Pinned Loading

1. Beyond-Log-Likelihood Beyond-Log-Likelihood Public

   [ICML'26 Spotlight] Beyond log-likelihood: exploring alternative objectives for supervised fine-tuning of language model post-training

   Python 62

2. RM-R1-UIUC/RM-R1 RM-R1-UIUC/RM-R1 Public

   [ICLR'26] RM-R1: Unleashing the Reasoning Potential of Reward Models

   Python 165 15

3. JUICE JUICE Public

   [ICML'25 Spotlight] Taming Knowledge Conflict in Language Models

   Jupyter Notebook 6

4. verl-project/verl verl-project/verl Public

   verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

   Python 21.8k 4k