Published several papers including 'v1: Learning to Point Visual Tokens for Multimodal Grounded Reasoning', 'GuideDog: A Real-World Egocentric Multimodal Dataset for Blind and Low-Vision Accessibility-Aware Guidance', etc.
Research Experience
Actively looking for internship opportunities!
Education
Ph.D. student at Yonsei University's CIPLAB, advised by Prof. Seon Joo Kim.
Background
Aiming to build intelligent systems that truly understand and interact with the real world, focusing on multimodal large language models, with an emphasis on multimodal reasoning and video understanding.