Popular repositories Loading

1. LUFFY LUFFY Public

   Official Repository of "Learning to Reason under Off-Policy Guidance"

   Python 450 66

2. TPO TPO Public

   Test-time preferenece optimization (ICML 2025).

   Jupyter Notebook 182 11

3. SU-01 SU-01 Public

   SU-01: Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling

   Python 80 5

4. Pi-Bench Pi-Bench Public

   Python 6

5. TRM TRM Public

   The code repository of paper "Characterizing, Evaluating, and Optimizing Complex Reasoning".

   Python 4