- Paper: 'Training-free Code-based Image Retouching with Vision Language Models', submitted
- Paper: 'Automated Model Discovery via Multi-modal & Multi-step Pipeline', NeurIPS'25
- Paper: 'SYNAuG: Exploiting Synthetic Data for Data Imbalance Problems', Pattern Recognition Letters'25 (IF 3.9)
- Workshop Paper: 'VLM’s Eye Examination: Instruct and Inspect Visual Competency of Vision Language Model', TMLR'25
Research Experience
- Full-time Research Intern, Huawei London Research Center, UK (Jan. 2025 - Dec. 2025)
- Projects: RetouchLLM & Automatic Photomontage
- Collaborators: Jiankang Deng, Ismail Elezi, Roy Miles
Education
- Ph.D. Student, POSTECH, South Korea, Advisor: Prof. Tae-Hyun Oh (Mar. 2022 - Present)
- Master's in Electrical Engineering, POSTECH, South Korea (Mar. 2020 – Feb. 2022)
- Bachelor's degree, Chung-Ang University (CAU), South Korea
Background
Research Interests: Reliable and automated multimodal systems by exploiting VLM & LLM as human proxies; Keywords: VLM & LLM, Agentic System, SFT & PO, Model Evaluation, Data Augmentation & Construction.