Zebra-CoT Dataset
Zebra CoT
university
AI & ML interests
chain-of-thought
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 • 4.29k • 64
multimodal-reasoning-lab/Chess
Viewer
• Updated
• 20.5k • 196 • 2
multimodal-reasoning-lab/Connect-Four
Viewer
• Updated
• 2.03k • 107
multimodal-reasoning-lab/Ciphers
Viewer
• Updated
• 6.59k • 112
multimodal-reasoning-lab/Checkers
Viewer
• Updated
• 2.75k • 101
multimodal-reasoning-lab/Chemistry
Viewer
• Updated
• 4.67k • 116 • 7
multimodal-reasoning-lab/Visual-Jigsaw
Viewer
• Updated
• 21.9k • 138 • 1
multimodal-reasoning-lab/Physics
Viewer
• Updated
• 7.09k • 141 • 4
multimodal-reasoning-lab/RPM
Viewer
• Updated
• 3k • 89 • 1
multimodal-reasoning-lab/Maze
Viewer
• Updated
• 20k • 58