Pinned Loading

1. GLM (General Language Model)

   Python 3.4k 345

2. slime is an LLM post-training framework for RL Scaling.

   Python 4.5k 598

3. An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks

   Python 2.1k 207

4. ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)

   Python 692 50

5. RL Scaling and Test-Time Scaling (ICML'25)

   114 1

6. Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework

   Python 230 16