Cambrian-S: Towards Spatial Supersensing in Video
Paper • 2511.04670 • Published • 39
Cambrian-S Models
-
-
nyu-visionx/Cambrian-S-7B-LFP
8B • Updated • 733 • 3 -
nyu-visionx/Cambrian-S-7B
Image-to-Text • 8B • Updated • 1.36k • 5 -
nyu-visionx/Cambrian-S-3B
Image-to-Text • 3B • Updated • 752 • 1 -
nyu-visionx/Cambrian-S-1.5B
Image-to-Text • 2B • Updated • 68 • 3 -
nyu-visionx/Cambrian-S-0.5B
Image-to-Text • 0.9B • Updated • 412 • 2 -
nyu-visionx/Cambrian-S-7B-S2
8B • Updated • 1.61k -
nyu-visionx/Cambrian-S-7B-S3
8B • Updated • 51.3k -
nyu-visionx/Cambrian-S-7B-S1
8B • Updated • 16 -
nyu-visionx/Cambrian-S-0.5B-S1
0.9B • Updated -
nyu-visionx/Cambrian-S-0.5B-S2
0.9B • Updated • 7 -
nyu-visionx/Cambrian-S-0.5B-S3
0.9B • Updated • 192 -
nyu-visionx/Cambrian-S-1.5B-S1
2B • Updated • 3 -
nyu-visionx/Cambrian-S-1.5B-S2
2B • Updated • 6 -
nyu-visionx/Cambrian-S-1.5B-S3
2B • Updated • 2 -
nyu-visionx/Cambrian-S-3B-S1
3B • Updated -
nyu-visionx/Cambrian-S-3B-S2
3B • Updated -
nyu-visionx/Cambrian-S-3B-S3
3B • Updated • 35