Popular repositories Loading

1. Just-Enough-Think Just-Enough-Think Public

   [ICLR26] An open-source project dedicated to training LRMs to achieve "just-enough" thinking

   Python 17

2. GA-Technical-Report GA-Technical-Report Public

   Technical Report & Evaluation Datasets for GenericAgent (GA)

   Python 11 8

3. FineCE FineCE Public

   Python 7 1

4. simple_GRPO simple_GRPO Public

   Forked from lsdefine/simple_GRPO

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

   Python 5

5. Proactive-Self-Refine-in-LLMs Proactive-Self-Refine-in-LLMs Public

   [ICLR26] An open-source project dedicated to training language models to proactively refine their outputs during generation via reinforcement learning.

   Python 5

6. jinyihan99.github.io jinyihan99.github.io Public

   HTML