I am Young-geun Kim, a tenure-track Assistant Professor in the Department of Mathematical Sciences at Ulsan National Institute of Science and Technology (UNIST).
    Before joining UNIST, I was the Hannan Endowed Visiting Assistant Professor in the Department of Statistics and Probability at Michigan State University (MSU), and a Postdoctoral Fellow in the Departments of Biostatistics and Psychiatry at Columbia University. I received my Ph.D. in Statistics from Seoul National University.

In an era of abundant yet complex high-dimensional data, the Representation Learning Lab focuses on statistical methods for representation learning. We aim to discover low-dimensional latent features that capture meaningful patterns and offer greater explainability than the raw data themselves. Our mission is to build AI that is both theoretically grounded and interpretable, with a focus on applying these data-driven methods to biomedical research.

For instance, we work on identifiable representation learning, developing models where learning the data distribution guarantees the recovery of the true conditional distributions of latent representations. We apply these methodologies to analyze neuroimaging data (e.g., functional MRI). By identifying latent biomarkers associated with mental disorders (e.g., Autism, OCD), we strive to advance precision psychiatry.

Recent News

• [02-01-2026] I joined the Department of Mathematical Sciences at Ulsan National Institute of Science and Technology (UNIST) as a tenure-track Assistant Professor.
• [08-06-2025] Our grant proposal has been accepted by the National Science Foundation; Statistical Understanding of Adversarial Training in Neural Networks, $180,000, 08/2025-07/2028, Role: Co-PI (PI: Dr. Yue Xing, Michigan State University)
• [03-27-2025] Our work has been accepted at Medical Imaging with Deep Learning; Title: A Novel GNN Framework Integrating Neuroimaging and Behavioral Information to Understand Adolescent Psychiatric Disorders
• [03-25-2025] Our Invited Session proposal has been accepted for International Indian Statistical Association (role: Speaker)
• [03-12-2025] Our work has been accepted at IEEE International Conference on Healthcare Informatics (selected as a long presentation); Title: Optimizing Contingency Management with Reinforcement Learning

Selected Publications

1. Kim, Y.-G., Lee, K., and Paik, M.C. (2022). Conditional Wasserstein generator. IEEE Transactions on Pattern Analysis and Machine Intelligence. [Paper][Code]

2. Kim, Y.-G., Kwon, Y., and Paik, M.C. (2019). Valid oversampling schemes to handle imbalance. Pattern Recognition Letters, 125 (1): 661-667. [Paper] [Code]

3. Kim, Y.-G., Liu, Y., and Wei, X. (2023). Covariate-informed representation learning to prevent posterior collapse of iVAE. Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (AISTATS 2023). [Paper] [Code]

4. Kim, Y.-G., Kwon, Y., Chang, H., and Paik, M.C. (2020). Lipschitz continuous autoencoders in application to anomaly detection. Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (AISTATS 2020). [Paper] [Code]

5. Kim, S., Kim, Y.-G., and Wang, Y. (2024). Temporal generative models for learning heterogeneous group dynamics of ecological momentary data. Biometrics [Paper] [Code]