VLMs exhibit consistent vertical-distance entanglement in embeddings from perspective bias in natural images, producing accuracy gaps that a new synthetic benchmark SpatialTunnel exposes as model-intrinsic.
Is the {obj1} closer to the camera than the {obj2}?
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Why Far Looks Up: Probing Spatial Representation in Vision-Language Models
VLMs exhibit consistent vertical-distance entanglement in embeddings from perspective bias in natural images, producing accuracy gaps that a new synthetic benchmark SpatialTunnel exposes as model-intrinsic.