Cambrian-S: Towards Spatial Supersensing in Video
Paper
•
2511.04670
•
Published
•
37
Cambrian-S Models
-
-
nyu-visionx/Cambrian-S-7B-LFP
8B • Updated • 1.24k • 3 -
nyu-visionx/Cambrian-S-7B
Image-to-Text • 8B • Updated • 3k • 5 -
nyu-visionx/Cambrian-S-3B
Image-to-Text • 3B • Updated • 2.9k • 1 -
nyu-visionx/Cambrian-S-1.5B
Image-to-Text • 2B • Updated • 27 • 3 -
nyu-visionx/Cambrian-S-0.5B
Image-to-Text • 0.9B • Updated • 565 • 2 -
nyu-visionx/Cambrian-S-7B-S2
8B • Updated • 63 -
nyu-visionx/Cambrian-S-7B-S3
8B • Updated • 260 -
nyu-visionx/Cambrian-S-7B-S1
8B • Updated • 14 -
nyu-visionx/Cambrian-S-0.5B-S1
0.9B • Updated • 3 -
nyu-visionx/Cambrian-S-0.5B-S2
0.9B • Updated • 23 -
nyu-visionx/Cambrian-S-0.5B-S3
0.9B • Updated • 22 -
nyu-visionx/Cambrian-S-1.5B-S1
2B • Updated • 9 -
nyu-visionx/Cambrian-S-1.5B-S2
2B • Updated • 8 -
nyu-visionx/Cambrian-S-1.5B-S3
2B • Updated • 7 -
nyu-visionx/Cambrian-S-3B-S1
3B • Updated • 7 -
nyu-visionx/Cambrian-S-3B-S2
3B • Updated • 6 -
nyu-visionx/Cambrian-S-3B-S3
3B • Updated • 6