GUI-Lens improves GUI grounding by having a VLM iteratively select crops to zoom into, guided by OCR and UI detector references, and verifies its proposed clicks before outputting a coordinate.
Claude3.7SonnetSystemCard
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
-
GUI-Lens: Coarse-to-Fine Cropping for GUI Grounding with General-Purpose VLMs
GUI-Lens improves GUI grounding by having a VLM iteratively select crops to zoom into, guided by OCR and UI detector references, and verifies its proposed clicks before outputting a coordinate.