A domain-specialized 7B vision-language model improves most planning-map interpretation scores on a new 300-example benchmark, but the headline 'best overall' claim is contradicted by the same table.
It serves as an important transportation hub in the image
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
PlanGPT-VL: Enhancing Urban Planning with Domain-Specific Vision-Language Models
A domain-specialized 7B vision-language model improves most planning-map interpretation scores on a new 300-example benchmark, but the headline 'best overall' claim is contradicted by the same table.