asatpath/Sim2Reason-Data
Viewer • Updated • 1.95k • 125
Sim2Reason
Official models and datasets for the paper Sim2Reason.
-
-
asatpath/Sim2Reason-3B
3B • Updated • 74 • 1 -
asatpath/Sim2Reason-7B
8B • Updated • 53 • 1 -
asatpath/Sim2Reason-14B
15B • Updated • 71 • 1 -
asatpath/Sim2Reason-30B
31B • Updated • 37 -
asatpath/Sim2Reason-32B
33B • Updated • 38 -
Solving Physics Olympiad via Reinforcement Learning on Physics Simulators
Paper • 2604.11805 • Published • 16