Kunwoong Kim

Hi! I’m a postdoctoral researcher in KAIST AI, working with Jinwoo Shin. Before that, I completed my Ph.D. in Statistics at Seoul National University, advised by Yongdai Kim. My research interest lies in trustworthy AI, vision-language models, and machine learning theory.

Email / CV (PDF) / Scholar / LinkedIn

Events

03-2026: Starting as a Postdoctoral Researcher at KAIST AI.
02-2026: Completed Ph.D. in Statistics at Seoul National University.
02-2026: “Doubly-Regressing Approach for Subgroup Fairness” accepted to ICLR 2026.
07-2025: “Fair Clustering via Alignment” accepted to ICML 2025.
02-2025: “Fair Representation Learning for Continuous Sensitive Attributes …” appeared in TPAMI.
01-2025: “Fairness Through Matching” appeared in TMLR.

Publications

Naive Visual Memory is Not Enough: A Failure-Mode Study of GUI Agents · ICML 2026 workshop FAGEN (Failure Modes in Agentic AI)

Seoyoung Choi, Minseok Ko, Hyunseok Lee, Kunwoong Kim, Woomin Song, Chanseok Jeon, Jinwoo Shin

Doubly-Regressing Approach for Subgroup Fairness · ICLR 2026

Kunwoong Kim*, Kyungseon Lee*, Jihu Lee, Dongyoon Yang, Yongdai Kim (*: co-first author)

[PDF]

A Fair Bayesian Inference through Matched Gibbs Posterior · ICLR 2026

Jihu Lee, Kunwoong Kim, Sehyun Park, Insung Kong, Dongyoon Yang, Yongdai Kim

[PDF]

Fair Model-based Clustering · AAAI 2026

Jinwon Park, Kunwoong Kim, Jihu Lee, Yongdai Kim

[PDF]

Fair Clustering via Alignment · ICML 2025

Kunwoong Kim, Jihu Lee, Sangchul Park, Yongdai Kim

[PDF]

Fairness Through Matching · Transactions on Machine Learning Research (TMLR) 2025

Kunwoong Kim, Insung Kong, Jongjin Lee, Minwoo Chae, Sangchul Park, Yongdai Kim

[PDF]

Fair Representation Learning for Continuous Sensitive Attributes using Expectation of Integral Probability Metrics · IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2025

Insung Kong*, Kunwoong Kim*, Yongdai Kim (*: co-first author)

[PDF]

ODIM: Outlier Detection via Likelihood of Under-Fitted Generative Models · ICML 2024

Dongha Kim, Jaesung Hwang, Jongjin Lee, Kunwoong Kim, Yongdai Kim

[PDF]

IOFM: Using the Interpolation Technique on the Over-Fitted Models to Identify Clean-Annotated Samples · AAAI 2024

Dongha Kim, Yongchan Choi, Kunwoong Kim, Ilsang Ohn, Yongdai Kim

[PDF]

On Measuring the Quality of Group Fairness · Journal of Artificial Intelligence Research and Applications 2024

Kunwoong Kim, Insung Kong, Jongjin Lee, Minwoo Chae, Sangchul Park, Yongdai Kim

[PDF]

Purifying Noisy Labels by Adversarial Search and SSL · Journal of Artificial Intelligence Research and Applications 2024

Dongha Kim, Yongchan Choi, Kunwoong Kim, Yongdai Kim

[PDF]

L_q Regularization for Fair Artificial Intelligence Robust to Covariate Shift · Statistical Analysis and Data Mining 2023

Seonghyeon Kim, Sara Kim, Kunwoong Kim, Yongdai Kim

[PDF]

Learning Fair Representation with a Parametric Integral Probability Metric · ICML 2022

Dongha Kim, Kunwoong Kim, Insung Kong, Ilsang Ohn, Yongdai Kim

[PDF]

SLIDE: A Surrogate Fairness Constraint to ensure Fairness Consistency · Neural Networks 2022

Kunwoong Kim, Ilsang Ohn, Sara Kim, Yongdai Kim

[PDF]