Sukmin Yun
I am currently a postdoctoral fellow at MBZUAI, working with Professor Eric Xing.
Previously, I was a Ph.D. student in the School of Electrical Engineering at Korea Advanced Institute of Science and Technology (KAIST), advised by Prof. Jinwoo Shin.
My research revolves around realistic machine learning problems with limited supervision. This includes many practical and challenging scenarios, e.g., learning with noisy labels, (open-set) semi-supervised learning, and self-supervised learning. Specifically, my previous research has been focused on developing a new way to use more supervisory signals from model or data. Recently, I am also interested in multi-modal learning (e.g., Vision-Language).
Contact: sukmin.yun [at] kaist [dot] ac [dot] kr
Publications
(C: conference / W: workshop / J: journal / P: preprint) (* = equal contribution)
[C6] IFSeg: Image-free Semantic Segmentation via Vision-Language Model
Sukmin Yun*, Seong Hyeon Park*, Paul Hongsuck Seo and Jinwoo Shin
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2023
Sukmin Yun, Jaehyung Kim, Dongyoon Han, Hwanjun Song, Jung-Woo Ha and Jinwoo Shin
International Conference on Machine Learning (ICML) 2022
Hwijoon Lim, Yechan Kim, Sukmin Yun, Jinwoo Shin and Dongsu Han
International Conference on Machine Learning (ICML) 2022
Sukmin Yun, Hankook Lee, Jaehyung Kim and Jinwoo Shin
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2022 (Oral Presentation)
Sukmin Yun*, Jongjin Park*, Kimin Lee and Jinwoo Shin
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020
Kimin Lee, Sukmin Yun, Kibok Lee, Honglak Lee, Bo Li and Jinwoo Shin
International Conference on Machine Learning (ICML) 2019 (Long Oral Presentation)
Jongjin Park*, Sukmin Yun*, Jongheon Jeong and Jinwoo Shin
L2ID Workshop at European Conference on Computer Vision (ECCV) 2022
eDUCATION
Korea Advanced Institute of Science and Technology (KAIST)
Ph.D. in Electrical Engineering - Advisor: Prof. Jinwoo Shin (Expected: Feb 2023)
Korea Advanced Institute of Science and Technology (KAIST)
B.S. in Mathematical Sciences - cum laude (Feb 2017)
wORK EXPERIENCE
External Research Collaborator
Naver AI Lab, Jeongja, South Korea (June 2021 - present)
Host: Dr. Jung-Woo Ha
This research project: Time Is MattEr: Temporal Self-supervision for Video Transformer is accepted in ICML 2022
Teaching Assistant
KAIST Machine Learning Engineer Bootcamp, Seoul, South Korea (Summer 2022)
EE405A: Electronic Design Lab - RoboCam (Robotic Camera), Daejeon, South Korea (Fall 2018)
Instructor: Prof. Jung-Woo Choi
MAS331: Topology, Daejeon, South Korea (Spring 2017)
Instructor: Prof. Ki Hyoung Ko
Research Assistant
EE Co-op Program: Field Training and Education Program, Daejeon, South Korea (Winter 2021)
EE Co-op Program: Field Training and Education Program, Daejeon, South Korea (Summer 2021)
HONORS & AWARDS
Winner, Qualcomm Innovation Fellowship Korea 2022
Participation Grant, International Conference on Machine Learning (ICML) 2022
Excellent Paper Award, KAIST-Samsung Electronics Industry-University Cooperation, 2019
Grand Prize
Travel Award, International Conference on Machine Learning (ICML) 2019
Academic Services
Conference Reviewer
ICML 2021, NeurIPS 2020, NeurIPS 2021, NeurIPS 2022, AAAI 2022, ICLR 2023, CVPR 2023
Journal Reviewer
TCSVT 2021