1210 W Dayton St
Madison, WI 53706
Hello! I’m a third-year Ph.D. student in the Department of Computer Sciences at the University of Wisconsin-Madison, where I am fortunate to be advised by Prof. Sharon Li. Previously, I received my M.S. and B.S. degrees in Electrical and Electronic Engineering from Yonsei University, where I was advised by Prof. Kwanghoon Sohn and Prof. Kibok Lee.
I am actively seeking Summer 2027 research internship opportunities, particularly in foundation models, AI agents, and robotics. Please get in touch!
My research focuses on building reliable AI agents by understanding when they may fail and using that insight to improve their decisions. I study how signals from model representations and behavior can help evaluate and guide agents and robotic systems built on foundation models.
My work connects two directions:
- Understanding, detecting, and evaluating failures: anomaly and hallucination detection, uncertainty quantification, and failure analysis. [WACV'23, CVPRW'24, 2×ICML'25, NeurIPS'25, 2×ICLR'26, 2×ACL'26, 2×NeurIPS'26, ECCVW'26]
- Guiding decisions through test-time computation and post-training: verification, ranking, progress evaluation, and learning from feedback. [ICML'25, NeurIPS'25, NeurIPS'26, NeurIPSW'26]
My broader goal is to turn these signals into actionable feedback that helps agents recover from mistakes and improve through experience.
News
| Sep 24, 2026 | Two papers have been accepted to NeurIPS 2026! 🌟 |
|---|---|
| Sep 21, 2026 | Excited to start my Student Researcher position at Google  |
| May 18, 2026 | I will be joining Microsoft Research Asia-Tokyo this May as a research intern, working on Embodied AI agents  |
| Apr 14, 2026 | I have passed my PhD qualifying exam!  |
| Apr 06, 2026 | Two papers have been accepted to ACL 2026! |
Professional Experience
-
Google
Sep 2026 – Present
Student Researcher · Self-Improving LLMs
New York, United States
-
Microsoft Research Asia–Tokyo
May 2026 – Aug 2026
Research Intern · VLA Test-Time Scaling
Tokyo, Japan
Selected Publications
All publications are listed on Google Scholar.
- NeurIPS Workshop
DiVeR: Decision-Critical Verifier Learning for VLA Test-Time ScalingPTA: From Pretrained Representations to Acting Agents (NeurIPS Workshop), 2026*Work done at Microsoft Research Asia–Tokyo. - NeurIPS
Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime MonitoringConference on Neural Information Processing Systems (NeurIPS), 2026 - NeurIPS
Neglected Free Lunch from Post-training: Progress Advantage for LLM AgentsConference on Neural Information Processing Systems (NeurIPS), 2026 - ACL (Main)
Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and OpportunitiesAnnual Meeting of the Association for Computational Linguistics (ACL), 2026 - ACL (Findings)
VAUQ: Vision-Aware Uncertainty Quantification for LVLM Self-EvaluationAnnual Meeting of the Association for Computational Linguistics (ACL), 2026 - NeurIPS
GLSim: Detecting Object Hallucinations in LVLMs via Global-Local SimilarityConference on Neural Information Processing Systems (NeurIPS) , 2025 - ICML
Steer LLM Latents for Hallucination DetectionInternational Conference on Machine Learning (ICML), 2025 - WACV
Normality guided multiple instance learning for weakly supervised video anomaly detectionIEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023
Reviewer Experience
- Conference: CVPR, ECCV, ACL, NeurIPS, ICLR, AAAI
- Journal: TPAMI, PR
Miscellaneous
Outside of research, I love playing the piano 🎹, listening to all kinds of music and attending concerts 🎶, and exploring art and architecture 🎨🏛️. If you share any of these interests, I’d love to connect!
Languages 🌐
Korean (Native), English, Japanese (JLPT N1)