Sumin Seo
PhD Student at MCML
📬 soochem23 [at] gmail [dot] com
I’m a first-year PhD student at Helmholtz Munich, Munich Center for Machine Learning (MCML), and LMU Munich.
My research focuses on clinically grounded data synthesis and foundation models, with expertise in medical imaging, deep learning, and multimodal representation learning. I am interested in developing robust, reliable, and interpretable medical AI systems for safe deployment in real-world clinical workflows.
I received my M.S. in Artificial Intelligence Applications from Korea University under the supervision of Prof. Jaewoo Kang and my B.S. in Biological Sciences and Data Science (Self-Designed Transdisciplinary Studies) from Sungkyunkwan University. I have also worked as a research intern at Lunit with Dr. Taesoo Kim and at the Health System Data Science Lab of Seoul National University under the supervision of Prof. Sang Min Park.
I love all kinds of movies and fictions, including indie films and science fiction. The quote I cherish most is:
"The only thing I do know… is that we have to be kind, especially when we don't know what's going on."
— Everything Everywhere All at Once (2022)
selected publications
Anatomy-Grounded Synthetic Coronary Angiography for Geometry-Informed Multi-View MatchingIn International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2026* Equal contribution
Accurate antibody loop structure prediction enables zero-shot design of target-specific antibodiesbioRxiv, 2024
ELVIS: Empowering Locality of Vision Language Pre-training with Intra-modal SimilarityarXiv preprint arXiv:2304.05303, 2023
Association between urban green space and the risk of cardiovascular disease: A longitudinal study in seven Korean metropolitan areasEnvironment international, 2019