Youngbeom Yoo
Youngbeom Yoo
Embedded Files
Hi👋, I'm Youngbeom Yoo.
I am a Ph.D. Student in Artificial Intelligence at Yonsei University advised by Prof. Seon Joo Kim.
I received Bachelor's Degree in Biomedical Engineering at Hankuk University of Foreign Studies.
Research Interests: Video Understanding, Spatial Reasoning
Experience
Experience
LG AI Research May 2026 - current
Research Scientist Intern
EXAONE Lab.
CIPLAB Jan 2024 - Feb 2024
Undergraduate Student Researcher
Advisor: Prof. Seon Joo Kim
SIITLAB Jan 2023 - Dec 2023
Undergraduate Student Researcher
Advisor: Prof. Junmo Kim
Dream2Real Jul 2022 - May 2023
AI Researcher
Seoul St.Mary's Hospital Jul 2021 - Feb 2022
Undergraduate Student Researcher
Advisor: Prof. Yoonho Nam & Joon-Yong Jung
Publications
Publications
Keep It Simple: Multi-Key Episodic Memory Retrieval for Ultra-long Video Understanding
Yeeun Choi, Youngbeom Yoo, Joon-Young Lee, Hyolim Kang*, Seon Joo Kim*
ECCV 2026
Coming Soon!
DyhimemSkill: Dynamic Hierarchical Memory and Task-Specific Skills for HD-EPIC VQA Challenge
Youngbeom Yoo, Yeeun Choi, Hyolim Kang, Seon Joo Kim
CVPRW 2026 @ EgoVis - HD-EPIC VQA Challenge🥉
Representing 3D Shapes With 64 Latent Vectors for 3D Diffusion Models
In Cho, Youngbeom Yoo, Subin Jeon, Seon Joo Kim
ICCV 2025
Paper / Project page / Code
Open-ended Hierarchical Streaming Video Understanding with Vision Language Models
Hyolim Kang*, Yunsu Park*, Youngbeom Yoo, Yeeun Choi, Seon Joo Kim
ICCV 2025
Real-Time Polyp Detection in Colonoscopy using Lightweight Transformer
Youngbeom Yoo*, Jae Young Lee*, Dong-Jae Lee, Jiwoon Jeon, Junmo Kim
WACV 2024
Awards & Honors
Awards & Honors
EgoVis CVPR 2026 Workshop Jun 2026
🥉3rd Place in HD-EPIC VQA Challenge
DyhimemSkill: Dynamic Hierarchical Memory and Task-Specific Skills for HD-EPIC VQA Challenge
ScanNet++ CVPR 2024 Workshop Jun 2024
🥉3rd Place in 3D Semantic Segmentation Challenge
Image-Point Fusion Point Transformer method
2022 AI Data Quality Improvement Open Lab Program Dec 2022
Special Award
A methodology for visualizing the domain gap between 3D synthetic data and real data using interior space 3D comprehensive data
Page updated
Google Sites
Report abuse