Jungsoo Kim

SNU Causality Lab

Graduate School of Data Science

Seoul National University

Seoul, Korea

During ICML (0706–0711), please feel free to reach out! I will be attending the EIML workshop (0710) with our spotlight paper, “A Tale of Two Uncertainties: Global-Local Attribution for Conformal Prediction,” which studies how global and local attribution can make uncertainty in conformal prediction easier to interpret. If you are also at ICML, I would be happy to meet and chat.

I am a Ph.D. student in the Causality Lab at the Graduate School of Data Science, Seoul National University, advised by Prof. Sanghack Lee. My research interests include causal inference, representation learning, conformal prediction, and trustworthy machine learning.

Before SNU, I studied Science, Technology and Policy and Quantitative Risk Management at Yonsei University’s Underwood International College, with an exchange semester in Mathematical and Computational Science at Yale-NUS College. Welcome anyone who has interest in questions that sit between statistical evidence, policy decisions, and real-world systems.

news

Jun 30, 2026	Our paper A Tale of Two Uncertainties: Global-Local Attribution for Conformal Prediction was selected as a spotlight paper at the ICML 2026 EIML workshop.

selected publications

EIML

A Tale of Two Uncertainties: Global–Local Attribution for Conformal Prediction

Sangyeon Cho, Minyoung Cho, Jungsoo Kim, and 2 more authors

In ICML 2026 Workshop on The 2nd Workshop on Epistemic Intelligence in Machine Learning: Learning under Unknown Unknowns for Real-world Impact, 2026

Spotlight Bib HTML

Spotlight paper at the EIML workshop

@inproceedings{cho2026tale,
  title = {A Tale of Two Uncertainties: Global--Local Attribution for Conformal Prediction},
  author = {Cho, Sangyeon and Cho, Minyoung and Kim, Jungsoo and Oh, Sujeong and Lee, Sanghack},
  booktitle = {ICML 2026 Workshop on The 2nd Workshop on Epistemic Intelligence in Machine Learning: Learning under Unknown Unknowns for Real-world Impact},
  year = {2026},
  url = {https://openreview.net/forum?id=2aIvedJMpp},
}

CauScien

Instrumental Variable Representation Learning under Confounded Covariates

Jungsoo Kim, Kwonho Kim, Inwoo Hwang, and 1 more author

In NeurIPS 2025 Workshop on CauScien: Uncovering Causality in Science, 2025

Bib

@inproceedings{kim2025instrumental,
  title = {Instrumental Variable Representation Learning under Confounded Covariates},
  author = {Kim, Jungsoo and Kim, Kwonho and Hwang, Inwoo and Lee, Sanghack},
  booktitle = {NeurIPS 2025 Workshop on CauScien: Uncovering Causality in Science},
  year = {2025},
}