RESEARCH FIELD
- Vision-Language-Action(VLA) Models
- Foundation Models for Robotics
- Multimodal Learning
EDUCATION
- 2024.09. - 2026.08.: M.S. Student in the School of Integrated Technology, GIST
- 2018.03. - 2024.08. : B.S. in Industrial Systems Engineering, GNU
WORK EXPERIENCE
- 2026.09 - present : Researcher in Korea Electronics Technology Institute (KETI)
- 2023.09. - 2024.08. : Internship at GIST AILAB
- 2023.04. - 2023.09. : Undergraduate Research Student at GNU DXLAB
Project
- 2024 - present : 스스로 불확실성을 자각하며 질문하면서 성장하는 에이전트 기술 개발 (과학기술정보통신부)
- 2024 - present: 고령자의 연속적인 통합 돌봄을 위한 AI*로봇 기반 디지털 트윈 돌봄 플랫폼 (보건복지부)
- 2024: 3D 모델 기반 객체 인식 및 AR 시각화 기술 PoC (현대자동차)
Publications - Domestic
- 박유민, 유연국, 이규빈, 시각언어모델을 활용한 개방형 지시문 기반 로봇 파지 대상 객체 분할 및 선택 시스템, (KRoC 2026)
Publications - INTERNATIONAL
- Park, Y., Yu, Y., Heo, Y., Lee, G., “Branch Soup: Improving Vision Foundation Model via Averaging Adapter Weights of Branched Checkpoints”,
NEUROCOMPUTING (Q1, IF 6.7), (2026)
- Kim, J., Park, Y., Hyun, S., Heo, Y., Yu, Y., Lee. S., Lee, G., “Human-Efficient Annotation System via Active Semi Supervised Learning and Selective Review”,
INTELLIGENT SYSTEM WITH APPLICATIONS (Q1, IF 5.5), (2026)
- Park, Y., Moon, S.*, Kim, J., and Chi, S., “Application of Domain-specific Thesaurus to Construction Documents based on Flow Margin of Semantic Similarity.”
ICCEPM 2024, Sapporo, Japan, (2024)
AWARD
- 2024, International Conference on Construction Engineering and Project Management(ICCEPM2024), Best Paper Award
← Members