# YongKyung Oh

> YongKyung Oh, Assistant Professor at Pusan National University.

## Profile

- [Academic website](https://yongkyung-oh.github.io/)
- [CV PDF](https://drive.google.com/file/d/12kr_OViGjSfBox5_kUnpnpop87liNlyV/view?usp=sharing)
- [Scientific Inference Lab](https://scientific-inference-lab.github.io/)
- [ORCID](https://orcid.org/0000-0002-8027-3433)
- [Google Scholar](https://scholar.google.com/citations?user=YJ1L50YAAAAJ)
- [GitHub](https://github.com/yongkyung-oh)
- [LinkedIn](https://www.linkedin.com/in/yongkyung-oh)

## Research

- [AI for Science](https://yongkyung-oh.github.io/#research): Combining machine learning, scientific knowledge, and simulation to discover mechanisms and understand complex systems.
- [Industrial AI & Decision-Making](https://yongkyung-oh.github.io/#research): Connecting machine learning, optimization, and simulation to support decisions in manufacturing, logistics, and service systems.
- [Evidence-Centered AI](https://yongkyung-oh.github.io/#research): Developing evaluation principles that align AI claims with robust comparisons, uncertainty assessment, and reproducible evidence.
- [Continuous-Time Modeling](https://yongkyung-oh.github.io/#research): Learning continuous dynamics from irregular observations through neural differential equations, with attention to stability and uncertainty.

## Publications

- [Silent failures in federated personalization of foundation models](https://doi.org/10.1145/3770855.3818661): KDD · Blue Sky Ideas Track, 2026.
- [Position: State-of-the-art claims require state-of-the-art evidence](https://proceedings.mlr.press/v306/oh26d.html): ICML, 2026.
- [Survey-aware machine learning: A guideline for valid population health inference based on scoping review](https://proceedings.mlr.press/v333/oh26a.html): CHIL, 2026.
- [FlowPath: Learning data-driven manifolds with invertible flows for robust irregularly-sampled time series classification](https://doi.org/10.1609/aaai.v40i29.39643): AAAI, 2026.
- [Continuum dropout for neural differential equations](https://doi.org/10.1609/aaai.v40i27.39442): AAAI, 2026.
- [TANDEM: Temporal attention-guided neural differential equations for missingness in time series classification](https://doi.org/10.1145/3746252.3760996): CIKM, 2025.
- [Modeling irregular astronomical time series with neural stochastic delay differential equations](https://doi.org/10.1145/3746252.3760805): CIKM, 2025.
- [Comprehensive review of neural differential equations for time series analysis](https://doi.org/10.24963/ijcai.2025/1179): IJCAI, 2025.
- [Multi-view contrastive learning for robust domain adaptation in medical time series analysis](https://proceedings.mlr.press/v287/oh25a.html): CHIL, 2025.
- [Deep interaction feature fusion for robust human activity recognition](https://doi.org/10.1007/978-981-97-9003-6_7): Human Activity Recognition and Anomaly Detection · Springer, 2025.
- [DualDynamics: Synergizing implicit and explicit methods for robust irregular time series analysis](https://doi.org/10.1609/aaai.v39i18.34173): AAAI, 2025.
- [Stable neural stochastic differential equations in analyzing irregular time series data](https://openreview.net/forum?id=4VIgNuQ1pY): ICLR, 2024.
- [Multivariate times series classification using multichannel CNN](https://doi.org/10.24963/ijcai.2022/835): IJCAI, 2022.
- [Multi-channel convolution neural network for gas mixture classification](https://doi.org/10.1109/icdmw53433.2021.00143): ICDM Workshops, 2021.
- [Exploiting logistics anomaly detection using maritime big data](https://www.proquest.com/docview/2511385302): IISE Annual Conference, 2019.
- [Predicting non-recurrent congestion impact: A pattern-based approach for speed drop ratio prediction using weighted k-nearest neighbors](https://doi.org/10.1016/j.cie.2025.111769): Computers & Industrial Engineering, 2026.
- [SmokeBERT: A bidirectional encoder representations from transformers–based model for quantitative smoking history extraction from clinical narratives to improve lung cancer screening](https://doi.org/10.1200/cci-25-00223): JCO Clinical Cancer Informatics, 2025.
- [TSSI: Time series as screenshot images for multivariate time series classification using convolutional neural networks](https://doi.org/10.1016/j.cie.2025.111393): Computers & Industrial Engineering, 2025.
- [TAOD-Net: Automated detection and analysis of thyroid-associated orbitopathy in facial imagery](https://doi.org/10.1016/j.cie.2025.111024): Computers & Industrial Engineering, 2025.
- [Comparative evaluation of VAE-based monitoring statistics for real-time anomaly detection in AIS data](https://doi.org/10.1080/03088839.2024.2388177): Maritime Policy & Management, 2025.
- [Multi-modal lifelog data fusion for improved human activity recognition: A hybrid approach](https://doi.org/10.1016/j.inffus.2024.102464): Information Fusion, 2024.
- [Multichannel convolution neural network for gas mixture classification](https://doi.org/10.1007/s10479-022-04715-2): Annals of Operations Research, 2024.
- [Grid-based Bayesian bootstrap approach for real-time detection of abnormal vessel behaviors from AIS data in maritime logistics](https://doi.org/10.1109/tase.2023.3329041): IEEE Transactions on Automation Science and Engineering, 2024.
- [Sensor drift compensation for gas mixture classification in batch experiments](https://doi.org/10.1002/qre.3354): Quality and Reliability Engineering International, 2023.
- [Time delay estimation of traffic congestion propagation due to accidents based on statistical causality](https://doi.org/10.3934/era.2023034): Electronic Research Archive, 2023.
- [Quantifying incident impacts and identifying influential features in urban traffic networks](https://doi.org/10.1080/21680566.2022.2063205): Transportmetrica B: Transport Dynamics, 2023.
- [Simulation-based anomaly detection in nuclear reactors](https://doi.org/10.7232/jkiie.2021.47.2.130): Journal of the Korean Institute of Industrial Engineers, 2021.
- [Transfer learning based approach for mixture gas classification](https://doi.org/10.7232/jkiie.2021.47.2.144): Journal of the Korean Institute of Industrial Engineers, 2021.