hykim_profile.jpg

Hoyoung Kim


I am a graduate student in the Graduate School of Artificial Intelligence at POSTECH and a member of the Machine Learning Laboratory, advised by Prof. Jungseul Ok.

My research interest lies in investigating diverse feedback mechanisms in machine learning, spanning from human-annotations to self-improvement, with the goal of the efficient evolution of artificial intelligence.

If you are interested in my research projects, please feel free to contact me via cskhy16@postech.ac.kr.

News

Jan 6, 2025 I won the BK21 excellence paper award from POSTECH GSAI.
May 2, 2024 A paper about active label correction with foundation models is accepted in ICML 2024.
Feb 26, 2024 I won the BK21 best paper award from POSTECH GSAI.
Sep 22, 2023 A paper about active learning for semantic segmentation is accepted in NeurIPS 2023.
Jul 13, 2023 A paper about active learning for semantic segmentation is accepted in ICCV 2023.

Education

Oct, 2020 - Present Pohang University of Science and Technology (POSTECH), Pohang, South Korea
Integrated M.S./Ph.D. in Graduate School of Artificial Intelligence
Advisor: Prof. Jungseul Ok
Mar, 2016 - Aug, 2020 Pohang University of Science and Technology (POSTECH), Pohang, South Korea
B.S in Computer Science and Engineering

Publications

  1. Efficient Latent Semantic Clustering for Scaling Test-Time Computation of LLMs
    Sungjae Lee,  Hoyoung Kim, Jeongyeon Hwang, Eunhyeok Park, and Jungseul Ok
    arXiv , 2025
    arXiv
  2. Enhancing Cost Efficiency in Active Learning with Candidate Set Query
    Yeho Gwon, Sehyun Hwang,  Hoyoung Kim, Jungseul Ok, and Suha Kwak
    arXiv , 2025
    arXiv
  3. Active Prompt Learning with Vision-Language Model Priors
    Hoyoung Kim, Seokhee Jin, Changhwan Sung, Jaechang Kim, and Jungseul Ok
    arXiv , 2025
    arXiv
  4. Active Label Correction for Semantic Segmentation with Foundation Models
    Hoyoung Kim, Sehyun Hwang, Suha Kwak, Suha Kwak, and Jungseul Ok
    International Conference on Machine Learning (ICML) , 2024
    arXiv Code Project page
  5. Active Learning for Semantic Segmentation with Multi-class Label Query
    Sehyun Hwang, Sohyun Lee,  Hoyoung Kim, Minhyeon Oh, Jungseul Ok, and Suha Kwak
    Neural Information Processing Systems (NeurIPS) , 2023
    arXiv Code Poster
  6. Adaptive Superpixel for Active Learning in Semantic Segmentation
    Hoyoung Kim, Minhyeon Oh, Sehyun Hwang, Suha Kwak, and Jungseul Ok
    International Conference on Computer Vision (ICCV) , 2023
    arXiv Code Poster
  7. Robust Deep Learning from Crowds with Belief Propagation
    Hoyoung Kim*, Seunghyuk Cho*, Dongwoo Kim, and Jungseul Ok
    International Conference on Artificial Intelligence and Statistics (AISTATS) , 2022
    arXiv Code Poster

Honors

BK21 Excellence Paper Award, POSTECH GSAI (2024)
  • Active Label Correction for Semantic Segmentation with Foundation Models (ICML24)
BK21 Best Paper Award, POSTECH GSAI (2023)
  • Adaptive superpixel for active learning in semantic segmentation (ICCV23)
CKAIA Best Paper Award (2022)
  • Fast Personalized Pruning in Federated Learning (CKAIA22)

Experience

Reviewer
  • Conference on Computer Vision and Pattern Recognition (CVPR)
  • Neural Information Processing Systems (NeurIPS)
  • International Conference on Learning Representations (ICLR)
  • International Conference on Computer Vision (ICCV)
  • International Journal of Computer Vision (IJCV)
Intern & Education
  • Nomad Connection (2017 Summer)
  • Samsung Electronics (2018 Summer)
  • Seoul National University Exchange Student (2019 Winter)
  • SK Hynix (2020 Winter)
  • I-Corps (2020 Fall)
Teaching Assistant
  • CSED515 Machine Learning (2021 Fall, 2022 Fall)
  • CSED273 Digital System Design (2023 Spring)
  • Hyundai Steel (Jan, 2022)
  • POSCO (Aug, 2023)