Minseon Kim

github google scholar linked in linked in CV

Me!

I am a Ph.D. student in MLAI Lab, advised by Professor Sung Ju Hwang at KAIST.
My primary research interests lie in the development of robust representations across a variety of domains and tasks, including image classification, language generation, and neural architecture search. Recently, I am interested in how to learn robust representation in the multi-modality and in the foundation models. If you're interested in collaborating on research projects related to robust representation in diverse domains, feel free to contact me :) This is my CV!

Publication (*equal contribution)

Targeted Adversarial Self-Supervised Learning
       Minseon Kim, Hyeonjeong Ha, Sooel Son, Sung Ju Hwang
        NeurIPS 2023, PDF

Generalizable Lightweight Proxy for Robust NAS against Diverse Perturbations
        Hyeonjeong Ha*, Minseon Kim*, Sung Ju Hwang
        NeurIPS 2023, PDF

Language Detoxification with Attribute-Discriminative Latent Space
       Minseon Kim*, Jin Myung Kwak*, Sung Ju Hwang
        ACL 2023, PDF

Meta-Prediction Model for Distillation-aware NAS on Unseen Datasets
       Hayeon Lee*, Sohyun An*, Minseon Kim, Sung Ju Hwang
        ICLR 2023 (Spotlight), PDF Code

Rethinking the Entropy of Instance in Adversarial Training
       Minseon Kim, Jihoon Tack, Jinwoo Shin, Sung Ju Hwang
        IEEE Conference on Secure and Trustworthy Machine Learning 2023 PDF Code

Lightweight Neural Architecture Search with Parameter Remapping and Knowledge Distillation
       Hayeon Lee*, Sohyun An*, Minseon Kim, Sung Ju Hwang
       AutoML workshop 2022, PDF

Few-shot Transferable Robust Representation Learning via Bilevel Attacks
       Minseon Kim*, Hyeonjeong Ha*, Sung Ju Hwang
        NeurIPS SafetyML workshop 2022, PDF

Consistency Regularization for Adversarial Robustness
       Jihoon Tack, Sihyun Yu, Jongheon Jeong, Minseon Kim, Sung Ju Hwang, and Jinwoo Shin
       AAAI 2022 PDF Code

MRI-based classification of neuropsychiatric systemic lupus erythematosus patients with self-supervised contrastive learning
       Francesca Inglese* and Minseon Kim* et al. (Correspond to Itamar Ronen)
       Frontiers in Neuroscience 2022 (Impact Factor: 4.67), PDF

Adversarial Self-Supervised Contrastive Learning
       Minseon Kim, Jihoon Tack, Sungju Hwang
        NeurIPS 2020, PDF Code

Progressive Face Super-Resolution via Attention to Facial Landmark
       Deokyun Kim*, Minseon Kim*, Gihyun Kwon*, Daeshik Kim
        BMVC 2019, PDF Code

MRI-based classification of neuropsychiatric systemic lupus erythematosus patients with self-supervised contrastive learning, European Society For Magnetic Resonance in Medicine and Biology, ESMRMB 2020
T1 Image Synthesis with Deep Convolutional Generative Adversarial Networks, Organization for Human Brain Mapping, OHBM 2018

Work Experience

Research Internship (06.2019-08.2019)
Radiology Department, Leiden University Medical Center (LUMC), Leiden, Netherland

Presented Talk


Invited talk "Adversarial Self-Supervised Contrastive Learning"
  • Stella Yu's Group, UC Berkeley, Virtual, Nov 2020.
  • NeurIPS Social: ML in Korea, Virtual, Dec 2020.
  • Korea Software Congress (KSC): Korea Post-NeurIPS-2020 Workshop, Virtual, Dec 2020.
  • Kakao Brain, Virtual, Feb 2021.
  • Korean Conference on Computer Vision, Virtual, Aug 2021.
Lightening talk "MRI-based classification of neuropsychiatric systemic lupus erythematosus patients with self-supervised contrastive learning"
  • ESMRMB, virtual, Sep 2020
General talk
  • "Deep neural network from CNN to GAN", LUMC, Leiden, Netherland, 2019 (2 weeks)

Academic Activity

Conference reviewer
  • International Conference on Learning Representations (ICLR): 2022, 2023, 2024
  • International Conference on Machine Learning (ICML): 2021, 2022, 2023
  • Conference on Neural Information Processing Systems (NeurIPS): 2021, 2022, 2023
  • Association for Computational Linguistics (ACL) ARR: 2022, 2023
  • Association for the Advancement of Artificial Intelligence (AAAI): 2020, 2021
  • AAAI Safe, Robust and Responsible AI (SRRAI), 2023
  • Asian Conference on Machine Learning (ACML): 2020, 2021
Journal reviewer
  • IEEE Transactions on Neural Networks and Learning Systems
  • Neural Computing and Applications
  • Machine Learning
  • Transactions on Machine Learning Research
  • Asian Conference on Machine Learning Journal Track
Area chair
  • The AAAI 2023 Workshop on Representation learning for Responsible Human-Centric AI: 2023 (Top Area Chair)

Education

Ph.D. in Artificial Intelligence

  • Korea Advanced Institute of Science and Technology (KAIST), current
  • Advisor: Prof. Sung Ju Hwang

M.S. in Electrical Engineering

  • Korea Advanced Institute of Science and Technology (KAIST)
  • Thesis: Differential representation of face pareidolia in human and deep neural network

B.S. in Bio & Brain Engineering and Computer Science (double major)

  • Korea Advanced Institute of Science and Technology (KAIST)

Contact

minseonkim@kaist(dot)ac(dot)kr