Topic
vector search
Policy-aware Vector Search: A Vision for Fine Grained Access Control in Vector Databases
A new paper from arXiv presents a vision for policy-aware vector search, formalizing the problem of fine-grained access control (FGAC) in vector databases. The authors compare enforcement strategies, present preliminary findings, and identify open challenges for achieving secure, high-performance vector search in security-sensitive applications like RAG and AI pipelines.
New Unifying Lens for Learning to Hash Could Cut Memory Costs in Large-Scale Retrieval
A new arXiv paper from researcher Sean Moran proposes a unifying lens for approximate nearest-neighbour search, framing all methods as variations of projection, quantisation, and organisation. The work introduces the open BitBudget benchmark and finds that quantisation delivers the largest memory savings, with one-bit codes matching uncompressed quality for most embedders at 1/32 the size. The study also shows supervised eight-byte codes can more than double retrieval quality over two-kilobyte floats.