Fine-tuning three VLMs on a synthetic, chain-of-thought-supervised street-view QA dataset substantially improves spatial reasoning, with the largest gains on negation and counterfactual questions.
End-to- end object detection with transformers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
How Well Do Vision--Language Models Understand Cities? A Comparative Study on Spatial Reasoning from Street-View Images
Fine-tuning three VLMs on a synthetic, chain-of-thought-supervised street-view QA dataset substantially improves spatial reasoning, with the largest gains on negation and counterfactual questions.