Sumin Yu

Seoul National University, Electrical and Computer Engineering, ysmsoomin@snu.ac.kr

I am a Ph.D. student in the Department of Electrical and Computer Engineering at Seoul National University, supervised by Prof. Taesup Moon.

Previously, I completed my undergraduate studies in the Department of Electrical and Computer Engineering at Seoul National University, with a thesis on algorithmic fairness for Alzheimer’s disease prediction.

My research has focused on AI ethics and AI safety. My interests also extend to the intersection of AI technology, policy, and governance, aiming to bridge technical research with broader societal and regulatory perspectives.

Research Interests

Ensuring safe and trustworthy AI, with a focus on algorithmic fairness, bias, and privacy risks.

AI governance and accountability for responsible and trustworthy AI.

CV

Education

Seoul National University

M.S./Ph.D. in Electrical and Computer Engineering

GPA: 4.11/4.3

Mar 2023 - Present

Seoul National University

B.S. in Electrical and Computer Engineering

GPA: 3.95/4.3 (Summa Cum Laude)
Thesis: “Achieving Rawls’ Fairness for MRI-based Alzheimer’s Disease Prediction”

Mar 2019 - Feb 2023

Publications

*: Equal Contribution, †: Corresponding Author

Sumin Yu, Taesup Moon†. "Who Will Become the Next Senior?: How Generative AI Erodes the Development Pathway in Software Engineering." (Under review at AIES 2026) [paper].

Sumin Yu*, Juhyeon Park*, Taesup Moon†. "PopResume: Causal Fairness Evaluation of LLM/VLM Resume Screeners with Population-Representative Dataset." (Committed to EMNLP 2026, ACL Rolling Review) [paper].

Sumin Yu*, Hyunwoong Bae*, Taesup Moon†. "Revisiting VLLM Safety Evaluation: Disentangling Benign Grounding from True Safety Failures in VLLMs." the Workshop on Safe and Trustworthy Multimodal AI Systems at International Conference on Computer Vision (ICCV), 2025. [paper].

Sumin Yu*, Taesup Moon†. "SP-Guard: Selective Prompt-adaptive Guidance for Safe Text-to-Image Generation." the European Workshop on Trustworthy AI at European Conference on Artificial Intelligence (ECAI), 2025. [paper].

Sangwon Jung*, Sumin Yu*, Sanghyuk Chun, Taesup Moon†. "Do Counterfactually Fair Image Classifiers Satisfy Group Fairness?--A Theoretical and Empirical Study." Neural Information Processing Systems (NeurIPS), 2024. [paper].

Experience

Consultant, AI Ethics Guideline Task Force

Seoul National University AI Policy Initiative (SAPI)
Aug 2025 - Jan 2026

SNU Tomorrow’s Edge Membership (STEM), Honor Society

College of Engineering, SNU
Sep 2022 - Aug 2023

Research Intern at Seoul National University

M.IN.D lab

Supervised by Prof. Taesup Moon & Dr. Sangwon Jung

Sep 2022 - Feb 2023

Student Society for Social Responsibility, SNU Social Responsibility

Member (2019.09 - 2020.08); President (2020.01 - 2020.08)
Sep 2019 - Aug 2020

Honors & Awards

Outstanding Paper Award

KCC 2026 XAI Workshop

For "PopResume: Causal Fairness Evaluation of LLM/VLM Resume Screeners with Population-Representative Dataset"

Jun 2026

SNU Summa Cum Laude

Seoul National University
Feb 2023

Full Scholarship

Cho Chang-seok Cultural Foundation
2019 – 2022