AutoGUI automatically generates contextual functionality annotations for 704k UI elements by having an LLM compare screen state before and after simulated interactions, and training on this data improves VLM UI grounding.
This element redirects the user to a specific website, allowing them to access its content and services
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
unclear 1representative citing papers
citing papers explorer
-
AutoGUI: Scaling GUI Grounding with Automatic Functionality Annotations from LLMs
AutoGUI automatically generates contextual functionality annotations for 704k UI elements by having an LLM compare screen state before and after simulated interactions, and training on this data improves VLM UI grounding.