Pinned Loading

1. Gap-in-Preference-Learning Gap-in-Preference-Learning Public

   Official code for "Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO".

   Python 3

2. Samplers-in-Online-DPO Samplers-in-Online-DPO Public

   Official code for "The Crucial Role of Samplers in Online Direct Preference Optimization".

   Python 7

3. MOD MOD Public

   Official code for "Decoding-Time Language Model Alignment with Multiple Objectives".

   Python 25 3

4. LaMo-2023 LaMo-2023 Public

   Official code for "Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning".

   Python 53 9