|
Eunseob Choi I am an undergraduate student at Gwangju Institute of Science and Technology (GIST), majoring in Electrical Engineering and Computer Science. I am also a research intern at the IMSI Research Lab, Seoul National University, advised by Prof. Nam-Joon Kim and Prof. Hyuk-Jae Lee. My research interests are computer vision, representation learning, and generative & foundation models, with applications to medical imaging. Recently, I have been working on the reliability and evaluation of pretrained vision systems. I'm always open to discussions and collaborations. Feel free to reach out! E-mail: eunseob [dot] kr [at] gmail [dot] com |
|
Publications |
|
Auditing Correlated Failures in Frozen-Feature Pretrained-Encoder Pools for Medical Segmentation
Eunseob Choi, Kyeonghun Kim, Hyuk-Jae Lee, Nam-Joon Kim Conference on Neural Information Processing Systems (NeurIPS), Evaluations and Datasets Track, 2026 (Poster) |
|
Auditing Capsule Vision 2024: Within-Split Train-to-Validation Re-Exposure and a Kvasir-Channel Sensitivity Diagnostic
Eunseob Choi, Kyeonghun Kim, Hyuk-Jae Lee, Nam-Joon Kim Conference on Neural Information Processing Systems (NeurIPS), Evaluations and Datasets Track, 2026 (Poster) |
|
ProsMAE: Multi-Source MAE Pretraining for ISUP Grade Classification
Anna Jung, Kyeonghun Kim, Youngung Han, Eunseob Choi, Jiwon Yang, Yunjin Seo, Ken Ying-Kai Liao, Hyuk-Jae Lee, Nam-Joon Kim IEEE Asia Pacific Conference on Circuits and Systems (APCCAS), 2026 |
|
MAESIL: Masked Autoencoder for Enhanced Self-supervised Medical Image Learning
Kyeonghun Kim, Hyeonseok Jung, Youngung Han, Junsu Lim, Yeonju Jean, Seongbin Park, Eunseob Choi, et al. International Conference on Electronics, Information, and Communication (ICEIC), 2026 |
|
NEMESIS: Noise-suppressed Efficient MAE with Enhanced Superpatch Integration Strategy
Kyeonghun Kim, Hyeonseok Jung, Youngung Han, Hyunsu Go, Eunseob Choi, et al. arXiv preprint, 2026 |
Posters |
|
GRAVEX: GPU-accelerated GAN‑Diffusion Representation for Counterfeit Pattern Analysis with MONAI-based Validation & Examination
Kyeonghun Kim, Eunseob Choi, Junsu Lim, Induk Um, Ken Ying-Kai Liao, Hyuk-Jae Lee NVIDIA GTC, 2026 |
|
GLARE: GPU-Accelerated 3D CT Vision-Language Reasoning via Efficient Anatomical Boundary Guidance
Youngung Han, Junsu Lim, Eunseob Choi, Soo Yong Kim, Yi Kwan Ginny Wong, Nam-Joon Kim NVIDIA GTC, 2026 |
Experience |
|
IMSI Research Lab, Seoul National University — Research Intern Aug. 2025 – Present
JB Woori Capital — AI Research Intern, AI Transformation Team Feb. 2026 – Apr. 2026
TeX-Corps EM, GIST — Researcher Mar. 2025 – Dec. 2025 |
Education |
|
Gwangju Institute of Science and Technology (GIST) — B.S. in Electrical Engineering and Computer Science Mar. 2024 – Present
University of California, Berkeley — Summer Session Exchange Student Jun. 2025 – Aug. 2025 |
Patents |
|
Eunseob Choi, "Hybrid Behavior Classification System and Method Combining Lightweight Edge Pose Estimation and Server Deep Analysis Based on 2D Monocular Images," Korean Patent Application No. 10-2025-082086-3, under examination. |
|
Design adapted from Jon Barron's website. |