Source: https://www.astrmira.com/en/research/papers/quiver/
Language: en

[Home](https://www.astrmira.com/en/)/[Research](https://www.astrmira.com/en/research/)/2605.02171

SEARCH SYSTEMS / ARXIV:2605.02171

# QuIVer: Rethinking ANN Graph Topology via Training-Free Binary Quantization

Builds, prunes, and navigates an ANN graph in a training-free two-bit space, reading full vectors only for final reranking and exposing the data regimes where compact topology works.

[Read on arXiv](https://arxiv.org/abs/2605.02171)[Open versioned PDF](https://arxiv.org/pdf/2605.02171v3)

Paper details

**Authors**: Wenxuan Xiao, Peidong Zhu, Zhiyou Wang, Chengcheng Li

**First submitted**: 2026-05-04

**Latest revision**: 2026-05-17

**Public version**: arXiv 2605.02171v3

Approximate nearest neighbors · Graph indexes · Binary quantization

Navigate with a compact binary graph, then rerank a small candidate set using the original vectors.

## Let quantization shape the graph

QuIVer asks whether binary quantization can be the metric space of the graph index itself. A training-free two-bit code combines sign and magnitude bits so Vamana edge selection, diversity pruning, and query navigation all operate in quantized space.

## Compact navigation, exact reranking

Queries are encoded as binary signatures and traverse candidates with bitwise operations. Full float32 vectors are read only at the end for reranking, separating frequently accessed signatures and adjacency lists from cold full-precision data.

No learned codebook or rotation matrix is required. Because quantization participates in construction and navigation, topology, computation, and memory layout can be designed around the compact representation together.

## Evaluate systems together with data geometry

Experiments on twelve million-scale datasets show strong distribution dependence: contrastive embeddings in cosine space fit the topology best, some multimodal representations follow, and native Euclidean or unstructured data perform poorly.

The work makes the tradeoff between compression, throughput, and data compatibility explicit, and provides a systems foundation for later work on quantization theory.

Read and cite

## Continue with the original paper.

The complete derivations, experimental setup, and results are available in the public manuscript.

[Abstract and version history ↗](https://arxiv.org/abs/2605.02171)  
[Full paper PDF ↗](https://arxiv.org/pdf/2605.02171v3)

Related papers

REPRESENTATION GEOMETRY · 2026.05

### What survives at one or two bits?

Research at a glance

Covariance Structure and Coordinate Heterogeneity Govern Binary Quantization of Contrastive Embeddings

Explains low-bit ranking behavior through covariance structure and coordinate heterogeneity, including why an extra magnitude bit and random rotation help different representations in different ways.

Representation geometry · Binary quantization

[Explore this research](https://www.astrmira.com/en/research/papers/covariance-binary-quantization/)

[arXiv](https://arxiv.org/abs/2605.17524)

VECTOR SEARCH · 2026.09

### When do compressed vectors make the same decisions?

Research at a glance

When Does Low-Bit Quantization Preserve the Decisions of Vector Search?

Places quantization error inside the ranking and graph-pruning decisions that vector search actually makes, relating reliability to comparison margins, correlated residuals, and execution traces.

Vector search · Decision stability

[Explore this research](https://www.astrmira.com/en/research/papers/low-bit-decisions/)

[arXiv](https://arxiv.org/abs/2609.09854)