arXiv:2510. 04127v2 Announce Type: replace-cross Abstract: Approximate nearest neighbour (ANN) search underpins large-scale retrieval, increasingly within the retrieval-augmented generation pipelines that ground large language models, yet the methods that address it have multiplied across communities until they are seldom read as a single field.
Matryoshka Hash Representations (MHR) propose a two‑stage quantization approach for retrieval‑augmented generation. First, a long binary code is learned; then, frozen, additional zero‑initialized residual adaptors are trained to produce searchable prefixes of varying byte budgets. Evaluated on MS MARCO and transferred to seven BEIR datasets, MHR achieves higher NDCG@10 and Recall@100 at 32‑byte budgets than baselines, especially in low‑budget regimes, and can also improve candidate shortlisting and graph‑index pruning.
Quanta is an open‑source Python library that unifies dense vector search over 4‑bit quantised embeddings, BM25 full‑text retrieval, and knowledge‑graph traversal behind a single retrieval API. It combines signals using weighted reciprocal rank fusion instead of normalising heterogeneous scores, arguing that such normalisations are query‑dependent. The library treats the graph as a candidate expander rather than a relevance scorer, widening the candidate pool and then re‑scoring documents with dense indexes under an identifier allowlist.
arXiv:2606. 11780v1 Announce Type: cross Abstract: We establish conditions for embedding a corpus of $N$ documents as $d$-dimensional vectors such that every $k$-subset $S \subseteq [N]$ is realizable as a result of top-$k$ retrieval by some query vector.
MRVQ (Matryoshka Residual Vector Quantization) is a single post‑hoc residual quantizer designed for frozen embeddings that can be truncated to support any combination of embedding dimension and code rate. By dropping residual stages or embedding coordinates, MRVQ provides a single resident artifact that serves all evaluated (dimension, rate) pairs, achieving the lowest memory usage among tested designs. Although it uses 17.8–22.0× less memory than three separately trained QINCo2 indices and 1.89–2.02× less than a lean shared‑model steelman, it trades off a small drop in nDCG@10 on FiQA compared to per‑rate QINCo2, yet still outperforms PQ, OPQ, and AdANNS‑OPQ at matched code size.
arXiv:2609.36376v1 Announce Type: cross Abstract: Dense retrieval, the key component of Retrieval Augmented Generation (RAG), retrieves the most relevant documents by comparing dense vector represent...
The paper investigates the geometric capacity of vector retrieval systems, focusing on the maximum recall achievable with a fixed document index. It demonstrates that, on real-world benchmarks, single-vector query encoders often underperform relative to the index’s potential. The authors provide theoretical evidence that learning such encoders can be computationally hard, constructing a task where a simple neural network can achieve perfect recall while any statistical-query learner would need exponentially many queries to surpass random chance.
arXiv:2608. 14648v1 Announce Type: cross Abstract: In this study, we revisit three widely used techniques in vector search and utilize them to optimize vector embedding indexing through clustering: dimensionality reduction, quantization, and dimension pruning.
The paper investigates how dimensionality reduction and quantization together affect text embedding compression across four task families in the Massive Text Embedding Benchmark using five pretrained models. It finds that combining these techniques can preserve near-original performance while drastically reducing storage, with some classification models retaining at least 99% of their score using less than 0.1% of the original storage. The optimal trade‑off between dimensionality and bit‑width varies by task, with retrieval tasks being more sensitive to compression.
arXiv:2608. 11240v1 Announce Type: new Abstract: Vector quantization is an old problem but has recently become central to AI infrastructure.
arXiv:2608.30384v1 Announce Type: new Abstract: By introducing RSLM (Rotated Scaled Lloyd-Max), a family of training-free vector quantization codecs compressing embeddings to 1--4 bits per dimension,...
arXiv:2608. 04074v1 Announce Type: cross Abstract: Long-context LLM decoding reads the key-value (KV) cache at every step.