Changhun Kim

Changhun Kim

Ph.D. Student

University of Wisconsin–Madison

I am an incoming Ph.D. student in Computer Science at University of Wisconsin–Madison, where I will work with Prof. Sharon Li and Prof. Grigorios Chrysos. Currently, I am a researcher at AITRICS, advised by Prof. Eunho Yang, and collaborate with Prof. Evan Shelhamer at The University of British Columbia and Prof. Juho Lee at KAIST. I received my M.S. in Artificial Intelligence and B.S. in Computer Science and Mathematics from KAIST.

My research focuses on algorithmic and theoretical foundations for trustworthy machine learning with applications to Generative AI (e.g., diffusion models, large language models) and Embodied AI (e.g., world models, vision-language-action models). I have worked on out-of-distribution generalization, explainable artificial intelligence, and uncertainty calibration across modalities including vision, speech, tabular data, and time series.

Contact
  • 500 Lincoln Dr, Madison, WI 53706, USA
  • changhun.a.kim@gmail.com
Education
  • Ph.D. in Computer Science, Sept 2026 – Present

    University of Wisconsin–Madison

  • M.S. in Artificial Intelligence, Feb 2024

    Korea Advanced Institute of Science and Technology (KAIST)

  • B.S. in Computer Science and Mathematics, Feb 2022

    Korea Advanced Institute of Science and Technology (KAIST)

News
  • [Mar 2025] One paper was accepted to ICLR 2025 Workshop on XAI4Science.
  • [Dec 2024] One paper was accepted to ICASSP 2025.
  • [Oct 2024] One paper was accepted to NeurIPS 2024 Workshop on Table Representation Learning.
  • [Sep 2024] I am attending ECCV 2024 in person. See you in Milano! 🇮🇹
  • [Jul 2024] One paper was accepted to ECCV 2024.
  • [Jun 2024] I am attending KOSMI 2024 in person. See you in Seoul! 🇰🇷
  • [Apr 2024] I am attending ICASSP 2024 in person. See you in Seoul! 🇰🇷
  • [Feb 2024] I have completed my master’s thesis defense and graduated from my master's program.
  • [Nov 2023] I am starting my next research journey as a machine learning researcher at AITRICS.
  • [Aug 2023] I am attending INTERSPEECH 2023 in person. See you in Dublin! 🇮🇪
  • [May 2023] One paper was accepted to INTERSPEECH 2023 as an oral presentation!
Employment

UBC Computer Vision Lab
UBC Computer Vision Lab, Vancouver, BC, Canada
External Collaborator, Jul 2025 – May 2026
AITRICS
AITRICS, Seoul, Korea
Researcher, Nov 2023 – May 2026
KAIST Machine Learning and Intelligence Lab
KAIST Machine Learning and Intelligence Lab, Daejeon, Korea
Graduate Research Assistant, Mar 2022 – Feb 2024
Undergraduate Research Assistant, Jun 2021 – Feb 2022
KAIST Vehicular Intelligence Lab
KAIST Vehicular Intelligence Lab, Daejeon, Korea
Undergraduate Research Assistant, Oct 2019 – Aug 2020
Netmarble
Netmarble, Seoul, Korea
Data Engineer, Jun 2019 – Aug 2019
Publications
SPAM: Sampling Pattern Meta-Learning for Domain Generalization on Irregular Time Series
SPAM: Sampling Pattern Meta-Learning for Domain Generalization on Irregular Time Series

Manuscript, 2025
 Development and External Validation of a Transformer-Based Cardiac Arrest Prediction System for General Ward Patients: A Multicenter Study
Development and External Validation of a Transformer-Based Cardiac Arrest Prediction System for General Ward Patients: A Multicenter Study

Manuscript, 2026
Paper
ReviewScore: Misinformed Peer-Review Detection with Large Language Models
ReviewScore: Misinformed Peer-Review Detection with Large Language Models

Manuscript, 2025
Paper
Delta-XAI: A Unified Framework for Explaining Prediction Changes in Online Time Series Monitoring
Delta-XAI: A Unified Framework for Explaining Prediction Changes in Online Time Series Monitoring

International Conference on Learning Representations (ICLR), 2026
Paper Code
Soft Equivariance Regularization for Invariant Self-Supervised Learning
Soft Equivariance Regularization for Invariant Self-Supervised Learning

International Conference on Learning Representations (ICLR), 2026
Paper Code
Position Paper: How Should We Responsibly Adopt LLMs in the Peer Review Process?
Position Paper: How Should We Responsibly Adopt LLMs in the Peer Review Process?

