Minsuk Kahng 강민석

Update: I recently left Google DeepMind and started a faculty job in South Korea in 2025.

Hi, I'm an Assistant Professor at Yonsei University in the Department of Computer Science and Engineering, where I co-lead the Human-Data Interaction Lab.

I work at the intersection of responsible AI, HCI, and data visualization. My research group studies how AI systems are built and evaluated to uncover safety and societal risks, and develops human-centered approaches and interactive visualization tools for people to build and use AI systems responsibly. For example, I created LLM evaluation tools widely used at Google.

Before joining Yonsei, I was a Senior Research Scientist at Google DeepMind in the People + AI Research (PAIR) team and an Assistant Professor at Oregon State University. I received my Ph.D. from Georgia Tech, advised by Polo Chau, along with a Dissertation Award.

Areas of expertise: Data Visualization, Responsible AI, Human-Computer Interaction (HCI)

Research Interests

AI systems are inherently imperfect. They fail unexpectedly, reflect societal biases, or produce unsafe outputs. We believe these issues are best addressed by enabling people to actively engage with the data behind these systems. To address this, my group develops human-centered workflows and interactive tools that help people analyze model behavior, datasets, and evaluation results, and critically examines how real-world AI systems are built and used. We're particularly interested in (but not limited to):

Note for Prospective Students

We're actively looking for graduate students and undergraduate interns. Applicants planning to start graduate studies in Fall 2026 are encouraged to reach out before March to explore mutual fit through an internship. We value diverse strengths and interests: whether you enjoy analyzing data, building interfaces, conducting studies with people, or examining AI's harms, there is a place for you in our lab. You do not need to excel in all areas; we welcome those with an interest in one of these. If you're interested, please email me your CV, transcript, and a one-page statement describing why you'd like to work with us and what relevant experience you have. If there's a potential fit, I'll get back to you within a week regarding next steps.

Selected Publications

Recent and representative work selected from the full publication list (5,000+ total citations; h-index: 28); * indicates corresponding authors
See all publications (including Preprints)

Employment

Education

Awards

Teaching

Student Advising

Invited Talks

Professional Service

Bio

Minsuk Kahng is an Assistant Professor in the School of Computing at Yonsei University in South Korea. His research aims to empower researchers and practitioners to responsibly develop AI systems through a human-centered, data-centric approach. To achieve this, he builds novel visual analytics tools and interactive methods that help these people interpret model behavior and explore large datasets. Kahng publishes papers at the top venue in the field of data visualization (IEEE VIS), as well as at premier conferences in the field of AI, Human-Computer Interaction, and Responsible Computing. His research has led to deployed technologies (e.g., LLM Comparator for Google, ActiVis for Facebook) and been recognized by prestigious awards, including a Google PhD Fellowship and an NSF Graduate Research Fellowship, and supported by government and industry sponsors in both the U.S. and Korea (including NSF, DARPA, Google, and NAVER). Before joining Yonsei, Minsuk was a Senior Research Scientist at Google DeepMind in the People + AI Research (PAIR) team and an Assistant Professor at Oregon State University. He received his Ph.D. from Georgia Tech with a Dissertation Award.

Website: https://minsuk.com
CV: https://minsuk.com/minsuk-kahng-cv.pdf