PulseAugur
实时 09:27:13
English(EN) OracleAnalyser: Analysing Implicit Semantics of Oracle Bone Scripts through MLLMs with Post-training

新AI框架使用Qwen2.5-VL分析古代甲骨文

研究人员开发了OracleAnalyser,一个旨在利用多模态大语言模型(MLLMs)分析甲骨文隐含义的新框架。该框架通过先进的后训练技术对Qwen2.5-VL-3B-Instruct模型进行微调,包括一种名为Stable Focal Preference Optimization(SFPO)的新颖偏好优化算法。该项目还引入了用于甲骨文推理和偏好的新数据集,以及用于评估分析能力的基准。实验表明,OracleAnalyser取得了卓越的分析性能,尽管参数量较小,但其表现优于更大的模型。 AI

影响 这项研究推动了MLLMs在历史文本分析中的应用,有望为深入了解古代文化和语言提供新的途径。

排序理由 该集群描述了一篇介绍使用LLMs分析古代文字的新颖框架和算法的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新AI框架使用Qwen2.5-VL分析古代甲骨文

报道来源 [2]

  1. arXiv cs.CV TIER_1 English(EN) · Zijia Song, Yelin Wang, Zhengyi Ma, Zitong Yu, Tianheng Wang, Jiahuan Zhang, Taorui Wang, Kaicheng Yu ·

    OracleAnalyser: Analysing Implicit Semantics of Oracle Bone Scripts through MLLMs with Post-training

    arXiv:2606.25906v1 Announce Type: new Abstract: With the advancement of artificial intelligence, research on oracle bone scripts has entered a new era. However, existing methods and benchmarks remain largely confined to recognition tasks, overlooking the equally crucial aspect of…

  2. arXiv cs.CV TIER_1 English(EN) · Kaicheng Yu ·

    OracleAnalyser: Analysing Implicit Semantics of Oracle Bone Scripts through MLLMs with Post-training

    With the advancement of artificial intelligence, research on oracle bone scripts has entered a new era. However, existing methods and benchmarks remain largely confined to recognition tasks, overlooking the equally crucial aspect of oracle bone analysis. To address this gap, we p…