Related papers: GEM: A Native Graph-based Index for Multi-Vector R…

Dense retrieval has achieved impressive advances in first-stage retrieval from a large-scale document collection, which is built on bi-encoder architecture to produce single vector representation of query and document. However, a document…

Universal multimodal embedding models have achieved great success in capturing semantic relevance between queries and candidates. However, current methods either condense queries and candidates into a single vector, potentially limiting the…

Modern retrieval-augmented generation (RAG) systems treat vector embeddings as static, context-free artifacts: an embedding has no notion of when it was created, how trustworthy its source is, or which other embeddings depend on it. This…

An exciting frontier in natural language understanding (NLU) and generation (NLG) calls for (vision-and-) language models that can efficiently access external structured knowledge repositories. However, many existing knowledge bases only…

We study efficient multi-vector retrieval for late interaction in any modality. Late interaction has emerged as a dominant paradigm for information retrieval in text, images, visual documents, and videos, but its computation and storage…

Acquiring labels are often costly, whereas unlabeled data are usually easy to obtain in modern machine learning applications. Semi-supervised learning provides a principled machine learning framework to address such situations, and has been…

Nowadays, data is represented by vectors. Retrieving those vectors, among millions and billions, that are similar to a given query is a ubiquitous problem, known as similarity search, of relevance for a wide range of applications.…

The rapid growth of machine learning capabilities and the adoption of data processing methods using vector embeddings sparked a great interest in creating systems for vector data management. While the predominant approach of vector data…

The objective of this work is to learn a compact embedding of a set of descriptors that is suitable for efficient retrieval and ranking, whilst maintaining discriminability of the individual descriptors. We focus on a specific example of…

Dense retrieval models use bi-encoder network architectures for learning query and document representations. These representations are often in the form of a vector representation and their similarities are often computed using the dot…

The prevalence of real-world multi-view data makes incomplete multi-view clustering (IMVC) a crucial research. The rapid development of Graph Neural Networks (GNNs) has established them as one of the mainstream approaches for multi-view…

Retrieval-Augmented Generation (RAG) applications increasingly rely on Filtered Approximate Nearest Neighbor Search (FANNS) to combine semantic retrieval with metadata constraints. While algorithmic innovations for FANNS have been proposed,…

Retrieval-Augmented Generation (RAG) systems have become a dominant approach to augment large language models (LLMs) with external knowledge. However, existing vector database (VecDB) retrieval pipelines rely on flat or single-resolution…

Recently, neural models for information retrieval are becoming increasingly popular. They provide effective approaches for product search due to their competitive advantages in semantic matching. However, it is challenging to use…

Standard Retrieval-Augmented Generation (RAG) chunking methods often create excessive redundancy, increasing storage costs and slowing retrieval. This study explores chunk filtering strategies, such as semantic, topic-based, and…

Nearest neighbour search over dense vector collections has important applications in information retrieval, retrieval augmented generation (RAG), and content ranking. Performing efficient search over large vector collections is a well…

Graph-based retrieval-augmented generation (RAG) enriches large language models (LLMs) with external knowledge for long-context understanding and multi-hop reasoning, but existing methods face a granularity dilemma: fine-grained…

ANNS for embedded vector representations of texts is commonly used in information retrieval, with two important information representations being sparse and dense vectors. While it has been shown that combining these representations…

Finding vertex-to-vertex correspondences in real-world graphs is a challenging task with applications in a wide variety of domains. Structural matching based on graphs connectivities has attracted considerable attention, while the…

Recent advancements in Retrieval-Augmented Generation (RAG) have enabled Large Language Models (LLMs) to access multimodal knowledge bases containing both text and visual information such as charts, diagrams, and tables in financial…