nvidia/PS3-1.5K-SigLIP2
Image Feature Extraction • 1B • Updated • 94 • 3
PS3: Scaling Vision Pre-Training to 4K Resolution
Enabling 4k resolution for VLMs, CVPR 2025, https://nvlabs.github.io/PS3/
-
-
nvidia/PS3-4K-SigLIP2
Image Feature Extraction • 1B • Updated • 147 • 2 -
nvidia/PS3_Lang-1.5K-SigLIP2
Image Feature Extraction • 0.5B • Updated • 87 • 2 -
nvidia/PS3_Lang-4K-SigLIP2
Image Feature Extraction • 0.6B • Updated • 79 • 1 -
nvidia/PS3-1.5K-C-RADIOv2
Image Feature Extraction • 0.9B • Updated • 76 • 1 -
nvidia/PS3-4K-C-RADIOv2
Image Feature Extraction • 1.0B • Updated • 79 • 1 -
nvidia/PS3-1.5K-SigLIP
Image Feature Extraction • 0.9B • Updated • 140 • 6 -
nvidia/PS3-4K-SigLIP
Image Feature Extraction • 1B • Updated • 92 • 4 -
nvidia/VILA-HD-8B-PS3-1.5K-SigLIP2
Image-Text-to-Text • Updated • 432 • 1 -
nvidia/VILA-HD-8B-PS3-4K-SigLIP2
Image-Text-to-Text • Updated • 167 • 3 -
nvidia/VILA-HD-8B-PS3-1.5K-C-RADIOv2
Image-Text-to-Text • Updated • 135 • 1 -
nvidia/VILA-HD-8B-PS3-4K-C-RADIOv2
Image-Text-to-Text • Updated • 132 • 1 -
nvidia/VILA-HD-8B-PS3-1.5K-SigLIP
Image-Text-to-Text • Updated • 149 • 4 -
nvidia/VILA-HD-8B-PS3-4K-SigLIP
Image-Text-to-Text • Updated • 138 • 2 -
Scaling Vision Pre-Training to 4K Resolution
Paper • 2503.19903 • Published • 42