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
•
16.3k
•
49
multimodal-reasoning-lab/Chess
Viewer
•
Updated
•
20.5k
•
92
multimodal-reasoning-lab/Connect-Four
Viewer
•
Updated
•
2.03k
•
53
multimodal-reasoning-lab/Ciphers
Viewer
•
Updated
•
6.59k
•
70
multimodal-reasoning-lab/Checkers
Viewer
•
Updated
•
2.75k
•
93
multimodal-reasoning-lab/Chemistry
Viewer
•
Updated
•
4.67k
•
91
•
7
multimodal-reasoning-lab/Visual-Jigsaw
Viewer
•
Updated
•
21.9k
•
180
•
1
multimodal-reasoning-lab/Physics
Viewer
•
Updated
•
7.09k
•
113
multimodal-reasoning-lab/RPM
Viewer
•
Updated
•
3k
•
74
•
1
multimodal-reasoning-lab/Maze
Viewer
•
Updated
•
20k
•
113