Pinned Loading

1. adaptive_decoding adaptive_decoding Public

   [ICML2024]Adaptive decoding balances the diversity and coherence of open-ended text generation.

   Python 19 1

2. weak-to-strong-preference-optimization weak-to-strong-preference-optimization Public

   [ICLR 2025 Spotlight] Weak-to-strong preference optimization: stealing reward from weak aligned model

   Python 16

3. ReAligner ReAligner Public

   [NeurIPS 2025] A Framework for Flexible Realignment of Language Models during Training and Inference

   Python 5

4. PSFT PSFT Public

   PSFT is a trust-region–inspired fine-tuning objective that views SFT as a policy gradient method with constant advantages, constraining policy drift to stabilize training and improve generalization.

   Python 34 1