20 results for “distributed vector databases”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
TrustANN provides query-level trust for distributed approximate nearest-neighbor retrieval without modifying the underlying algorithm.
This paper proposes Yi, a system for efficient and effective in-place updates in large-scale vector indexing, achieving higher update and search throughput than state-of-the-art methods.
ACRONYM is a novel algorithm-hardware co-designed platform that enables high-recall, continuous approximate nearest neighbor search in memory for dynamic vector databases, achieving massive throughput…
This paper proposes a synopsis-guided approach to optimize vector search in databases by predicting the fidelity of different configurations and selecting the most cost-effective one for each query.
Lixuan Guo, Yifei Wang, Tiansheng Wen, Aosong Feng +2 more
The paper introduces Single-stage Sparse Retrieval (SSR), a method that replaces computationally expensive vector clustering with sparse autoencoding to achieve highly efficient multi-vector retrieval…
This paper proves that single-vector embeddings require a larger representation size than multi-vector embeddings to approximate certain similarities.
Yu Liu, Kun Peng, Wenxiao Zhang, Fangfang Yuan +3 more
Trans-RAG introduces a novel query-centric vector transformation technique to enable secure, efficient, and accurate cross-organizational retrieval in RAG systems without plaintext decryption.
Hanxi Li, Jianan Zhou, Jiale Lao, Yibo Wang +4 more
The paper introduces the Black-Hole Attack, a poisoning vulnerability that exploits geometric defects in high-dimensional embedding spaces to force malicious vectors into the top-k results of vector d…
The paper presents a randomized algorithm that solves the exact Euclidean shortest vector problem in polynomial space and improved time complexity.
Computes class probabilities in block-independent disjoint probabilistic databases.
RankLens is a single-rank emulation system that enables analysis, debugging, and tuning of distributed training with reduced resource requirements.
This paper proposes a query-aware routing framework for filtered ANN search to achieve state-of-the-art recall and QPS balance.
This paper provides a nearly sharp characterization of the matvec query complexity of sparse matrix approximation.
This paper embeds an IVF index in Parquet files' footers for approximate nearest-neighbor search in a lakehouse table, using existing file pruning for filtering and improving search performance.
Establishes conditions for embedding documents as vectors for top-k retrieval and analyzes the required dimension and precision.