Conference of the European Chapter of the Association for Computational Linguistics (EACL), 2026 (Findings)
Paper
TIMING: Temporality-Aware Integrated Gradients for Time Series Explanation
TIMING: Temporality-Aware Integrated Gradients for Time Series Explanation

International Conference on Machine Learning (ICML), 2025 (Spotlight, 313/12107=2.6%)
ICLR Workshop on XAI4Science, 2025
CIKM Workshop on Human-Centric AI, 2025 (Best Paper Award)
Paper Code
Stable-TTS: Stable Speaker-Adaptive Text-to-Speech Synthesis via Prosody Prompting
Stable-TTS: Stable Speaker-Adaptive Text-to-Speech Synthesis via Prosody Prompting

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2025
Paper
CloudFixer: Test-Time Adaptation for 3D Point Clouds via Diffusion-Guided Geometric Transformation
CloudFixer: Test-Time Adaptation for 3D Point Clouds via Diffusion-Guided Geometric Transformation

European Conference on Computer Vision (ECCV), 2024
Paper Code
SGEM: Test-Time Adaptation for Automatic Speech Recognition via Sequential-Level Generalized Entropy Minimization
SGEM: Test-Time Adaptation for Automatic Speech Recognition via Sequential-Level Generalized Entropy Minimization

Conference of the International Speech Communication Association (INTERSPEECH), 2023 (Oral)
Paper Code
Structure-Aware Set Transformers: Temporal and Variable-Type Attention Biases for Asynchronous Clinical Time Series
Structure-Aware Set Transformers: Temporal and Variable-Type Attention Biases for Asynchronous Clinical Time Series

ICLR Workshop on Time Series in the Age of Large Models, 2026
Paper
DeltaSHAP: Explaining Prediction Evolutions in Online Patient Monitoring with Shapley Values
DeltaSHAP: Explaining Prediction Evolutions in Online Patient Monitoring with Shapley Values

ICML Workshop on Actionable Interpretability, 2025
Paper Code
AdapTable: Test-Time Adaptation for Tabular Data via Shift-Aware Uncertainty Calibrator and Label Distribution Handler
AdapTable: Test-Time Adaptation for Tabular Data via Shift-Aware Uncertainty Calibrator and Label Distribution Handler

NeurIPS Workshop on Table Representation Learning, 2024
Paper Code
Patents
DeltaSHAP: Explaining Prediction Evolutions in Online Patient Monitoring with Shapley Values

KR Patent App. 10-2026-0072989, 2026
Method for Providing Explanation for Patient State Prediction and Electronic Apparatus Therefor

KR Patent App. 10-2025-0009664, 2025
Test-Time Adaptation for Automatic Speech Recognition via Sequential-Level Generalized Entropy Minimization

US Patent App. 18/594,442, 2024
KR Patent App. 10-2024-0006413, 2024
KR Patent App. 10-2024-0023266, 2024
Awards and Honors

Best Paper Award
CIKM 2025 Workshop on Human-Centric AI

Top Reviewer (206/10,943=1.9%)
ICML 2025

Complimentary Registration
ICML 2025

Dongwon Full Master’s Scholarship
Dongwon Group

Magna Cum Laude
KAIST College of Engineering

Silver Prize
Korean Undergraduate Mathematics Competition

Overseas Exchange Scholarship
Mirae Asset

Representative of Student Exchange Ambassador
KAIST

Honor Student
KAIST College of Engineering

KAIST Convergence AMP Scholarship
KAIST School of Computing

Winner
Science Quiz of the KAIST–POSTECH Science War

National Full Undergraduate Scholarship
Korea Student Aid Foundation (KOSAF)
Teaching Experience

Teaching Assistant
Tabular Learning at Hanwha Ocean Capstone Project

Teaching Assistant
AI Soccer Challenge at Bokja Girls’ High School AI Education Program
Academic Service

Journal Reviewer

Conference Reviewer

Workshop Reviewer