I'm a PhD student in Artificial Intelligence at Yonsei University and a member of the Artificial Intelligence and Information Systems Laboratory (AI-ISL), advised by Professor Albert No.
My research interests include LLMs, VLMs, and World models, with a particular interest in understanding and diagnosing model behavior—how reliably models perceive, reason, and act, and where these processes break down.
Research Experience.
- 2024 — Present · PhD in Artificial Intelligence, Yonsei University (Seoul, Korea)
- 2022 — 2023 · Student Researcher, Ghent University (Ghent, Belgium)
Publications.
* Equal contribution · † Co-corresponding authors
ConferenceNeurIPS 2026
WorkshopICML 2026 EMMQA Workshop (Oral)
ConferenceEMNLP 2026 (Oral)
Same Trajectory, Contradictory Rewards (RoboRMBench): Paraphrase Fragility in Vision Language Reward Models
ConferenceEMNLP 2026 (Oral)
WorkshopICML 2026 SCALE Workshop (Oral)
BenchPreS: A Benchmark for Context-Aware Personalized Preference Selectivity of Persistent-Memory LLMs
ConferenceACL 2026 (Findings)
DUSK: Do Not Unlearn Shared Knowledge
ConferenceICLR 2026
Rethinking Benign Relearning: Syntax as the Hidden Driver of Unlearning Failures
ConferenceICLR 2026
A2D: Any-Order, Any-Step Safety Alignment for Diffusion Language Models