Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
Do Vision Transformers Need All-to-All Attention? Global Communication Through Elastic Learned Cores
Alan Z. Song, Yinjie Chen, Mu Nan +8
Vision Transformers (ViTs) learn rich visual-semantic representations through all-to-all self-attention among patch tokens. However, this design implicitly assumes that direct pair…
cs.CV2026
Human-like Object Grouping in Self-supervised Vision Transformers
Hossein Adeli, Seoyoung Ahn, Andrew Luo +3
Vision foundation models trained with self-supervised objectives achieve strong performance across diverse tasks and exhibit emergent object segmentation properties. However, their…
cs.CV2025
Towards Interpretable Visual Decoding with Attention to Brain Representations
Pinyuan Feng, Hossein Adeli, Wenxuan Guo +3
Recent work has demonstrated that complex visual stimuli can be decoded from human brain activity using deep generative models, offering new ways to probe how the brain represents…