Jiaqi Wang kokolerk

Pinned Loading

1. [NeurIPS 2025] Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models

   Python 55 4

2. MLNLP社区用来帮助大家避免论文投稿小错误的整理仓库。 Paper Writing Tips

   4.4k 526

4. Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (LLM).

   Python 579 59

5. [NeurIPS 2025]A Signed Graph Approach to Understanding and Mitigating Oversmoothing in GNNs

   Python 2

6. [TMLR2025] DivIL: Unveiling and Addressing Over-Invariance for Out-of- Distribution Generalization

   Python 4