3 papers
cs.CV2026
SiNGER: A Clearer Voice Distills Vision Transformers Further
Geunhyeok Yu, Sunjae Jeong, Yoonyoung Choi +2
Vision Transformers are widely adopted as the backbone of vision foundation models, but they are known to produce high-norm artifacts that degrade representation quality. When know…
cs.LG2026
Scale-Consistent State-Space Dynamics via Fractal of Stationary Transformations
Geunhyeok Yu, Hyoseok Hwang
Recent deep learning models increasingly rely on depth without structural guarantees on the validity of intermediate representations, rendering early stopping and adaptive computat…
cs.CV2024
A2XP: Towards Private Domain Generalization
Geunhyeok Yu, Hyoseok Hwang
Deep Neural Networks (DNNs) have become pivotal in various fields, especially in computer vision, outperforming previous methodologies. A critical challenge in their deployment is…