Me!

Minseon Kim github google scholar linked in linked in CV

I am a post doc researcher at Microsoft Research–Montréal. ☃️ I completed my PhD at KAIST, advised by Professor Sung Ju Hwang.
My current research interests lie in identifying realistic safety risks in AI models and developing adaptable and controllable approaches to enhance the trustworthiness of AI models. If you're interested in collaborating on research projects related to AI safety, feel free to contact me :)

Publication (*equal contribution)

Enhancing Variational Autoencoders with Smooth Robust Latent Encoding
       Hyomin Lee*, Minseon Kim*, Sangwon Jang, Jongheon Jeong, Sung Ju Hwang
       ArXiv 2025, PDF

debug-gym: A Text-Based Environment for Interactive Debugging
       Xingdi Yuan, Morgane M Moss, Charbel El Feghali, Chinmay Singh, Darya Moldavskaya, Drew MacPhee, Lucas Caccia, Matheus Pereira, Minseon Kim, Alessandro Sordoni, Marc-Alexandre Côté
       ArXiv 2025, PDF

Exploring Sparse Adapters for Scalable Merging of Parameter Efficient Experts
       Samin Yeasar Arnob, Zhan Su, Minseon Kim, Oleksiy Ostapenko, Doina Precup, Lucas Caccia, Alessandro Sordoni
       ICML Workshop on Modularity for Collaborative, Decentralized, and Continual Deep Learning 2025, PDF

Automatic Jailbreaking of the Text-to-Image Generative AI Systems
       Minseon Kim, Hyomin Lee, Boqing Gong, Huishuai Zhang, Sung Ju Hwang
       ICML Next Generation of AI Safety Workshop 2024, PDF, Project Page, Code

Optimizing Query Generation for Enhanced Document Retrieval in RAG
       Hamin Koo, Minseon Kim, Sung Ju Hwang
       Arxiv 2024, PDF

Protein Representation Learning by Capturing Protein Sequence-Structure-Function Relationship
       Eunji Ko*, Seul Lee*, Minseon Kim*, Dongki Kim, Sung Ju Hwang
       ICLR MLGenX workshop 2024 (Spotlight), PDF

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

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

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

Context-dependent Instruction Tuning for Dialogue Response Generation
       Jin Myung Kwak, Minseon Kim, Sung Ju Hwang
       ArXiv 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 SaTML 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

Learning Transferable Adversarial Robust Representations via Multi-view Consistency
       Minseon Kim*, Hyeonjeong Ha*, Dong Bok Lee, Sung Ju Hwang
       NeurIPS SafetyML workshop 2022, Under review, 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
       M. Kim*, F. Inglese*, G. Steup-Beekman, T. Huizinga, M. Van Buchem, J. Bresser, D. Kim, I. 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

T1 Image Synthesis with Deep Convolutional Generative Adversarial Networks
       Minseon Kim, Chihye Han, Jisuk Park, Dae-Shik Kim
       OHBM 2018

Experience

Post Doc Researcher (Current)
  • ML core team, Microsoft Research Montréal
Research Internship (06.2024-08.2024)
  • ERA–KASL AI Safety Research, University of Oxford
  • Collaborate with Prof. Philip Torr, Prof. David Krueger, Dr. Adel Bibi, Dr. Fazl Barez
Research Collaboration (07.2023-05.2024)
  • Theory Center, Microsoft Research Asia
  • Collaborate with Prof. Huishuai Zhang
Research Internship (06.2019-08.2019)
  • Radiology Department, Leiden University Medical Center (LUMC)
  • Collaborate with Prof. Itamar Ronen

Presented Talk


Invited talk
"Unsupervised Context Understanding for Safer LLMs"
  • Women in MSR – Project Green , MSR, Mar. 2025
"Designing safety systems for LLM-based services"
  • Tea Talk, Mila, Feb. 2025
"How to obtain safety effectively and efficiently"
  • RWE AI Journal Club, Microsoft, Nov. 2024
"Automatic Jailbreaking of the Text-to-Image Generative AI Systems"
  • Guest Lecture, Korea University, May. 2024
"Effective Targeted Attacks for Adversarial Self-Supervised Learning"
  • Samsung AI Forum 2023, Samsung, Nov. 2023
"Generalizable Lightweight Proxy for Robust NAS against Diverse Perturbations"
  • R&D AI Conference, Hyundai, Nov. 2023
"Adversarial Self-Supervised Contrastive Learning"
  • Stella Yu's Group, UC Berkeley, Nov. 2020
  • NeurIPS Social: ML in Korea, Dec. 2020
  • Korea Software Congress (KSC): Korea Post-NeurIPS-2020 Workshop, Dec. 2020
  • Kakao Brain, Feb. 2021
  • Korean Conference on Computer Vision, Aug. 2021
"MRI-based classification of neuropsychiatric systemic lupus erythematosus patients with self-supervised contrastive learning"
  • ESMRMB (Lightening Talk), Sep. 2020
"Deep neural network from CNN to GAN"
  • LUMC, Aug. 2019

Academic Activity

Conference reviewer
  • International Conference on Machine Learning (ICML): 2021-2025
  • Conference on Neural Information Processing Systems (NeurIPS): 2021-2025
  • International Conference on Computer Vision (ICCV): 2025
  • International Conference on Learning Representations (ICLR): 2022-2024
  • Association for Computational Linguistics (ACL) ARR: 2022-2023
  • AAAI Safe, Robust and Responsible AI (SRRAI): 2023
  • AAAI Workshop on Representation learning for Responsible Human-Centric AI (Area Chair): 2023
  • Association for the Advancement of Artificial Intelligence (AAAI): 2020-2021
  • Asian Conference on Machine Learning (ACML): 2020-2021
Journal reviewer
  • Transactions on Pattern Analysis and Machine Intelligence
  • IEEE Computational Intelligence Magazine
  • 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
Organizer

Education

Ph.D. in Graduate School of AI
  • Korea Advanced Institute of Science and Technology (KAIST)
  • Thesis: Towards Safe and Robust Representation with Self-Supervised Learning
  • 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
  • Advisor: Prof. Dae-shik Kim
B.S. in Bio & Brain Engineering and Computer Science (double major)
  • Korea Advanced Institute of Science and Technology (KAIST)

Contact

minseon5113(at)gmail(dot)com