相关论文: Beyond the Grid: Layout-Informed Multi-Vector Retr…

In this paper, we rethink sparse lexical representations for image retrieval. By utilizing multi-modal large language models (M-LLMs) that support visual prompting, we can extract image features and convert them into textual data, enabling…

Document retrieval in real-world scenarios faces significant challenges due to diverse document formats and modalities. Traditional text-based approaches rely on tailored parsing techniques that disregard layout information and are prone to…

The ability of having a sparse representation for a certain class of signals has many applications in data analysis, image processing, and other research fields. Among sparse representations, the cosparse analysis model has recently gained…

Multi-vector retrieval methods such as ColBERT and its recent variant, the ConteXtualized Token Retriever (XTR), offer high accuracy but face efficiency challenges at scale. To address this, we present WARP, a retrieval engine that…

This paper presents a novel method for parsing and vectorizing semi-structured data to enhance the functionality of Retrieval-Augmented Generation (RAG) within Large Language Models (LLMs). We developed a comprehensive pipeline for…

Vectors are universal mathematical objects that can represent text, images, speech, or a mix of these data modalities. That happens regardless of whether data is represented by hand-crafted features or learnt embeddings. Collect a large…

Multimodal embedding models have been crucial in enabling various downstream tasks such as semantic similarity, information retrieval, and clustering over different modalities. However, existing multimodal embeddings like VLM2Vec, E5-V, GME…

Relational understanding is critical for a number of visually-rich documents (VRDs) understanding tasks. Through multi-modal pre-training, recent studies provide comprehensive contextual representations and exploit them as prior knowledge…

Visual RAG has offered an alternative to traditional RAG. It treats documents as images and uses vision encoders to obtain vision patch tokens. However, hundreds of patch tokens per document create retrieval and storage challenges in a…

Embedding-based retrieval methods construct vector indices to search for document representations that are most similar to the query representations. They are widely used in document retrieval due to low latency and decent recall…

Despite advances in Large Language Models (LLMs) and Multimodal LLMs (MLLMs) for visual document understanding (VDU), visual information extraction (VIE) from relation-rich documents remains challenging due to the layout diversity and…

Automated parsing of scanned documents into richly structured, machine-readable formats remains a critical bottleneck in Document AI, as traditional multi-stage pipelines suffer from error propagation and limited adaptability to diverse…

The vast increase in amount and complexity of digital content led to a wide interest in ad-hoc retrieval systems in recent years. Complementary, the existence of heterogeneous data sources and retrieval models stimulated the proliferation…

Retrieval-Augmented Generation (RAG) has emerged as an effective paradigm for generating contextually accurate answers by integrating Large Language Models (LLMs) with retrieval mechanisms. However, in legal contexts, users frequently…

Current vision-language retrieval aims to perform cross-modal instance search, in which the core idea is to learn the consistent visionlanguage representations. Although the performance of cross-modal retrieval has greatly improved with the…

Many recent document embedding models are trained on document-as-image representations, embedding rendered pages as images rather than the underlying source. Meanwhile, existing benchmarks for scientific document retrieval, such as ArXivQA…

Traditional information retrieval is based on sparse bag-of-words vector representations of documents and queries. More recent deep-learning approaches have used dense embeddings learned using a transformer-based large language model. We…

Multimodal encoders have pushed the boundaries of visual document retrieval, matching textual query tokens directly to image patches and achieving state-of-the-art performance on public benchmarks. Recent models relying on this paradigm…

Retrieval-Augmented Generation (RAG) systems combine vector similarity search with large language models (LLMs) to deliver accurate, context-aware responses. However, co-locating the vector retriever and the LLM on shared GPU infrastructure…

Visual Place Recognition (VPR) is a crucial component of 6-DoF localization, visual SLAM and structure-from-motion pipelines, tasked to generate an initial list of place match hypotheses by matching global place descriptors. However,…