Paper

Beyond Fixed-Length Calibration for Post-Training Compression of LLMs

Jaehoon Oh, Dokwan Oh

EMNLP (long, findings), 2025

OrthoRank: Token Selection via Sink Token Orthogonality for Efficient LLM Inference

Seungjun Shin, Jaehoon Oh, Dokwan Oh

ICML, 2025

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

EMNLP (long, findings), 2024

FedSOL: Stabilized Orthogonal Learning with Proximal Restrictions in Federated Learning

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

CVPR, 2024

FedFN: Feature Normalization for Alleviating Data Heterogeneity Problem in Federated Learning

SeongYoon Kim, Gihun Lee, Jaehoon Oh, Se-Young Yun

Federated Learning in the Age of Foundation Models Workshop at NeurIPS, 2023

Synergy with Translation Artifacts for Training and Inference in Multilingual Tasks

Jaehoon Oh^*, Jongwoo Ko^*, Se-Young Yun

EMNLP (short, main), 2022

Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficulty

Jaehoon Oh^*, Sungnyun Kim^*, Namgyu Ho^*, Jin-Hwa Kim, Hwanjun Song, Se-Young Yun

NeurIPS, 2022

ReFine: Re-randomization before Fine-tuning for Cross-domain Few-shot Learning

Jaehoon Oh^*, Sungnyun Kim^*, Namgyu Ho^*, Jin-Hwa Kim, Hwanjun Song, Se-Young Yun

CIKM (short), 2022

Interpretable Deep Learning Model for Analyzing the Relationship between the Electronic Structure and Chemisorption Property

Doosun Hong^*, Jaehoon Oh^*, Kihoon Bang, Soonho Kwon, Se-Young Yun, Hyuck Mo Lee

The Journal of Physical Chemistry Letters (IF: 6.475), 2022

How to Fine-tune Models with Few Samples: Update, Data Augmentation, and Test-time Augmentation

Yujin Kim^*, Jaehoon Oh^*, Sungnyun Kim, Se-Young Yun

Updatable Machine Learning Workshop at ICML, 2022

FedBABU: Toward Enhanced Representation for Federated Image Classification

Jaehoon Oh^*, SangMook Kim^*, Se-Young Yun

ICLR, 2022

Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation

Taehyeon Kim^*, Jaehoon Oh^*, Nak Yil Kim, Sangwook Cho, Se-Young Yun

IJCAI, 2021

BOIL: Towards Representation Change for Few-shot Learning

Jaehoon Oh^*, Hyungjun Yoo^*, ChangHwan Kim, Se-Young Yun

ICLR, 2021

TornadoAggregate: Accurate and Scalable Federated Learning via the Ring-Based Architecture

Jin-woo Lee, Jaehoon Oh, Sungsu Lim, Se-Young Yun, Jae-Gil Lee

Toward Robust, Secure and Efficient Machine Learning Workshop at AAAI, 2021

SIPA: A Simple Framework for Efficient Networks

Gihun Lee^*, Sangmin Bae^*, Jaehoon Oh, Se-Young Yun

BigData4SmartEnergy Workshop at ICDM, 2020

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 Workshop at RecSys, 2019

TED Talk Recommender Using Speech Transcripts

Jaehoon Oh^*, Injung Lee^*, Yeon Seonwoo^*, Simin Sung, Ilbong Kwon, Jae-Gil Lee

ASONAM (demo), 2018