cv

Deep Learning Researcher

Naver Webtoon AI

Worked on large-scale generative models for images, videos, and 3D assets; developed internal diffusion pipelines and multimodal tooling.

• Built internal Python library for image, video, and 3D content generation using state-of-the-art diffusion models.
• Developed AI Studio, a user-friendly generative framework for creation and inpainting.
• Collaborated with SNU Visual Computing Lab on CHUPA (ICCV 2023 Oral, ECCV 2024 Oral).

Deep Learning Researcher

Deepbrain AI

Worked on deepfake detection and large-scale video dataset construction.

• Developed KoDF, a major Korean deepfake detection dataset.
• First-author contribution to KoDF paper accepted at ICCV 2021.

Research Assistant

Columbia University – CGUI Lab

Worked on Augmented Reality interfaces for medical imaging and intraoral scanning.

• Contributed to AR-assisted intraoral scanning research (Journal of Prosthodontics 2024).

Data Scientist

Emadri

Designed recommendation systems for recommending packing list items for travelers.

Data Analyst

Krafton

Provided 20+ data analysis papers on TERA, Krafton’s leading MMORPG Title.

Ph.D.

University of Central Florida

Computer Science

Master of Science

Columbia University

Data Science

Bachelor of Arts

University of Virginia

Computer Science, Statistics

GraspDiffusion: Synthesizing Realistic Whole-body Hand-Object Interaction

WACV 2026

Introduces a diffusion-based method for generating realistic, full-body hand-object interactions.

Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models

ECCV 2024

Presents a method for affordance discovery using pretrained 2D diffusion models.

Augmented-Reality-Assisted Intraoral Scanning: A Proof-of-Concept Study

Journal of Prosthodontics 2024

Demonstrates the use of AR to enhance intraoral scanning workflows.

Chupa: Carving 3D Clothed Humans from Skinned Shape Priors Using 2D Diffusion Probabilistic Models

ICCV 2023 (Oral)

Proposes a diffusion-driven pipeline for 3D clothed human reconstruction.

Interactive Cartoonization with Controllable Perceptual Factors

CVPR 2023

Presents a controllable cartoonization framework using perceptual factor modulation.

LPMM: Intuitive Pose Control for Neural Talking-Head Model via Landmark-Parameter Morphable Model

arXiv

KoDF: A Large-scale Korean DeepFake Detection Dataset

ICCV 2021

Introduces a large-scale deepfake detection dataset focused on Asian subjects.

AI Photocard

Internal Python library for generating images, videos, and 3D assets using diffusion models.

• Python-based diffusion pipelines

AI Studio

User-friendly generative AI system enabling image creation and inpainting.

• Python, C#

ARIOS: AR-assisted Intraoral Scanning

Developed AR pipeline for improved intraoral scanning procedures.

• C#
• AR Research

Chupa

Diffusion-based 3D human reconstruction pipeline developed with SNU Visual Computing Lab.

• ICCV 2023 Oral

KoDF Dataset

Large-scale Asian deepfake dataset with detection model.

Pally: AR for Social Transition

Microsoft HoloLens + 5G project supporting social development for autistic children.

ICCV Oral

ICCV

Top 1.8% of submissions for CHUPA (ICCV 2023 Oral).

Verizon 5G EdTech Challenge – Winning Project

Verizon

Top 10 selected projects for Pally.

IBM Call for Code Hackathon – 1st Place

IBM

Order of the Orange Stole

University of Virginia

Recognition for early graduation.

Dean’s List

University of Virginia

For academic excellence.