Bio
Publications
CV
Github
Scholar

Won-Seok Choi

Ph.D Student
Dept. Computer Science and Engineering
Seoul National University

Contact

wchoi (at) bi.snu.ac.kr
dnjstjr4349 (at) gmail.com


Research Interests

My current research goal is to design a cognitive agent that can understand the dynamic environment through active interactions. To achieve this, an agent should deal with critical problems such as lack of additional information, data imbalance, distribution shifts, and physical embodiment limitations. Specifically, my research topics belong to:


Biography

[2019.09 ~ Current] Ph.D. student at Seoul National University (Prof. Byoung-Tak Zhang)
[2015.03 ~ 2019.08] Bachelor’s degree in CSE at Seoul National University
[2013.03 ~ 2015.02] Graduated Chungnam Science High School

Academic Experiences

[2021-S ~ Current] 인공지능 만들기, K-MOOC online lecture, Teaching Assistant (8th semester)
[2020-S ~ 2022] Samsung NPEX Course, Teaching Assistant
[2020-F, 2022-F] Artificial Neural Networks, dept.CSE, SNU, Teaching Assistant
[2019-F] Machine Learning, dept.CSE, SNU, Teaching Assistant


Publications

DUEL: Duplicate Elimination on Active Memory for Self-Supervised Class-Imbalanced Learning

Won-Seok Choi, Hyundo Lee, Dong-Sig Han, Junseok Park, Heeyeon Koo, Byoung-Tak Zhang
The 38th Annual AAAI Conference on Artificial Intelligence (AAAI 2024)
[paper]

Unveiling the Significance of Toddler-Inspired Reward Transition in Goal-Oriented Reinforcement Learning

Junseok Park, Yoonsung Kim, Hee bin Yoo, Min Whoo Lee, Kibeom Kim, Won-Seok Choi, Minsu Lee, Byoung-Tak Zhang
The 38th Annual AAAI Conference on Artificial Intelligence (AAAI 2024)
[paper]

Learning Geometry-aware Representations by Sketching

Hyundo Lee, Inwoo Hwang, Hyunsung Go, Won-Seok Choi, Kibeom Kim, Byoung-Tak Zhang
The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023 (CVPR 2023)
[paper]

DUEL: Adaptive Duplicate Elimination on Working Memory for Self-Supervised Learning

Won-Seok Choi, Hyundo Lee, Dong-Sig Han, Junseok Park, Byoung-Tak Zhang
NeurIPS 2022 SSLTheoryPractice Workshop
[paper] [workshop]

Message passing adaptive resonance theory for online active semi-supervised learning

Taehyeong Kim, Injune Hwang, Hyundo Lee, Hyunseo Kim, Won-Seok Choi, Joseph J Lim, Byoung-Tak Zhang
International Conference on Machine Learning 2021 (ICML 2021)
[paper]

ARLET: Adaptive Representation Learning with End-to-end Training

Won-Seok Choi, Injune Hwang, Byoung-Tak Zhang
NeurIPS 2020 Workshop on BabyMind
[paper] [workshop]

Label propagation adaptive resonance theory for semi-supervised continuous learning

Taehyeong Kim, Injune Hwang, Gi-Cheon Kang, Won-Seok Choi, Hyunseo Kim, Byoung-Tak Zhang
45th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2020)
[paper]