|
Jinyeong Kim Hi, I'm an undergraduate student at Yonsei University, majoring in Medicine and AI. I am currently an intern at MICV Lab (Prof. Seong Jae Hwang) and INT-RO Lab (Prof. Sangjoon Park). My research interests include interpretability, clinical applications of AI, and multimodal models. |
|
|
Mono-Modalizing Extremely Heterogeneous Multi-Modal Medical Image Registration
Kyobin Choo, Hyunkyung Han, Jinyeong Kim, Chanyong Yoon, Seong Jae Hwang MICCAI, 2025 Our cyclic framework solves the registration problem under extremely heterogeneous conditions. |
|
Pathology-Aware Adaptive Watermarking for Text-Driven Medical Image Synthesis
Chanyoung Kim*, Dayun Ju*, Jinyeong Kim, Woojung Han, Roberto Alcover-Couso, Seong Jae Hwang MICCAI, 2025 (Early Accept, < 9%) First-ever watermarking method specifically designed for text-driven medical image synthesis. |
|
Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding
Seil Kang, Jinyeong Kim, Junhyeok Kim, Seong Jae Hwang CVPR, 2025 (Highlight, < 3.7%) A few attention heads in frozen LVLMs demonstrate strong visual grounding capabilities. These "localization heads" immediately enable training-free detection and segmentation. |
|
See What You Are Told: Visual Attention Sink in Large Multimodal Models
Seil Kang*, Jinyeong Kim*, Junhyeok Kim, Seong Jae Hwang ICLR, 2025 Large multimodal models consistently see irrelevant parts of the input. Our work demystifies this phenomenon, dubbed "visual attention sink," and proposes a simple mitigation strategy. |
|
Adopted from Jon Barron's website. |