A Research Group for AI+ Frameworks

Popular repositories Loading

1. SPO SPOPublic

   Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models

   Python 56 7

2. CorgiPile CorgiPilePublic

   A New DataSet API with Efficient Shuffle Mechanism for PyTorch (SGD/Adam without Full Data Shuffle)

   Python 1 1

3. DEEP-GRPO DEEP-GRPOPublic

   Deep Dense Exploration for LLM Reinforcement Learning via Pivot-Driven Resampling