研究人员开发了新的多模态文档检索框架，以提高对视觉丰富的文档进行问答的准确性。MIDR将多模态推理转移到索引时间，在准确性和效率方面比ColQwen2.5等现有方法取得了显著的进步。Doc-REFRAG通过压缩视觉标记并选择性地扩展相关标记，解决了现实世界多图像场景中的挑战，在多个基准测试中表现优于基线，且延迟更低。 AI
影响 多模态文档检索的这些进步可以显著提高处理复杂、视觉丰富的信息的AI系统的准确性和效率。
排序理由 该集群包含两篇详细介绍多模态文档检索新方法的论文。
在 arXiv cs.IR (Information Retrieval) 阅读 →
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2609.01316v1 Announce Type: cross Abstract: Retrieval over visually rich documents has a representation problem: important content often lives in tables, charts, figures, and layout relations that plain OCR linearizes, corrupts, or omits. ColPali-family visual retrievers ad…
Retrieval over visually rich documents has a representation problem: important content often lives in tables, charts, figures, and layout relations that plain OCR linearizes, corrupts, or omits. ColPali-family visual retrievers address this with patch-level multi-vector indexes a…
Real-world knowledge resides in multimodal documents, necessitating retrieval-augmented generation (RAG) for accurate question answering. However, existing multimodal RAG models are primarily designed for single-image or closed-document settings and exhibit limited accuracy in re…
arXiv:2608.30163v1 Announce Type: cross Abstract: Real-world knowledge resides in multimodal documents, necessitating retrieval-augmented generation (RAG) for accurate question answering. However, existing multimodal RAG models are primarily designed for single-image or closed-do…