Database
Towards High-Performance Multimodal Discovery: Evaluating Retrieval Efficacy and Operational Scalability in Digital Libraries
arXiv cs.IR0 views
arXiv:2611.17726v1 Announce Type: new Abstract: Large-scale digital repositories with million plus digitized volumes serve as vital engines for scientific and scholarly discovery. However, as collections grow, finding specific research or educational material remains a significant challenge. This difficulty is compounded by the multimodal nature of texts, that is, texts which combine dense narrative content with essential illustrative charts, annotated diagrams, and complex layouts. Historically, discovery has been supported by full-text search indexes implemented as inverted indexes (e.g., Lucene or Solr). While these systems scale well for textual strings, they are fundamentally "blind" to the semantic nuance of visual information. We explore the benefit of discovery through texts that have been converted to numerical vectors. By representing page images as numerical vectors rather than OCR-extracted text, and doing so for both text and images on a page, we capture both textual and visual semantics while mitigating reverse engineering and copyright infringement concerns. The primary contribution of this research is an evaluation of the multimodal retrieval landscape, encompassing both semantic precision and architectural scalability. Our findings demonstrate that integrating visual and textual features significantly enhances the discovery of relevant material, particularly in domains where diagrammatic content is essential for conceptual understanding. We assess retrieval efficacy, demonstrating that the system achieves sub-linear scalability. Our findings suggest that an optimized vector database configuration is the critical factor in transforming VLM-based embeddings into a production-ready, library-scale discovery solution.
Source:https://arxiv.org/abs/2611.17726PreviousAgent Security Meets Regulatory Reality -- A Practitioner Systematization of Autonomous-Agent Threats and Controls in Regulated Financial SystemsNextWho Counts as Exposed? Measurement Choices in an Open, Re-estimable Index of Occupational AI Exposure
Related posts

SQL Challenge : ROW_NUMBER() vs RANK() vs DENSE_RANK() – What's the Difference?
0dev.to Database
Why we don't offer a free database, and what we built instead
0dev.to Database
Listing Even Cycles Faster than the Submodular-Width Barrier
0arXiv cs.DB
LuthorSQL: A One-Pass Text-to-SQL Model as System 1 for a Slower LLM Agent
0arXiv cs.DB
MEM-SQL: Memory-Empowered Text-to-SQL
0arXiv cs.DB
Query Processing with eBPF-Offload on Computational Storage
0arXiv cs.DB