GGT-100K: Generative Ground Truth for Generalizable Real-World Image Restoration Paper • 2605.31039 • Published 7 days ago • 41
LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence Paper • 2605.25979 • Published 11 days ago • 27
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding Paper • 2605.27365 • Published 10 days ago • 137
Eagle Collection Eagle is a family of frontier vision-language models with data-centric strategies. The model supports both HD image and long-context video input. • 17 items • Updated about 12 hours ago • 45
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding Paper • 2605.27365 • Published 10 days ago • 137