Pinned Loading

1. Guided-GRPO Guided-GRPO Public

   A Guided Reinforcement Learning framework enhancing MLLM reasoning via process-level verification and collaborative rollout strategies.

   Python 47

2. GMT GMT Public

   GMT: Graph-as-Memory Tuning for deep KG–LLM fusion via cross-attention.

   Python 11 1

3. OpenDCAI/DataFlow-MM OpenDCAI/DataFlow-MM Public

   Dataflow-MM, multi-media operators for Dataflow. We aim to prepare data for Multimodal Large Language Models.

   Python 39 19

4. tongruiliu.github.io tongruiliu.github.io Public

   my page

   HTML 1

5. OpenDCAI/DataFlex OpenDCAI/DataFlex Public

   DataFlex is a data-centric training framework that enhances model performance by either selecting the most influential samples, optimizing their weights, or adjusting their mixing ratios.

   Python 642 70

6. canvas-rl canvas-rl Public

   Python 3