Chanyu Moon

KAIST Graduate School of AI

moon.chanyu@kaist.ac.kr

I am a Ph.D. student at KAIST, advised by Prof. Jong Chul Ye. I earned my M.S. in Artificial Intelligence (advised by Prof. Ji-Woong Choi) and B.S. in Electrical Engineering and Computer Science, both from DGIST.

My research focuses on Medical AI, with a particular emphasis on Vision-Language Models (VLMs), Large Language Models, and Agentic AI. I am passionate about applying these advanced techniques to tackle critical challenges in the medical domain.

news

Aug 24, 2026	Joined BISPL at KAIST Graduate School of AI as a Ph.D. student, advised by Prof. Jong Chul Ye. Excited for the next chapter!
Aug 24, 2026	Graduated with an M.S. in AI from DGIST, advised by Prof. Ji-Woong Choi (CSP Lab).
May 12, 2025	Our paper “OFF-CLIP: Improving Normal Detection Confidence in Radiology CLIP with Simple Off-Diagonal Term Auto-Adjustment” has been early accepted to MICCAI 2025 (top 9%).

selected publications

MICCAI
OFF-CLIP: Improving Normal Detection Confidence in Radiology CLIP with Simple Off-Diagonal Term Auto-Adjustment

Junhyun Park^*, Chanyu Moon^*, Donghwan Lee, and 2 more authors

In Proceedings of the 28th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI). Early accept (top 9%) , 2025

Abs arXiv Bib HTML PDF

Contrastive Language-Image Pre-training (CLIP) models for radiology suffer from high false-positive rates on normal images. We identify two causes: conventional InfoNCE treats different normal patients as negative pairs, preventing a cohesive normal cluster, and reports of abnormal patients contain normal sentences that are forced to align with abnormal images. OFF-CLIP addresses these with an off-diagonal term loss that treats all normal samples as positive pairs, and with sentence-level text filtering that removes normal descriptions from abnormal reports. Applied to CARZero, OFF-CLIP substantially improves normal detection while maintaining abnormal classification performance on VinDr-CXR, Open-I, PadChest, and CheXpert.
@inproceedings{park2025off, title = {OFF-CLIP: Improving Normal Detection Confidence in Radiology CLIP with Simple Off-Diagonal Term Auto-Adjustment}, author = {Park, Junhyun and Moon, Chanyu and Lee, Donghwan and Kim, Kyungsu and Hwang, Minho}, booktitle = {Proceedings of the 28th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)}, year = {2025}, }
ICTC
Efficient Biomedical Time-series Contrastive Learning: Revisiting Taylor Expansion in Loss Optimization

Yunho Jeong^*, Chanyu Moon^*, Jinmo Kim, and 1 more author

In 2025 16th International Conference on Information and Communication Technology Convergence (ICTC), 2025

Abs Bib HTML

Contrastive learning has become a cornerstone for self-supervised time-series representation learning, yet its practical application is often hindered by the quadratic computational and memory complexity of the standard InfoNCE loss. We leverage a first-order Taylor expansion to approximate the InfoNCE loss, circumventing the explicit computation of the full similarity matrix and reducing the complexity to a linear scale. Integrated into TS2Vec and evaluated on the UCI Human Activity Recognition benchmark, our approach achieves up to a 7.3x speedup and an 8.5x reduction in peak memory usage while maintaining classification accuracy comparable to the original model.
@inproceedings{jeong2025efficient, title = {Efficient Biomedical Time-series Contrastive Learning: Revisiting Taylor Expansion in Loss Optimization}, author = {Jeong, Yunho and Moon, Chanyu and Kim, Jinmo and Choi, Ji-Woong}, booktitle = {2025 16th International Conference on Information and Communication Technology Convergence (ICTC)}, pages = {146--151}, year = {2025}, organization = {IEEE}, }