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.CV2026
Keep it SymPL: Symbolic Projective Layout for Allocentric Spatial Reasoning in Vision-Language Models
Jaeyun Jang, Seunghui Shin, Taeho Park +1
Perspective-aware spatial reasoning involves understanding spatial relationships from specific viewpoints-either egocentric (observer-centered) or allocentric (object-centered). Wh…
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…