Publications: 'Social World Models: Universal Structured Representation for Social Reasoning' (arXiv, 2025); 'Socratic-MCTS: Test-Time Visual Reasoning by Asking the Right Questions' (EMNLP, 2025); 'Hypothesis-Driven Theory-of-Mind Reasoning for Large Language Models' (publication details not provided).
Research Experience
Currently a Postdoctoral Researcher at NVIDIA, previously a Young Investigator and an intern at the Allen Institute for AI (Ai2).
Education
Ph.D. in Computer Science from Seoul National University, advised by Gunhee Kim; Postdoctoral Researcher at NVIDIA, working with Yejin Choi
Background
Research Interests: Reasoning and cognitive capabilities of large language models. Professional Field: Computer Science, focusing on enhancing machines' cognitive abilities through computational methods, particularly in reasoning (e.g., social, cognitive, multimodal) and interactive agents. Bio: Incoming Assistant Professor at KAIST AI, leading the Computation & Cognition (COCO) Lab.
Miscellany
Interests: Takes an interdisciplinary approach to research, bridging AI and cognitive science, especially interested in distilling insights from human development and cognition into models for reasoning.