Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks Paper β’ 2501.08326 β’ Published Jan 14 β’ 35
Running 19 19 Hugging Face Values π€ Empower users to use machine learning through an open collaboration platform
Running 542 542 Vision Arena (Testing VLMs side-by-side) πΌ Analyze images to detect and label objects