Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning Paper • 2502.06781 • Published 15 days ago • 59
Tajik Datasets Collection Datasets that have tajik subset or entirely tajik • 13 items • Updated 5 days ago • 3
SYNTHETIC-1 Collection A collection of tasks & verifiers for reasoning datasets • 9 items • Updated 5 days ago • 48
GeoPixel Collection Pixel Grounding Large Multimodal Model in Remote Sensing • 3 items • Updated 5 days ago • 1