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 — scalable, theoretically grounded frameworks for reliable predictions, with emphasis on evidential deep learning, efficient Bayesian inference, out-of-distribution detection, and robustness under distribution shift.

I am also interested in statistical machine learning for structured and industrial data, including multivariate time-series anomaly detection, class-imbalanced semi-supervised learning, and continuous causal effect estimation. Recent publications: Courtroom Analogy (ICML 2026), F‑EDL (NeurIPS 2025), DAEDL (ICML 2024).

Previously a research intern at Samsung Advanced Institute of Technology (SAIT) and SK Hynix, working on uncertainty-aware anomaly detection for semiconductor manufacturing.

Open to research discussions and collaborations — feel free to reach out.

Curriculum Vitae All Publications

Selected Publications

See all →
ICML 2026

Courtroom Analogy: A New Perspective on Uncertainty-Aware Classification

Taeseong Yoon, Heeyoung Kim
NeurIPS 2025

Uncertainty Estimation by Flexible Evidential Deep Learning

Taeseong Yoon, Heeyoung Kim
ICML 2024

Uncertainty Estimation by Density-Aware Evidential Deep Learning

Taeseong Yoon, Heeyoung Kim

Publications

Google Scholar  ·  * equal contribution  ·  bold = me

2026

ICML 2026
ICML 2026 Uncertainty Quantification

Courtroom Analogy: A New Perspective on Uncertainty‑Aware Classification

Taeseong Yoon, Heeyoung Kim

International Conference on Machine Learning (ICML), 2026

[arXiv] [PDF] [Code] [BibTeX]
IEEE TASE
IEEE TASE Time Series

Knowledge‑Assisted Multi‑Graph Structure Learning for Multivariate Time‑Series Anomaly Detection in Multi‑Stage Industrial Processes

Jaeyeong Lee*, Taeseong Yoon*, Wonmo Koo, Heeyoung Kim

IEEE Transactions on Automation Science and Engineering (TASE), 2026

[IEEE Xplore]

2025

NeurIPS 2025
NeurIPS 2025 Uncertainty Quantification

Uncertainty Estimation by Flexible Evidential Deep Learning

Taeseong Yoon, Heeyoung Kim

Advances in Neural Information Processing Systems (NeurIPS), 2025

[Proceedings] [OpenReview] [arXiv] [Code]

2024

ICML 2024
ICML 2024 Uncertainty Quantification

Uncertainty Estimation by Density‑Aware Evidential Deep Learning

Taeseong Yoon, Heeyoung Kim

Proceedings of the 41st International Conference on Machine Learning (ICML), 2024

[arXiv] [PMLR] [Code]

Under Review

ACM CIKM
Time Series Under Review

Graph‑Transformer‑Enhanced Probabilistic State‑Space Models for Multivariate Time‑Series Anomaly Detection

W. Koo, J. Lee, T. Yoon, H. Kim

Under review — ACM CIKM

NeurIPS sub.
Robust DL Under Review

LALA: Learning‑Aware Logit Adjustment for Class‑Imbalanced Semi‑Supervised Learning

T. Park, T. Yoon, H. Kim

Under review — NeurIPS

In Preparation

prep.
Uncertainty Quantification

SCOPE: Support Calibrated Posterior Evidence for Second‑Order Uncertainty Quantification

Taeseong Yoon, Heeyoung Kim

In preparation

prep.
Causal Inference

Adaptive Variable Selection for Continuous Treatment Effect Estimation

H. Cho*, T. Yoon*, I. Jeong, H. Kim

In preparation

News

Research

My core focus is uncertainty quantification for deep learning — scalable, theoretically grounded methods for reliable predictions. I am broadly interested in statistical machine learning for complex structured and industrial data.

UQ & Bayesian ML

Uncertainty Quantification

Evidential deep learning, efficient Bayesian inference, OOD detection, and robustness under distribution shift.

Anomaly Detection

Time-Series & Industrial Data

Multivariate time-series anomaly detection including graph structure learning and probabilistic state-space models.

Statistical ML

Structured & Imbalanced Data

Class-imbalanced semi-supervised learning and continuous causal effect estimation.

Talks & Presentations

CV

View full 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
  • Python PyTorch NumPy SciPy scikit-learn R LaTeX Git
  • Korean (Native)  ·  English (Fluent; TOEIC 895)