Exploring Ordinal Bias in Action Recognition for Instructional Videos, ICLR Workshop on Spurious Correlation and Shortcut Learning: Foundations and Solutions, 2025
Background-aware Moment Detection for Video Moment Retrieval, WACV, 2025
Zero-Shot Vision-and-Language Navigation with Collision Mitigation in Continuous Environment, CVPR Workshop on Embodied AI, 2025
Modal-specific Pseudo Query Generation for Video Corpus Moment Retrieval, EMNLP, 2022
Research Experience
Research intern at KIST, mentored by Hwasup Lim and Taekgeun You, focusing on Embodied AI, particularly Vision-Language-Action models.
Education
Master's degree from Seoul National University (SNU), advised by Byoung-Tak Zhang; Bachelor's degree from Yonsei University; Internship at A*STAR, mentored by Haiyue Zhu.
Background
Research interests include multimodal AI, generative AI, and data-center AI. Most of my research is about understanding video and images with language guidance, thereby developing embodied AI from internet AI.