PreView improves GUI grounding without retraining the model
A lightweight preprocessor adds zoomed views and cues, lifting accuracy for three frozen vision-language models on five benchmarks.
1 stories, newest first · one card per story
A lightweight preprocessor adds zoomed views and cues, lifting accuracy for three frozen vision-language models on five benchmarks.
Today 1K readers · 1.5K views · 1.1K reads · all time 159K views