AI RESEARCH
Hybrid-Vector Retrieval for Visually Rich Documents: Combining Single-Vector Efficiency and Multi-Vector Accuracy
arXiv CS.CV
•
ArXi:2510.22215v2 Announce Type: replace-cross Retrieval over visually rich documents is essential for tasks such as legal discovery, scientific search, and enterprise knowledge management. Existing approaches fall into two paradigms: single-vector retrieval, which is efficient but coarse, and multi-vector retrieval, which is accurate but computationally expensive. To address this trade-off, we propose HEAVEN, a plug-and-play two-stage hybrid-vector framework.