo-Labeling for Robust Lung Segmentation in Computed Tomography Scans
Proposal: Vision-Language Modeling for Medical Image Analysis
Seoul National University
GPA: 3.68/4.3
Thesis: Development of an AI-Enhanced AR Navigation System for Precise Mastoidectomy
Yeungnam University
Merit-based scholarship (70% tuition waiver), GPA: 3.95/4.5 (Major)
Experience
University of California, Los Angeles
Computer Vision and Imaging Biomarkers Lab
Advisors: Prof. Matthew S. Brown & Prof. Dan Ruan
Seoul National University
Medical Image Innovation Laboratory
Advisor: Prof. Won-Jin Yi