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.

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…

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 proves that single-vector embeddings require a larger representation size than multi-vector embeddings to approximate certain similarities.

This paper presents an index for the maximum segment sum problem with query offset and range, using O(log^2 n) query time and O(n log n) space.

This paper introduces SVD-RAG, a cost-efficient and content-adaptive summarization method for hierarchical Retrieval-Augmented Generation systems using Singular Value Decomposition on dense sentence e…

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 proposes a novel geometric embedding hashing method to recover object correspondences (vector links) between two embedding clouds generated by different black-box encoders using only a small…

The paper introduces PATH, an in-situ indexing architecture for Processing-in-Memory systems that achieves higher throughput, lower tail latency, and fewer memory accesses than state-of-the-art scheme…

The paper introduces Latent Terms, a method that shows dense retrieval models implicitly learn sparse, Zipfian vocabularies that can be used for classical BM25-style sparse scoring without requiring s…

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.

This paper proposes a lightweight encoder-based MEL solution called FAST-MEL that meets three objectives: high linking accuracy, computational efficiency, and storage efficiency.