DINOv3 Collection DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 13 items • Updated Aug 21, 2025 • 478
KVAE 1.0 Collection KVAE 1.0 tokenizers are for images (KVAE-2D-1.0) and video (KVAE-3D-1.0) are distributed under MIT license (commercial use is possible). • 2 items • Updated Dec 14, 2025 • 7
MedGemma Release Collection Collection of Gemma 3 variants for performance on medical text and image comprehension to accelerate building healthcare-based AI applications. • 9 items • Updated 24 days ago • 434