Welcome to Our ML&PR Lab

Research and Innovation

Learn More

OUR TEAM

Professor

Prof. Jangho Kim

Prof. Jangho Kim

Assistant Professor

School of Artificial Intelligence

College of Computer Science, Kookmin University

국민대학교 소프트웨어융합대학 인공지능학부

e-mail: jangho.kim@kookmin.ac.kr

Tel: 02-910-4791

PhD Students

Hea Eun Lee

Hea Eun Lee

Natural Language Processing

Master Students

Sangho An

Sangho An

Model Pruning, Quantization, PEFT

Hyunjoon Cho

Hyunjoon Cho

Machine Unlearning,
Autonomous Driving

Taeseong Jeong

Taeseong Jeong

generative model,
diffusion model

Jinwoo Chung

Jinwoo Chung

Quantization

Undergraduate Students

Solhee Hwang

Solhee Hwang

Model Compression,
Computer Vision

Czorapinska Weronika

Czorapinska Weronika

Autonomous Driving, Quantization

Jiwoong Yang

Jiwoong Yang

Generative model

Sungyeop Jung

Sungyeop Jung

Model compression,
Federated Learning

Graduated Members

Jongyun Shin

HYUNDAI MOBIS

Jinwoo Kim

Kookmin Univ

About Our Lab

Our research focus

MLPR 연구실에서는 Machine Learning과 Pattern Recognition을 활용해서 효율적인 인공지능 알고리즘 또는 모델을 만드는 연구를 하고 있습니다. 특히, Ubiqutous AI “누구에게나 어디에서든지 사용가능한 AI”를 지향하고 있습니다.

Publications

Our research contributions

2025

Exploring Diverse Sparse Network Structures via Dynamic Pruning with Weight Alignment

Jinwoo Kim, Jongyun Shin, Sangho An, Jangho Kim

Proceedings of the 34th ACM International Conference on Information and Knowledge Management (CIKM 2025) (BK21+ 사업 선정 우수학술대회)

Sparse Structure Exploration and Re-optimization for Vision Transformer

Sangho An, Jinwoo Kim, Keonho Lee, Jingang Huh, Chanwoong Kwak, Yujin Lee, Moonsub Jin, Jangho Kim

The 41th Conference on Uncertainty in Artificial Intelligence (UAI 2025) (BK21+ 사업 선정 우수학술대회)

2024

Cooperative Meta-Learning with Gradient Augmentation

Jongyun Shin, Seunjin Han, Jangho Kim

The 40th Conference on Uncertainty in Artificial Intelligence (UAI 2024) (BK21+ 사업 선정 우수학술대회)

2023

Finding Efficient Pruned Network via Refined Gradients for Pruned Weights

Jangho Kim, Jayeon Yoo*, Yeji Song*, KiYoon Yoo, Nojun Kwak (* equal contribution)

The 31st ACM International Conference on Multimedia (ACM MM 2023) (BK21+ 사업 선정 우수학술대회)

Self-Distilled Self-Supervised Representation Learning

Jiho Jang, KiYoon Yoo, Seonhoon Kim, Chaerin Kong, Jangho Kim, Nojun Kwak

Winter Conference on Applications of Computer Vision 2023 (WACV 2023)

2022

Domain Generalization with Relaxed Instance Frequency-wise Normalization for Multi-device Acoustic Scene Classification

Byeonggeun Kim, Seunghan Yang, Jangho Kim, Hyunsin Park, Juntae Lee, Simyung Chang

The 23nd Annual Conference of the International Speech Communication Association (InterSpeech 2022), Incheon, korea (한국정보과학회 선정 우수학술대회)

Variational On-the-Fly Personalization

Jangho Kim*, Jun-Tae Lee*, Simyung Chang, Nojun Kwak (* equal contribution)

The Thirty-ninth International Conference on Machine Learning (ICML 2022), July 2022 (BK21+ 사업 선정 우수학술대회)

Detection of Word Adversarial Examples in Text Classification: Benchmark and Baseline via Robust Density Estimation

KiYoon Yoo, Jangho Kim, Jiho Jang, Nojun Kwak

Findings of ACL 2022 (BK21+ 사업 선정 우수학술대회)

2021

Vehicle Image Generation Going Well With the Surroundings

Jeesoo Kim*, Jangho Kim*, Jaeyoung Yoo, Daesik Kim, Nojun Kwak (* equal contribution)

