PulseAugur
实时 11:53:00
English(EN) Multimodal Knowledge Edit-Scoped Generalization for Online Recursive MLLM Editing

ScopeEdit通过控制知识传播来增强多模态LLM编辑

研究人员推出了一种新颖的多模态在线知识编辑方法ScopeEdit,用于大型语言模型(MLLM)。该方法旨在控制每次编辑的语义范围,确保更正能够迁移到相关的跨模态变体,而不会对不相关的输入产生负面影响。ScopeEdit将更新分解为模态局部和共享泛化分支,利用正交低秩空间和Sherman-Morrison递归来实现高效、有界开销。实验表明,ScopeEdit在各种基准测试和MLLM架构中,在范围内的迁移和范围外的局部性之间的平衡方面是有效的。 AI

影响 提高了多模态LLM中知识更新的精度和控制力,有望带来更强大、更可靠的AI系统。

排序理由 该条目是一篇研究论文,详细介绍了一种新的多模态LLM编辑方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

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

ScopeEdit通过控制知识传播来增强多模态LLM编辑

报道来源 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Siyuan Li, Youyuan Zhang, Ruitong Liu, Junxi Wang, Jing Li ·

    Multimodal Knowledge Edit-Scoped Generalization for Online Recursive MLLM Editing

    arXiv:2607.01978v1 Announce Type: new Abstract: Online multimodal knowledge editing requires injecting a continual stream of visual-textual corrections into multimodal large language models (MLLMs) with bounded overhead and minimal disruption to unrelated behaviors. Existing edit…

  2. arXiv cs.CL TIER_1 English(EN) · Jing Li ·

    Multimodal Knowledge Edit-Scoped Generalization for Online Recursive MLLM Editing

    Online multimodal knowledge editing requires injecting a continual stream of visual-textual corrections into multimodal large language models (MLLMs) with bounded overhead and minimal disruption to unrelated behaviors. Existing editors mainly emphasize edit reliability and long-h…