Published several papers including 'VisEscape: A Benchmark for Evaluating Exploration-driven Decision-making in Virtual Escape Rooms', 'Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers', 'When AI co-scientists fail: SPOT-a benchmark for automated verification of scientific research', etc.
Research Experience
Working as a research scientist intern at Exaone Lab, conducting research on advanced foundation large language models.
Education
Bachelor's degree in Computer Science; currently pursuing an integrated MS/PhD program in Computer Science; Advisor: Youngjae Yu.
Background
Research interests include developing reliable agent systems, focusing on agent's reasoning, action-decision, and human-centric AI. Currently working at Yonsei University MIRLAB (Multimodal Intelligence Research Lab).