Scholar
Chanhyuk Lee
Google Scholar ID: mpSpDHcAAAAJ
KAIST
Citations & Impact
Citations
15
H-index
2
i10-index
1
Publications
3
Co-authors
5
list available
Publications
Resume (English only)
Academic Achievements
- - One paper accepted at NeurIPS 2025
- - [P2] AdaRank: Adaptive Rank Pruning for Enhanced Model Merging, Preprint, arXiv
- - [P1] Revisiting Weight Averaging for Model Merging, Preprint, arXiv
- - [C1] Universal Few-Shot Spatial Control for Diffusion Models, Conference on Neural Information Processing Systems (NeurIPS), 2025, arXiv
Research Experience
- - Working in VL Lab, led by Prof. Seunghoon Hong
- - Current research focuses on model fusion and parameter alignment
Education
- - M.S. in Computer Science, Korea Advanced Institute of Science and Technology (KAIST), Mar. 2025 - Present, Advisor: Prof. Seunghoon Hong
- - B.S. in Computer Science and Chemistry (Double Major), Korea Advanced Institute of Science and Technology (KAIST), Mar. 2019 - Feb. 2025
- - Gyeonggi Science High School for Gifted, Mar. 2016 - Feb. 2019
Background
- - Research Interests: Neural network scaling, particularly developing efficient approaches to build large models with limited resources.
- - Professional Field: Computer Science and Chemistry
- - Introduction: Currently a Master's student at KAIST School of Computing, focusing on model fusion and parameter alignment, exploring how different networks can be combined while preserving their capabilities.
