Popular repositories Loading

1. SDPO SDPO Public

   Reinforcement Learning via Self-Distillation (SDPO)

   Python 1k 116

2. SafetyPolytope SafetyPolytope Public

   Learning Safety Constraints for Large Language Models (ICML2025)

   Python 35 6

3. gosafeopt gosafeopt Public

   Globally Safe Model-free Exploration of Dynamical Systems

   Python 33 6

4. safe-learning safe-learning Public

   A collection of algorithms and experiment tools for safe sim to real transfer in robotics.

   Python 28 8

5. user_interactions user_interactions Public

   Aligning Language Models from User Interactions via Self-Distillation

   Python 26 5

6. opax opax Public

   Python 19 4