Kyungmin Lee

I am a graduate student at Algorithmic Intelligence Lab (ALIN-LAB), at Korea Advanced Institute of Science and Technology (KAIST), working with by Prof. Jinwoo Shin. Before joining ALIN-LAB, I was a research officer at Agency for Defense Development, working on Defense AI technology. I received my B.S. degrees in Mathematics and Electrical Engineering at KAIST in 2019.

Email  /  CV  /  Google Scholar  /  Twitter  /  Github

profile photo

My research interests span probabilistic machine learning, representation learning and applications. My recent researches focus on self-supervised representation learning and representation distillation methods by using contrastive learning.

B2T Explaining Visual Biases as Words by Generating Captions
Younghyun Kim, Sangwoo Mo, Minkyu Kim, Kyungmin Lee, Jaeho Lee, Jinwoo Shin


STUNT STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables
Jaehyun Nam, Jihoon Tack, Kyungmin Lee, Hankook Lee, Jinwoo Shin
ICLR, 2023,   (Spotlight Presentation)
Workshop on Table Representation Learning (NeurIPSW-TRL) 2022
Bronze Prize, Samsung Humantech Paper Awards 2023

Code | Openreview

RenyiCL RényiCL: Contrastive Representation Learning with Skew Rényi divergence
Kyungmin Lee, Jinwoo Shin
NeurIPS, 2022

Code | Openreview

ECCV2022 GCISG: Guided Causal Invariant Learning for Improved Syn-to-Real Generalization
Gilhyun Nam, Gyeongjai Choi, Kyungmin Lee
ECCV, 2022

b3do Pseudo-spherical Knowledge Distillation
Kyungmin Lee, Hyeongkeun Lee

b3do Representation Distillation by Prototypical Contrastive Predictive Coding
Kyungmin Lee
ICLR, 2022

Preliminary version presented at NeurIPS 2021 Workshop on Self-supervised Learning: Theory and Practice.

b3do Provable Defense by Denoised Smoothing with Learned Score function
Kyungmin Lee
ICLR Workshop on Security and Safety in Machine Learning Systems, 2021   (Travel Award)

The source of this website is from here.