Youngeun Nam

Postdoctoral Fellow, University of Toronto. Irreplaceable.

profile.jpg

I am a Postdoctoral Fellow at the University of Toronto, where I work with Prof. Eldan Cohen in the OptiMaL Lab on data-centric machine learning for real-world problems. My research focuses on improving the quality, reliability, and efficiency of data and learning systems, and I am also interested in agentic AI for building more adaptive and robust models in practice.

Before joining the University of Toronto, I completed my Ph.D. in Computer Science at KAIST, where I was advised by Prof. Jae-Gil Lee in the Data Mining Lab. I have industry experience from roles in software engineering, data analytics, and AI research, which continues to shape my interest in bridging algorithmic advances with deployable, trustworthy systems.

My long-term goal is to develop next-generation learning systems that are accurate and dependable under real operational constraints, helping narrow the gap between research and applications.

Publications

  1. ACL Main
    QuDAR: Query-Wise Dual-Perspective Adaptive Retrieval
    Joeun Kim, Seunghyouk Yoon, Xuan-Bach Le, Youngeun Nam, Doyoung Kim, Hwanjun Song, and Jae-Gil Lee
    In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), Main, 2026
  2. KDD
    Bi-Modal Learning for Networked Time Series
    Youngeun Nam*, Jihye Na*, Susik Yoon, Hwanjun Song, Jae-Gil Lee, and Byung Suk Lee
    In Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2025
    PDF Video Poster
  3. ICWSM
    Mobility Networked Time-Series Forecasting Benchmark Datasets
    Jihye Na*, Youngeun Nam*, Susik Yoon, Hwanjun Song, Byung Suk Lee, and Jae-Gil Lee
    In Proceedings of the International AAAI Conference on Web and Social Media (ICWSM), 2025
    PDF Poster
  4. KDD
    Mitigating Source Label Dependency in Time-Series Domain Adaptation under Label Shifts
    Jihye Na, Youngeun Nam, Junhyeok Kang, and Jae-Gil Lee
    In Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2025
    PDF Video
  5. TheWebConf
    Breaking the time-frequency granularity discrepancy in time-series anomaly detection
    Youngeun Nam, Susik Yoon, Yooju Shin, Minyoung Bae, Hwanjun Song, Jae-Gil Lee, and Byung Suk Lee
    In Proceedings of the ACM on Web Conference (TheWebConf), 2024
    PDF Video Poster
  6. KDD
    Semi-Supervised Learning for Time Series Collected at a Low Sampling Rate
    Minyoung Bae, Yooju Shin, Youngeun Nam, Young Seop Lee, and Jae-Gil Lee
    In Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2024
    PDF Video
  7. ECML PKDD
    Context-Aware Deep Time-Series Decomposition for Anomaly Detection in Businesses
    Youngeun Nam, Patara Trirat, Taeyoon Kim, Youngseop Lee, and Jae-Gil Lee
    In Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD), 2023
    PDF Poster Slides
  8. AAAI Demo
    AnoViz: A Visual Inspection Tool of Anomalies in Multivariate Time Series
    Patara Trirat*, Youngeun Nam*, Taeyoon Kim, and Jae-Gil Lee
    In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2023
    PDF Video Poster
  9. AAAI
    COVID-EENet: Predicting Fine-Grained Impact of COVID-19 on Local Economies
    Doyoung Kim, Hyangsuk Min, Youngeun Nam, Hwanjun Song, Susik Yoon, Minseok Kim, and Jae-Gil Lee
    In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2022
    PDF Video
  10. KDD
    Hi-COVIDNet: Deep Learning Approach to Predict Inbound COVID-19 Patients and Case Study in South Korea
    Minseok Kim, Junhyeok Kang, Doyoung Kim, Hwanjun Song, Hyangsuk Min, Youngeun Nam, Dongmin Park, and Jae-Gil Lee
    In Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2020
    PDF Video