Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
TextSpan
anchor
Findings
IC-108
Per-patch logit lens confidence in LLaVA localizes objects spatially, achieving mAP 79.90 on ImageNet segmentation, 8.03% above raw VLM attention
[compared-to]
IC-678
Specific attention heads in CLIP ViT-L's last 4 layers encode specific image properties (color, shape, location, counting, texture) that are linearly recoverable via text directions
[primary]
IC-679
CLIP relies on background/location as a spurious cue for bird classification, and ablating geolocation heads improves worst-group accuracy by 25.2%
[primary]