Posts tagged with "uitag"
- Hybrid UI Detection: Why We Split Vision and Intelligenceuitag combines Apple Vision's text detection with a fine-tuned YOLO model to hit 90.8% coverage on ScreenSpot-Pro — faster and cheaper than VLM-only approaches.
- Benchmarking UI Detection on ScreenSpot-ProHow we evaluated uitag against 1,581 annotations across 26 professional macOS applications — methodology, results, and what the numbers actually mean.
- Why Detection and Intelligence Should Be Separate LayersThe architectural argument for splitting UI perception from UI reasoning — and what happens when you don't.
- Multi-Signal Verification for VLM UI AgentsOne detection method is a guess. Two that agree are evidence. How Leith uses signal redundancy to make UI interaction reliable.