Scholar
Youngwan Lee
Google Scholar ID: EqemKYsAAAAJ
Electronics and Telecommunications Research Institute; KAIST
Citations & Impact
Citations
2,223
H-index
13
i10-index
14
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- 2025: Paper 'VideoICL' accepted at CVPR 2025
- 2025: Two papers accepted at ICLR 2025
- 2024: Paper 'KOALA' accepted at NeurIPS 2024
- 2024: Paper 'DiT-Pruner' accepted at ECCVW 2024 (Workshop on Green Foundation Models)
- 2024: Paper 'EVEREST' accepted at ICML 2024
- Dec 2023: Released KOALA, a fast text-to-image synthesis model
- 2023: Two papers accepted at ICLR 2023
- 2022: One paper accepted at CVPR 2022
- Published multiple papers at top-tier venues including CVPR, ICLR, NeurIPS, ICML, and ECCV, covering topics such as diffusion model compression, video understanding, multimodal safety, and efficient Transformers
Background
- Ph.D. student at the Graduate School of AI, KAIST, advised by Prof. Sung Ju Hwang in the Machine Learning and Artificial Intelligence (MLAI) Lab
- Senior researcher at the Visual Intelligence Lab, ETRI, Daejeon, South Korea
- Research interests include how computers understand the world, with a focus on efficient 2D/3D neural network design, object detection, instance segmentation, semantic segmentation, and video classification
- Has explored Vision Transformer architectures and self-supervised learning
- Recently focused on multimodal learning, including text-to-image generation and safety for vision-language models
- Advocates for 'Slow Science'
Co-authors