• Education

Ph. D. in Graduate School of Artificial Intelligence, KAIST (2019.03-2023.08)

• Advisor: Prof. Se-Young Yun

• Optimization & Statistical Inference(OSI) Lab

• Thesis: Practical Data Selection Strategies for Incomplete Supervised Federated Learning

M. S. in Graduate School of Data Science, KAIST (2017.03-2019.03)

• Advisor: Prof. Se-Young Yun

• Optimization & Statistical Inference(OSI) Lab

• Thesis: Gradient compression with random projection and sequential update method

B. S. in Mathematics, Kookmin University (2008.03-2014.08)

• Valedictorian (GPA: 4.34 / 4.5)

• Work History

Chungnam National University (Assistant Professor)  - 2024.09-

• Department of Artificial Intelligence

University of British Columbia (Postdoctoral Researcher)  - 2023.08-2024.06

• Medical Image Analysis

KT (Research Intern)  - 2020.05-2020.09

• Implementation of the simulation of COVID virus spread

Naver Corp (Research Intern) - 2018.09-2019.02

• Development of deep learning cloud platform NSML, developed by CLOVA AI Research

Ouniwang (Software Engineer) - 2015.09-2016.12

• Database management

• RESTful API development

• Back-end development

AskStory (Software Engineer) - 2014.02-2015.08

• Back-end development

• Database Management

• Android & IoT development

AhnLab  (Intern) -2013.03-2013.08

• Web Development

• Create a security report

• Publication

[C7] PTCMIL: Multiple Instance Learning via Prompt Token Clustering for Whole Slide Image Analysis

• Beidi Zhao*, Sangmook Kim*, Hao Chen, Chen Zhou, Zu-hua Gao, Gang Wang, Xiaoxiao Li

• International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2025)

[C6] Automated Filtering of Human Feedback Data for Aligning Text-to-Image Diffusion Models

• Yongjin Yang, Sihyeon Kim, Hojung Jung, Sangmin Bae, SangMook Kim, Se-Young Yun, Kimin Lee

• The 2025 International Conference on Learning Representations (ICLR 2025)

[C5] BAPO: Base-Anchored Preference Optimization for Overcoming Forgetting in Large Language Models Personalization

• Gihun Lee, Minchan Jeong, Yujin Kim, Hojung Jung, Jaehoon Oh, SangMook Kim, Se-Young Yun

• The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024 Findings)

[C4] FedSoL: Stabilized Orthogonal Learning in Federated Learning

• Gihun Lee, Minchan Jeong, SangMook Kim, Jaehoon Oh, Se-Young Yun

• The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024 (CVPR 2024)

[W6] Towards Unbiased Evaluation of Detecting Unanswerable Questions in EHRSQL

• Yongjin Yang*, Sihyeon Kim*, SangMook Kim*, Gyubok Lee, Se-Young Yun, Edward Choi

• ICLR 2024 Workshop on Navigating and Addressing Data Problems for Foundation Models

[W5] FedSoL: Bridging Global Alignment and Local Generality in Federated Learning

• Gihun Lee, Minchan Jeong, SangMook Kim, Jaehoon Oh, Se-Young Yun

• NeurIPS 2023 Workshop “Federated Learning in the Age of Foundation Models”

[C3] Re-thinking Federated Active Learning based on Inter-class Diversity

• SangMook Kim*, Sangmin Bae*, Hwanjun Song, Se-Young Yun

• The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023 (CVPR 2023)

[W4] MEDIAR: harmony of data-centric and model-centric for multi-modality microscopy

• Gihun Lee*, SangMook Kim*, Joonkee Kim*, Se-Young Yun

• 1st winner (outstanding award winner) [1/102]

• NeurIPS 2022 Challenge CellSeg: "Weakly Supervised Cell Segmentation in Multi-modality High-Resolution Microscopy Images

[W3] LG-FAL : Federated Active Learning Strategy using Local and Global Models

• SangMook Kim*, Sangmin Bae*, Hwanjun Song, Se-Young Yun

• ICML 2022 Workshop: "Adaptive Experimental Design and Active Learning in the Real World" 2022

[C2] FedRN: Exploiting k-Reliable Neighbors Towards Robust Federated Learning

• SangMook Kim, Wonyoung Shin*, Soohyuk Jang*, Hwanjun Song, Se-Young Yun

• International Conference on Information and Knowledge Management 2022 (CIKM 2022)

[C1] FedBABU: Toward Enhanced Representation for Federated Image Classification

• Jaehoon Oh*, Sangmook Kim*, Se-Young Yun

• The Tenth International Conference on Learning Representations (ICLR 2022)

[W2] A pipelined hybrid recommender system for ranking the items on the display

• Jaehoon Oh*, Sangmook Kim*, Se-Young Yun, Seungwoo Choi, Mun Yong Yi

• RecSys Challenge '19: Proceedings of the Workshop on ACM Recommender Systems Challenge

[W1] Gradient Compression with Random Projection

• Sangmook Kim, Se-Young Yun

• International Workshop on Big Data Analysis for Smart Energy (BigData4SmartEnergy) 2019, IEEE International Conference on Big Data and Smart Computing (BigComp) 2019

• Awards

NeurIPS 2022 Challenge CellSeg: "Weakly Supervised Cell Segmentation in Multi-modality High-Resolution Microscopy Images

• 1st winner (outstanding award winner) [1/102] News Viedo