Align Once to Explain: Feature Alignment for Scalable B-cosification of Foundational Vision Transformers
Open paper
Benchmark
Model
Rank
Results
image-classification-on-cifar-100
ALOE DINOv3 ViT-B/16
#54
Percentage correct: 89.14
image-classification-on-cifar-10
ALOE DINOv3 ViT-B/16
#75
Percentage correct: 98.08
Rank counts only results with a code link.