I am a 5th-year PhD student at Yonsei University, advised by professor Seong Jae Hwang in the Medical Imaging & Computer Vision Lab. I am also starting as a Student Researcher at Google (Mountain View, CA Office), working on Efficient Video Representation Learning, hosted by Li Zhang.
I am broadly interested in learning algorithms that bridge visual understanding and multi-modal generative modeling, with a particular focus on label-efficient semantic segmentation, medical-image foundation models and multimodal generation, including image and video generation.
dnwjddl@yonsei.ac.kr
Engineering Research Park, Yonsei University, Seoul, Republic of Korea
PhD in Computer Science, 2022~Present
Yonsei University, Seoul
BS in Human Intelligence and Information Engineering, 2017~2022
Sangmyung University, Seoul
Interpretable Motion-Attentive Maps: Spatio-Temporally Localizing Concepts in Video Diffusion Transformers
CVPR 2026 Highlight