InfiR : Crafting Effective Small Language Models and Multimodal Small Language Models in Reasoning

Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) have made significant advancements in reasoning capabilities. However, they still face challenges such as high computational demands and privacy concerns. This paper focuses on developing efficient Small Language Models (SLMs) and Multimodal Small Language Models (MSLMs) that retain competitive reasoning abilities. We introduce a novel training pipeline that enhances reasoning capabilities and facilitates deployment on edge devices, achieving state-of-the-art performance while minimizing development costs. \InfR~ aims to advance AI systems by improving reasoning, reducing adoption barriers, and addressing privacy concerns through smaller model sizes. Resources are available at https://github. com/Reallm-Labs/InfiR.

@article{xie2025_2502.11573,
  title={ InfiR : Crafting Effective Small Language Models and Multimodal Small Language Models in Reasoning },
  author={ Congkai Xie and Shuo Cai and Wenjun Wang and Pengxiang Li and Zhijie Sang and Kejing Yang and Yiming Zhang and Zhen Li and Guanghao Zhu and Zeyu Liu and Yang Yu and Yuhang Liu and Su Lu and Baoyi He and Qi Zhou and Xiaotian Han and Jianbo Yuan and Shengyu Zhang and Fei Wu and Hongxia Yang },
  journal={arXiv preprint arXiv:2502.11573},
  year={ 2025 }
}