MV-IVF: an inverted-file index built natively over multi-vector embeddings
_reachsumit · x · 2026-11-10
MV-IVF builds an IVF-style index directly over multi-vector embeddings instead of relying on single-vector proxies or filter-and-rerank. Key insight: once point clouds are assigned to clusters, the center-update step reduces to standard single-vector clustering, enabling MV-Lloyd, a Lloyd-style algorithm clustering point clouds under a Chamfer objective to build a hierarchical IVF tree.
Queries use best-first beam search over the tree, accelerated by low-bit quantization, query compression, and cache-efficient batched search. Implemented in the optimized C++ library MVSIC, showing strong latency-recall tradeoffs on BEIR and LoTTE.
More from Research
- Claude Fable 5.2 tops VIALS-AA science visual reasoning benchmark at 67% with heavy tool use — ArtificialAnlys · 2026-11-10
- WVU researcher presents 10 years of tractometry work on Alzheimer's white matter vulnerability — PTenigma · 2026-11-10
- New cryo-EM structure: pSTAT1 bound to importin alpha 5 (PDB 11GJ) — chaitjo · 2026-11-10
- ARLoop: fully-open 1.2B looped transformer beats Huginn-3.5B and Qwen3.5-2B on all 8 benchmarks — hhsun1 · 2026-11-10
- RAGCap-Bench: A Fine-Grained Benchmark for Intermediate Capabilities in Agentic RAG — kalyan_kpl · 2026-11-10
- Networks Aren't Scale Invariant, Yet Countless Methods Assume It — Why? — Jianlin_S · 2026-11-10