Multi-view geometry, scene representations, and feed-forward reconstruction for visual understanding.
Research Focus
What I work on
Understanding human-object interactions, tool choice, and physical state changes from first-person videos.
Building structured data, annotation workflows, and evaluation protocols for embodied AI research.
Education
Academic background
- B.S. in Electrical Engineering
- Mar 2021 – Expected Aug 2027
- GPA: 4.1/4.3 (Major GPA: 4.19/4.3)
- Exchange Student, School of Electrical and Electronic Engineering
- Jan 2026 – May 2026
Research Experience
Labs & roles
S-Lab (MMLab), NTU
Jan 2026 – Present
Research Intern (Advisor: Prof. Ziwei Liu, NTU)
- Co-leading EgoTools, a tool-centric egocentric dataset and benchmark for embodied tool-use reasoning, with focus on data collection, annotation workflows, quality control, and benchmark design.
Computer Vision Lab (CVLAB), KAIST AI
Jun 2025 – Dec 2025
Research Intern (Advisor: Prof. Seungryong Kim, KAIST AI)
- Conducting research on 3D vision: multi-view scene reconstruction pipelines integrating Gaussian Splatting and transformer-based depth estimation (VGGT / NoPoSplat).
Video and Image Computing Lab (VICLAB), KAIST
Dec 2024 – Jun 2025
Research Intern (Advisor: Prof. Mun Churl Kim, KAIST EE)
- Reviewed object detection models (RCNN–YOLO, ViT).
- Implemented baseline detectors for few-shot and anomaly detection tasks.
Publications
Selected work
1
EgoTools: Tool-Centric Reasoning in Real-World Egocentric Videos.
2
C3G: Learning Compact 3D Representations from Feed-Forward Novel View Synthesis.
*Equal contribution.
Projects
Technical projects
FaceVerify-AM: Face Verification with AM-Softmax (EE.40034, KAIST)
Two-stage metric-learning pipeline for face verification using ResNet-18 and AM-Softmax.
- Scratch training → fine-tuning structured training design
- Ablation on loss, optimizer, LR scheduler, and augmentation strategies
- Achieved 8.02% EER (baseline: 22.31%)
Honors
Awards & scholarships
- KAIST Presidential Fellowship (15th) Feb 2025 – Present
- KAIST EE, Dean’s List Award Spring 2024 Awarded to the top 3% of all EE students
- KAIST, Freshman Dean’s List Award Fall 2021 Awarded to the top 3% of all freshman students
- Woon Hae Scholarship (12th) Feb 2025 – Dec 2025
- National Science & Engineering Scholarship for Academic Excellence Aug 2025 – Present
- KAIST Shared Lives Award (Top-ranked Recipient) Feb 2026 For exceptional and sustained blood donation service (20 donations in one year)
Activities
Leadership & service
- KAIST AI Studying Club (Include) · Google Student Ambassador Sep 2024 – Dec 2025
- Young Engineers Honor Society (YEHS) Jan 2025 – Present
- EERun (KAIST EE Running Club), President Sep 2024 – Dec 2025
- KAIST Freshman Proctor / Freshman Tutoring Program Mar 2022 – Dec 2024
More activities available in CV.
Skills
Technical toolkit
Programming: Python, C/C++, PyTorch, Git, LaTeX
Research Tools: video preprocessing, dataset curation, annotation pipelines, evaluation scripts
Languages: Korean (Native), English (Fluent)