A fine-tuned small multimodal LLM outperforms much larger general models on urban tasks in a new benchmark, with caveats about benchmark overlap with training data.
Touchdown: Natural language naviga- tion and spatial reasoning in visual street environments
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence with Spatial Reasoning and Understanding
A fine-tuned small multimodal LLM outperforms much larger general models on urban tasks in a new benchmark, with caveats about benchmark overlap with training data.