Pinned Loading

1. MM-UPT MM-UPT Public

   [NeurIPS 2025] Unsupervised Post-Training for Multi-Modal LLM Reasoning via GRPO

   Python 51 2

2. Diff-eRank Diff-eRank Public

   [NeurIPS 2024] A Novel Rank-Based Metric for Evaluating Large Language Models

   Python 53 2

3. Diabetica Diabetica Public

   [SCI-FM@ICLR 2025] Specialized LLMs capable of handling various diabetes tasks

   Python 49 6

4. InstructionGPT-4 InstructionGPT-4 Public

   InstructionGPT-4

   Python 41 3

5. RL-with-Cold-Start RL-with-Cold-Start Public

   SFT+RL boosts multimodal reasoning

   Python 35