28th International Conference on Neural Information Processing (ICONIP 2021), Dec. 2021

Domain Generalization of Efficient Acoustic Scene Classification using Residual Normalization

Byeonggeun Kim, Seunghan Yang, Jangho Kim, Simyung Chang

IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE) Workshop, Nov. 2021

PQK: Model Compression via Pruning, Quantization, and Knowledge Distillation

Jangho Kim, Simyung Chang, Nojun Kwak

The 22nd Annual Conference of the International Speech Communication Association (InterSpeech 2021), Aug 2021, Brno, Czech Republic (한국정보과학회 선정 우수학술대회)

Prototype-based Personalized Pruning

Jangho Kim, Simyung Chang, Sungrack Yun, Nojun Kwak

2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2021), June. 2021, online

2020

Position-based Scaled Gradient for Model Quantization and Sparse Training

Jangho Kim, KiYoon Yoo, Nojun Kwak

Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS 2020), Dec. 2020, online (BK21+ 사업 선정 우수학술대회)

Feature Fusion for Online Mutual Knowledge Distillation

Jangho Kim, Minsung Hyun, Inseop Chung, Nojun Kwak

25th International Conference on Pattern Recognition (ICPR 2020), Milan, Italy, Jan. 2021 (BK21+ 사업 선정 우수학술대회)

Feature-map-level Online Adversarial Knowledge Distillation

Inseop Chung, SeongUk Park, Jangho Kim, Nojun Kwak

Thirty-seventh International Conference on Machine Learning (ICML 2020), July 2020, Online (BK21+ 사업 선정 우수학술대회)

StackNet: Stacking Parameters for Continual learning

Jangho Kim*, Jeesoo Kim*, Nojun Kwak (* equal contribution)

CVPR 2020 Workshop on Continual Learning in Computer Vision, June 2020, Seattle WA (Online)

2018

Paraphrasing Complex Network: Network Compression via Factor Transfer

Jangho Kim, SeoungUK Park, Nojun Kwak

Thirty-second Conference on Neural Information Processing Systems (NeurIPS 2018), Montreal, Canada, Dec. 2018 (BK21+ 사업 선정 우수학술대회)

2016

Detecting Korean characters in natural scenes by alphabet detection and agglomerative character construction

Jangho Kim, Yong-Joong Kim, Yonghyun Kim, Daijin Kim

IEEE International Conference on Systems, Man, and Cybernetics 2016 (SMC 2016) (한국정보과학회 선정 우수학술대회)

2025

Entropy-Guided Meta-Initialization regularization for few-shot text classification

Jongyun Shin, Jinwoo Kim, Jangho Kim

Expert Systems with Applications

Magnitude attention-based dynamic pruning

Jihye Back, Namhyuk Ahn, Jangho Kim

Expert Systems with Applications

Layerwise-priority-based gradient adjustment for few-shot learning

Jangho Kim, JunHoo Lee, Donghoon Han, Nojun Kwak

Expert Systems with Applications

Quantization-aware training with Dynamic and Static Pruning

Sangho An, Jongyun Shin, Jangho Kim

IEEE Access

2023

2022

Model Compression via Position-Based Scaled Gradient

Jangho Kim, KiYoon Yoo, Nojun Kwak

IEEE Access, vol. 10

논문 제목 예시

저자1, 저자2, 저자3

(Under Review)

2021

QTI Submission to DCASE 2021: Residual Normalization for Device-Imbalanced Acoustic Scene Classification with Efficient Design

Byeonggeun Kim, Seunghan Yang, Jangho Kim, Simyung Chang

IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE), Jul. 2021

2019

QKD: Quantization-aware Knowledge Distillation

Jangho Kim*, Yash Bhalgat*, Jinwon Lee, Chirag Patel, Nojun Kwak (* equal contribution)

arXiv, Nov. 2019.

Notice

연구실 소식 및 공지사항

대학원생 & 학부 연구생 연구원 모집

2025-03-04

딥러닝에 관심 있는 학부생을 모집합니다.

CONTACT US

연구실에 관심이 있으시면 연락주세요

연구실 연락처

이메일: jangho.kim@kookmin.ac.kr

주소: 국민대학교 미래관4층37호실