vggt
๐
447
VGGT (CVPR 2025)
GOT - OCR (from : UCAS, Beijing)
Generate unique images from text descriptions
Generate images from text descriptions
Identify objects in real-time video
Track, rank and evaluate open LLMs and chatbots
Embedding Leaderboard
Describe images and extract text with Florence-2
Enhance photo of a document with selected approaches!