Year: 2026
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Institution: Apple (United States)
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7138224465
Cites:
Cited by:
Related to: