News
- Mar. 2026 I begin to work as an Applied AI Researcher at Krafton AI. Career
- Jan. 2026 Our What "Not" to Detect paper got accepted to ICLR 2026! Paper
- Oct. 2025 Two papers PartCATSeg and 3D-Aware VLM Finetuning selected as QIFK 2025 Finalist. Award
- Aug. 2025 Our 3D-Aware VLM Finetuning paper accepted to EMNLP 2025 Findings. Paper
- Jun. 2025 I got ML engineering internship at Snap Inc. in Santa Monica, CA. Career
- Jun. 2025 I got awarded Korean Presidential Science Scholarship for Graduate Students. Award
- May. 2025 Our ScribbleDiff paper accepted to ICIP 2025. Paper
- Feb. 2025 Our PartCATSeg paper accepted to CVPR 2025. Paper
- Jan. 2025 Our DreamCatalyst paper accepted to ICLR 2025. Paper
- Sep. 2024 Our PartCLIPSeg paper accepted to NeurIPS 2024. Paper
- Sep. 2023 Joined CVML Lab as an M.S. graduate student at KAIST AI. Career
Selected Publications
All Publications →
* equal contribution · † corresponding author
3D-Aware Vision-Language Models Fine-Tuning with Geometric Distillation
DreamCatalyst: Fast and High-Quality 3D Editing via Controlling Editability and Identity Preservation
Understanding Multi-Granularity for Open-Vocabulary Part Segmentation
Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Views
Work Experience
Krafton AI
Applied AI Researcher
- Working in AI Art Gen Team at Krafton AI.
Snap Inc.
ML Engineer Intern
- Led cross-reference dataset preprocessing pipeline for personalized video generation
- Developed cross-reference dataset pipeline and multi-subject adapter architecture for VideoAlchemist 2.0
Selected Projects
All Projects →
Raon-VisionEncoder
Krafton AI
A Fully Open SigLIP2-class Vision Encoder
- Developed a vision encoder with comparable performance to SigLIP2-NaFlex using only open data
- Built VLM training pipeline integrating the vision encoder with a language model for downstream VQA evaluation and training optimization
VideoAlchemist 2.0
Snap Inc.
Multi-Subject Personalized Video Generation
- Developed a personalized video generation model supporting multiple subjects with fine-grained temporal control
- Built cross-reference dataset pipeline and multi-subject adapter architecture for personalized video generation
- Contributed to foundation of dataset generation pipeline and adapter design of AlcheMinT
3D-Aware VLM Finetuning
Samsung Research
- Electronic Device and Method for Operating Thereof and Storage Medium
- Paper: 3D-Aware Vision-Language Models Fine-Tuning with Geometric Distillation
Korean Patent: 10-2025-0109574
Education
M.S. in Artificial Intelligence
B.S. in Computer Science and Engineering
Honors & Awards
Grand Prize, IPIU 2026
Paper: What "Not" to Detect
Feb. 2026
Selected by Qualcomm AI Research · PartCATSeg & 3D-Aware VLM Finetuning
Oct. 2025
Korean Presidential Science Scholarship for Graduate Students
Awarded by the President of Korea
Jun. 2025
2nd Place, Open Vocabulary Part Segmentation Challenge at CVPR 2024
2nd Place on both Track 1 & 2 · 4th Workshop on Open World Vision (VPLOW) at CVPR 2024
2024
Excellence Award, 2023 POSTECH OIBC Challenge
3rd Place (3/120) · AI Competition of Solar Power Generation Forecasting
Dec. 2023
2022 ICPC Asia Korea Regional Contest
48th in Korea, 62nd in Preliminary
2022
Dean's List, Sogang University
Top 1%: Spring 2018, Spring 2019, Fall 2022 · Top 5%: Fall 2018
2018 – 2022
Korea National Science and Technology Scholarship
Spring 2019, Fall 2022, Spring 2023, Fall 2023 (4 Semesters)
2019 – 2023
Academic Activities
Reviewer
CVPRW 2026, 3DV 2026
2026