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

Research / Publications

# Questions.  
Evidence. Progress.

Our research begins with questions worth asking, then builds methods and evidence across different fields. This page brings together papers, current directions, and the next questions opened by each result.

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)

LOW-BIT LLMS · 2026.09

## Why does the value of the same quantization move change?

Research at a glance

Contextual Utility of Quantization Moves in Extreme Low-Bit LLMs

Studies the real utility of a discrete move in extreme low-bit LLMs by evaluating the move along its own path and combining decisions in an evolving model state.

LLM quantization · Post-training

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

[arXiv](https://arxiv.org/abs/2609.09867)

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)

SEARCH SYSTEMS · 2026.05

## QuIVer: building the search graph directly in binary space

Research at a glance

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.

Approximate nearest neighbors · Graph indexes

[Explore this research](https://www.astrmira.com/en/research/papers/quiver/)

[arXiv](https://arxiv.org/abs/2605.02171)

4 papers

Have a question worth pursuing together?

[Talk with us](https://www.astrmira.com/en/collaborate/)