在企业搜索中实现多模态精准检索，无需重构系统架构。
AMES: Approximate Multi-modal Enterprise Search via Late Interaction Retrieval
- 采用晚期交互机制，统一处理文本、图像、视频的跨模态检索。
- 在ViDoRe V3上达到与先进模型相当的排名效果，延迟可接受。
- 兼容现有系统，适合需要快速集成多模态搜索的企业用户。
我们提出AMES（近似多模态企业搜索），一种无需后端依赖的统一多模态晚期交互检索架构。实验表明，细粒度的多模态晚期交互检索可在不重新设计架构的前提下，部署于生产级企业搜索引擎中。文本标记、图像块和视频帧通过多向量编码器映射到共享表示空间，实现跨模态检索而无需特定模态的检索逻辑。AMES采用两阶段流程：第一阶段并行进行标记级近似最近邻搜索，结合每文档的Top-M MaxSim近似；第二阶段由加速器优化的Exact MaxSim重排序。在ViDoRe V3基准测试中，AMES在基于Solr的可扩展、生产就绪系统中实现了具有竞争力的排序性能。
原文摘要 · Abstract (English)
We present AMES (Approximate Multimodal Enterprise Search), a unified multimodal late interaction retrieval architecture which is backend agnostic. AMES demonstrates that fine-grained multimodal late interaction retrieval can be deployed within a production grade enterprise search engine without architectural redesign. Text tokens, image patches, and video frames are embedded into a shared representation space using multi-vector encoders, enabling cross-modal retrieval without modality specific retrieval logic. AMES employs a two-stage pipeline: parallel token level ANN search with per document Top-M MaxSim approximation, followed by accelerator optimized Exact MaxSim re-ranking. Experiments on the ViDoRe V3 benchmark show that AMES achieves competitive ranking performance within a scalable, production ready Solr based system.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。