Pinned Loading

1. MENTOR MENTOR Public

   (ICLR2026) Selective Expert Guidance For Effective and Diverse Exploration in Reinforcement Learning of LLMs

   Python 8

2. DUCL DUCL Public

   (AAAI26 Oral) Difficulty Is Not Enough: Curriculum Learning for LLMs Fine-tuning Must Consider Utility

   Python

3. lsdefine/simple_GRPO lsdefine/simple_GRPO Public

   A very simple GRPO implement for reproducing r1-like LLM thinking.

   Python 1.7k 132