Scholar
Hyogon Ryu
Google Scholar ID: Xq5B3LQAAAAJ
KRAFTON
Citations & Impact
Citations
15
H-index
2
i10-index
0
Publications
3
Co-authors
4
list available
Resume (English only)
Academic Achievements
- 1. Paper 'DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion Models' accepted to ICLR 2025
- 2. Paper 'Memory-Efficient Fine-Tuning for Quantized Diffusion Model' accepted to ECCV 2024
- 3. Conference Reviewer for ICLR 2025
Research Experience
- 1. Naver Corp. (2022.01-2022.02)
- - Software Engineer Internship, Dept. of Multimodal Applications
- - Project: Extracting Trivia Sentence from Unstructured Text Data and Search Engine Improvement
- 2. AI Research Lab, Korea University (2021.01-2021.12)
- - Undergraduate Research Student (Advisor: Sangkyun Lee)
- - Project: Energy Backdoor Attacks on Deep Learning Models
Education
- 1. M.S. in Artificial Intelligence, KAIST, 2023.02-2025.02
- 2. B.S. in Cyber Defense, Korea University, 2019.03-2023.02
Background
- Currently pursuing a Master’s in AI at CVML Lab, KAIST. Earned a Bachelor’s degree in Cyber Defense from Korea University. Deeply interested in enhancing the efficiency of deep learning models, not only from a software perspective but also by focusing on hardware and system-aware optimization. While my work has primarily focused on diffusion model quantization, my broader goal is to eliminate redundancies in computationally intensive models to achieve sustainable AI.
