google/paligemma2-28b-pt-896
Image-Text-to-Text • 28B • Updated • 506 • 52
vision
-
-
lmstudio-community/olmOCR-7B-0225-preview-GGUF
Image-Text-to-Text • 8B • Updated • 244 • 13 -
vidore/colqwen2.5-v0.2
Visual Document Retrieval • Updated • 104k • 99 -
vidore/colpali-v1.3
Visual Document Retrieval • Updated • 13.8k • 99 -
vidore/colSmol-500M
Visual Document Retrieval • Updated • 1.41k • 22 -
deepseek-ai/deepseek-vl2
Image-Text-to-Text • 27B • Updated • 4.75k • 387 -
gen2seg: Generative Models Enable Generalizable Instance Segmentation
🚀6A demo of our gen2seg SD and MAE-H models.
-
nvidia/NitroGen
Reinforcement Learning • Updated • 555 -
naver-hyperclovax/HyperCLOVAX-SEED-Omni-8B
Text Generation • 11B • Updated • 288 • 191 -
microsoft/Phi-4-reasoning-vision-15B
Image-Text-to-Text • 15B • Updated • 4.17k • 173 -
nvidia/asset-harvester
Image-to-3D • Updated • 141 • 39 -
facebook/sam3.1
Mask Generation • Updated • 88.2k • 419 -
MeshWeaver: Sparse-Voxel-Guided Surface Weaving for Autoregressive Mesh Generation
Paper • 2606.04688 • Published • 5