Publications

Preprints/Working Papers

WIP 2026 Contextual Bandit-based Adaptive and Efficient Inference for Vision Transformers under Distribution Shift

Seok-Ju Hahn, Byeongwoo An, Eungjoo Lee

Details

Role:

Description:

BibTeX:

@article{TBD}

WIP 2026 Decentralized Freshness Management of Foundation Models in Networked ML System

Seok-Ju Hahn, Kibaek Kim

Details

Role:

Description:

BibTeX:

@article{TBD}

Submitted 2026 Tackling Utility-driven Asynchrony through Decoupled Federated Learning

Krishnan Raghavan, Emon Dey, Seok-Ju Hahn, Yijiang Li, Todd Munson, Kibaek Kim

Details

Role:

Description:

BibTeX:

@article{TBD}

Submitted 2026 Generalization-Aware Local Epoch Assignment for Federated Learing

Seok-Ju Hahn, Kibaek Kim

Details

Role:

Description:

BibTeX:

@article{TBD}

Submitted 2025 Differentially Private Collaborative Augmentation for Federated Sparse-view CT Reconstruction

Seok-Ju Hahn, Myoung Hoon Lee, Hwijung Kim, Jun-Seok Yun, Jong Pil Yun, Junghye Lee

Details

Role:

Description:

BibTeX:

@article{TBD}

Peer-reviewed Publications

NeurIPS 2025 Diffusion Federated Datasets

Seok-Ju Hahn, Junghye Lee

Main track

Details

Role:

Description:

BibTeX:

@article{placeholder, title = {Placeholder}}

KDD 2024 CAFO: Feature-Centric Explanation on Time Series Classification

Jaeho Kim, Seok-Ju Hahn, Yoontae Hwang, Junghye Lee, Seulki Lee

Oral · Research track

Details

Role:

Description:

BibTeX:

@article{placeholder, title = {Placeholder}}

ICML 2024 Pursuing Overall Welfare in Federated Learning through Sequential Decision Making

Seok-Ju Hahn, Gi-Soo Kim, Junghye Lee

Main track

Details

Role:

Description:

BibTeX:

@article{placeholder, title = {Placeholder}}

eBioMedicine Prediction of Type 2 Diabetes using Genome-wide Polygenic Risk Score and Metabolic Profiles: A Machine Learning Analysis of Population-based 10-year Prospective Cohort Study

Seok-Ju Hahn*, Suhyeon Kim*, Young Sik Choi, Junghye Lee, Jihun Kang

* equal contribution · IF=11.1 · Enlisted as "The One Who Honours Korea (Hanbitsa)" in 2022

Details

Role:

Description:

BibTeX:

@article{placeholder, title = {Placeholder}}

KDD 2022 Connecting Low-Loss Subspace for Personalized Federated Learning

Seok-Ju Hahn, Minwoo Jeong, Junghye Lee

Oral · Research track

Details

Role:

Description:

BibTeX:

@article{placeholder, title = {Placeholder}}