ICML2026
Taeseong Yoon
Ph.D. Candidate · Industrial & Systems Engineering · KAIST
I am a Ph.D. candidate at KAIST, advised by Professor Heeyoung Kim in the Engineering Data Science Lab. My research focuses on uncertainty quantification (UQ) for deep learning, with an emphasis on scalable and theoretically grounded methods for reliable prediction, including evidential deep learning, efficient Bayesian deep learning, conformal prediction, and out-of-distribution detection. I am also interested in statistical machine learning for structured and industrial data, including time-series analysis, tabular foundation models, causal inference, and robust learning under distribution shift.
Open to research discussions and collaborations — feel free to reach out.
Featured Publications
All publications →Publications
2026
CIKM2026
Time Series
GT-PSSM: Unified Probabilistic Framework for Stochastic Dynamics Modeling and Dependency Learning in Multivariate Time Series Anomaly Detection
Venue35th International ACM Conference on Knowledge and Information Management (CIKM), Rome, Italy, November 2026
IEEE TASE2026
Time Series
Knowledge‑Assisted Multi‑Graph Structure Learning for Multivariate Time‑Series Anomaly Detection in Multi‑Stage Industrial Processes
Venue IEEE Transactions on Automation Science and Engineering (TASE), 2026
2025
NeurIPS2025
Uncertainty Quantification
Uncertainty Estimation by Flexible Evidential Deep Learning
Venue Advances in Neural Information Processing Systems (NeurIPS), 2025
2024
ICML2024
In Preparation
ICLR2027
Uncertainty Quantification
In preparation
BASC: Bayesian-Supervised Amortized Support Contraction for Second-Order Uncertainty
TargetICLR 2027
ICLR2027
Robust DL
In preparation
Weak-View Classifier Learning for Class-Imbalanced Semi-Supervised Learning
TargetICLR 2027
AISTATS2027
Causal Inference
In preparation
Adaptive Variable Selection for Continuous Treatment Effect Estimation
TargetAISTATS 2027
News
newOur paper GT-PSSM was accepted at CIKM 2026.
newOur paper Knowledge-Assisted Multi-Graph Structure Learning was accepted for publication in IEEE TASE.
Our paper Courtroom Analogy was accepted at ICML 2026.
Named a Gold Reviewer for ICML 2026.
Presented F-EDL at NeurIPS 2025.
Gave an invited talk on F-EDL at the 2025 INFORMS Annual Meeting.
Gave an invited seminar on uncertainty quantification at POSCO Labs.
Presented DAEDL at the Qualcomm Innovation Fellowship Korea finalist session.
Received the Best Poster Award (3rd Prize) at Samsung AI Forum 2024.
Presented DAEDL at ICML 2024.
Research
My work develops reliable and scalable uncertainty methods for deep learning and statistical learning methods for structured data, causal questions, and distribution shift.
UQ & Bayesian ML
Uncertainty Quantification
Evidential deep learning, efficient Bayesian deep learning, conformal prediction, and out-of-distribution detection.
Structured Data
Time-Series & Tabular Learning
Time-series analysis, tabular foundation models, and statistical learning for industrial data.
Reliable ML
Causal & Robust Learning
Causal inference and robust learning under distribution shift, class imbalance, and limited supervision.
Talks & Presentations
-
Courtroom Analogy: A New Perspective on Uncertainty-Aware Classification
ICML 2026 (Poster, Seoul, planned) · KDMS 2026 Top Conference Session (Invited Talk, planned)
-
Uncertainty Estimation by Flexible Evidential Deep Learning
NeurIPS 2025 (Poster, San Diego) · KIIE Annual Fall Conference (Daejeon) · INFORMS Annual Meeting, Invited Session (Atlanta)
-
Uncertainty Quantification Methods for Deep Learning
Invited Seminar — POSCO Labs, Jul. 2025
-
Uncertainty Estimation by Density‑Aware Evidential Deep Learning
KIIE Annual Spring Conference, Jeju (Jun. 2025) · Qualcomm Innovation Fellowship Korea Finalist (Dec. 2024) · Samsung AI Forum Invited Poster (Oct. 2024) · ICML 2024 Poster Session, Vienna (Jul. 2024)
-
Out‑of‑Distribution Detection Using Dirichlet‑Based Uncertainty Methods
KIIE Annual Fall Conference, Ulsan, Nov. 2023
CV
Education
- Ph.D. Candidate, Industrial & Systems Engineering, KAIST — Advisor: Prof. Heeyoung Kim
- B.S., Industrial & Systems Engineering, KAIST
Honors & Awards
- Gold Reviewer, ICML 2026
- Next‑Generation Engineering Researcher, IPSEK
- Best Poster Award (3rd Prize), Samsung AI Forum
- Finalist, Qualcomm Innovation Fellowship Korea
- Dean's List, Dept. of Industrial & Systems Engineering, KAIST
Academic Service
- Reviewer — ICML 2026 (Gold Reviewer); NeurIPS 2025, 2026
- Reviewer — TMLR (2026–present) · IISE Transactions · Computers & Industrial Engineering · Medical Image Analysis
Research & Industry Experience
- Research Intern, Samsung Advanced Institute of Technology (SAIT) — ML Lab, AI Research Center Uncertainty-aware anomaly detection for semiconductor quality inspection.
- Undergraduate Research Intern, Industrial Statistics Lab, KAIST Bayesian nonparametric modeling — Dirichlet process Gaussian mixture models.
- Intern, SK Hynix — QA Team, Mobile DRAM Engineering Bank-address pattern analysis for fault detection in mobile DRAM quality data.
Teaching & Leadership
- Lab Representative — Engineering Data Science Lab, KAIST
- Teaching Assistant — Engineering Statistics I (IE241), KAIST
- Academic Tutor — Engineering Statistics I & II (IE241/IE242), KAIST
Skills
- Probabilistic ML · Deep Learning · Bayesian Statistics · Uncertainty Quantification · Time‑Series Analysis
-
PythonPyTorchNumPySciPyscikit-learnRLaTeXGit - Korean (Native) · English (Fluent; TOEIC 895)