Pinned Loading

1. TRAPO TRAPO Public

   Official Repository of "[ICLR26] TRAPO: A Semi-Supervised Reinforcement Learning Framework for Boosting LLM Reasoning"

   Python 29 1

2. OLR OLR Public

   Can LLMs Learn to Reason Robustly under Noisy Supervision?

   Python 11 1

3. OPRD OPRD Public

   OPRD: On-Policy Representation Distillation (https://arxiv.org/abs/2606.06021)

   Python 86 4