Zebra-CoT Dataset
Zebra CoT
university
AI & ML interests
None defined yet.
Recent Activity
View all activity
Organization Card
The Multimodal Reasoning Lab brings together researchers from Columbia, U Maryland, USC, and NYU.
We created the Zebra‑CoT dataset to enable interleaved vision–language reasoning and have developed state-of-the-art visual reasoning models built on this foundation.
datasets
19
multimodal-reasoning-lab/Zebra-CoT
Viewer
•
Updated
•
160k
•
6.97k
•
52
multimodal-reasoning-lab/Chess
Viewer
•
Updated
•
20.5k
•
82
•
2
multimodal-reasoning-lab/Connect-Four
Viewer
•
Updated
•
2.03k
•
17
multimodal-reasoning-lab/Ciphers
Viewer
•
Updated
•
6.59k
•
63
multimodal-reasoning-lab/Checkers
Viewer
•
Updated
•
2.75k
•
20
multimodal-reasoning-lab/Chemistry
Viewer
•
Updated
•
4.67k
•
41
•
7
multimodal-reasoning-lab/Visual-Jigsaw
Viewer
•
Updated
•
21.9k
•
53
•
1
multimodal-reasoning-lab/Physics
Viewer
•
Updated
•
7.09k
•
83
•
2
multimodal-reasoning-lab/RPM
Viewer
•
Updated
•
3k
•
19
•
1
multimodal-reasoning-lab/Maze
Viewer
•
Updated
•
20k
•
51