Yuan3.0 Flash：面向企业应用的开源多模态大语言模型
Yuan3.0 Flash: An Open Multimodal Large Language Model for Enterprise Applications
AI总结：
Yuan3.0 Flash通过RAPO算法提升企业任务性能，实现高效多模态大语言模型开源
摘要：
我们介绍了Yuan3.0 Flash，一个开源的混合专家（MoE）多模态大语言模型，具有37亿个激活参数和4000亿个总参数，专门设计用于提升企业导向任务的性能，同时在通用任务上保持竞争能力。为解决大型推理模型（LRMs）中常见的过度思考现象，我们提出了反思感知自适应策略优化（RAPO），一种新的强化学习训练算法，能够有效调节过度思考行为。在检索增强生成（RAG）、复杂表格理解和摘要等企业导向任务中，Yuan3.0 Flash始终表现出色。此外，它在数学、科学等领域也展示了强大的推理能力，达到前沿模型的准确性水平，但仅需大约1/4到1/2的平均token数。Yuan3.0 Flash已完全开源，以促进进一步研究和实际部署：https://github.com/Yuan-lab-LLM/Yuan3.0。
英文摘要：
We introduce Yuan3.0 Flash, an open-source Mixture-of-Experts (MoE) MultiModal Large Language Model featuring 3.7B activated parameters and 40B total parameters, specifically designed to enhance performance on enterprise-oriented tasks while maintaining competitive capabilities on general-purpose tasks. To address the overthinking phenomenon commonly observed in Large Reasoning Models (LRMs), we propose Reflection-aware Adaptive Policy Optimization (RAPO), a novel RL training algorithm that effectively regulates overthinking behaviors. In enterprise-oriented tasks such as retrieval-augmented generation (RAG), complex table understanding, and summarization, Yuan3.0 Flash consistently achieves superior performance. Moreover, it also demonstrates strong reasoning capabilities in domains such as mathematics, science, etc., attaining accuracy comparable to frontier model while requiring only approximately 1/4 to 1/2 of the average tokens. Yuan3.0 Flash has been fully open-sourced to facilitate further research and real-world deployment: https://github.com/Yuan-lab-LLM/Yuan3.0.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
