Related papers: ESPN: Memory-Efficient Multi-Vector Information Re…

The pipelines transmission system is one of the growing aspects, which has existed for a long time in the energy industry. The cost of in-pipe exploration for maintaining service always draws lots of attention in this industry. Normally…

This paper introduces Sparsified Late Interaction for Multi-vector (SLIM) retrieval with inverted indexes. Multi-vector retrieval methods have demonstrated their effectiveness on various retrieval datasets, and among them, ColBERT is the…

Information retrieval evaluation often suffers from fragmented practices -- varying dataset subsets, aggregation methods, and pipeline configurations -- that undermine reproducibility and comparability, especially for foundation embedding…

Learning a high-dimensional dense representation for vocabulary terms, also known as a word embedding, has recently attracted much attention in natural language processing and information retrieval tasks. The embedding vectors are typically…

Recurrent neural networks (RNNs) have achieved state-of-the-art performances in many natural language processing tasks, such as language modeling and machine translation. However, when the vocabulary is large, the RNN model will become very…

Dual-encoder-based dense retrieval models have become the standard in IR. They employ large Transformer-based language models, which are notoriously inefficient in terms of resources and latency. We propose Fast-Forward indexes -- vector…

Text embedding models serve as a fundamental component in real-world search applications. By mapping queries and documents into a shared embedding space, they deliver competitive retrieval performance with high efficiency. However, their…

Dense vector representations for sentences made significant progress in recent years as can be seen on sentence similarity tasks. Real-world phrase retrieval applications, on the other hand, still encounter challenges for effective use of…

Embedding techniques have become essential components of large databases in the deep learning era. By encoding discrete entities, such as words, items, or graph nodes, into continuous vector spaces, embeddings facilitate more efficient…

Multimodal large language models (MLLMs) have recently demonstrated strong capabilities in understanding and generating responses from diverse visual inputs, including high-resolution images and long video sequences. As these models scale…

Training and inference on edge devices often requires an efficient setup due to computational limitations. While pre-computing data representations and caching them on a server can mitigate extensive edge device computation, this leads to…

Modern deep learning models capture the semantics of complex data by transforming them into high-dimensional embedding vectors. Emerging applications, such as retrieval-augmented generation, use approximate nearest neighbor (ANN) search in…

Recently, Multi-modal Large Language Models (MLLMs) have shown remarkable effectiveness for multi-modal tasks due to their abilities to generate and understand cross-modal data. However, processing long sequences of visual tokens extracted…

Retrieving relevant items that match users' queries from billion-scale corpus forms the core of industrial e-commerce search systems, in which embedding-based retrieval (EBR) methods are prevailing. These methods adopt a two-tower framework…

Vector-based retrieval systems have become a common staple for academic and industrial search applications because they provide a simple and scalable way of extending the search to leverage contextual representations for documents and…

Neural ranking models for information retrieval (IR) use shallow or deep neural networks to rank search results in response to a query. Traditional learning to rank models employ machine learning techniques over hand-crafted IR features. By…

Implicit Neural Representations (INRs) aim to parameterize discrete signals through implicit continuous functions. However, formulating each image with a separate neural network~(typically, a Multi-Layer Perceptron (MLP)) leads to…

Recent advancements in Deep Neural Network (DNN) models have significantly improved performance across computer vision tasks. However, achieving highly generalizable and high-performing vision models requires expansive datasets, resulting…

The ability of machine learning models to store input information in hidden layer vector embeddings, analogous to the concept of `memory', is widely employed but not well characterized. We find that language model embeddings typically…

This paper describes a compact and effective model for low-latency passage retrieval in conversational search based on learned dense representations. Prior to our work, the state-of-the-art approach uses a multi-stage pipeline comprising…