Scholar
Seonho Lee
Google Scholar ID: DFKGTG0AAAAJ
KAIST AI, ex-ML intern @ Snap Inc.
Citations & Impact
Citations
12
H-index
2
i10-index
0
Publications
6
Co-authors
0
Publications
Resume
Academic Achievements
- - Publications:
- 1. 3D-Aware VLM Finetuning with Geometric Distillation (EMNLP 2025 Findings)
- 2. Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part Segmentation (CVPR 2025)
- 3. Scribble-Guided Diffusion for Training-free Text-to-Image Generation (ICIP 2025)
- 4. DreamCatalyst: Fast and High-Quality 3D Editing via Controlling Editability and Identity Preservation (ICLR 2025)
- 5. Understanding Multi-Granularity for Open-Vocabulary Part Segmentation (NeurIPS 2024)
- 6. What “Not” to Detect: Improving Object Detection under Negation via Reasoning and Token Merging (Preprint)
- - Awards:
- 1. QIFK (Qualcomm Innovation Fellowship Korea) 2025 Finalist
- 2. Korean Presidential Science Scholarship for Graduate Students (June 2025)
Research Experience
- - Position: Graduate Researcher
- - Workplace: CVML Lab at KAIST
- - Projects:
- 1. Generative AI
- 2. Vision-Language Understanding
- - Internship Experience:
- - ML Engineer Intern at Snap Inc. (Jun 2025 - Sep 2025)
- - Data Engineer & Back-end Engineer at Life Planning Lab (Dec 2021 - Jan 2022)
Education
- - Degree: Master's
- - University: KAIST
- - Advisor: Prof. Hyunjung Shim
- - Duration: Sep 2023 - Present
- - Major: Artificial Intelligence
Background
- - Research Interests: AI, especially in Computer Vision
- - Field of Study: Artificial Intelligence
- - Brief Introduction: Aims to use AI to help people freely envision, realize, and share what they believe in
Miscellany
- - Personal Interests: Not explicitly mentioned