Related papers: Visual Late Chunking: An Empirical Study of Contex…

Chunking is a crucial preprocessing step in retrieval-augmented generation (RAG) systems, significantly impacting retrieval effectiveness across diverse datasets. In this study, we systematically evaluate fixed-size chunking strategies and…

This paper presents VLCache, a cache reuse framework that exploits both Key-Value (KV) cache and encoder cache from prior multimodal inputs to eliminate costly recomputation when the same multimodal inputs recur. Unlike previous heuristic…

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…

Documents are visually rich structures that convey information through text, but also figures, page layouts, tables, or even fonts. Since modern retrieval systems mainly rely on the textual information they extract from document pages to…

Computer science texts are particularly rich in both narrative content and illustrative charts, algorithms, images, annotated diagrams, etc. This study explores the extent to which vector-based multimodal retrieval, powered by…

RAG-based QA has emerged as a powerful method for processing long industrial documents. However, conventional text chunking approaches often neglect complex and long industrial document structures, causing information loss and reduced…

Large language models (LLMs) with extended context windows have become increasingly prevalent for tackling complex tasks. However, the substantial Key-Value (KV) cache required for long-context LLMs poses significant deployment challenges.…

With the development of pre-trained language models, the dense retrieval models have become promising alternatives to the traditional retrieval models that rely on exact match and sparse bag-of-words representations. Different from most…

Document chunking is a critical task in natural language processing (NLP) that involves dividing a document into meaningful segments. Traditional methods often rely solely on semantic analysis, ignoring the spatial layout of elements, which…

Multimodal documents contain diverse elements, such as tables, figures, and layouts, which can complicate retrieval tasks. While current approaches typically combine dense visual embedding models with supervised rerankers to achieve…

Composed video retrieval (CoVR) is a challenging problem in computer vision which has recently highlighted the integration of modification text with visual queries for more sophisticated video search in large databases. Existing works…

We present a feature vector formation technique for documents - Sparse Composite Document Vector (SCDV) - which overcomes several shortcomings of the current distributional paragraph vector representations that are widely used for text…

The effectiveness of Retrieval-Augmented Generation (RAG) is highly dependent on how documents are chunked, that is, segmented into smaller units for indexing and retrieval. Yet, commonly used "one-size-fits-all" approaches often fail to…

Retrieval-Augmented Generation (RAG) systems lose retrieval accuracy when similar documents coexist in the vector database, causing unnecessary information, hallucinations, and factual errors. To alleviate this issue, we propose CHOP, a…

High-resolution (HR) image perception presents a key bottleneck for multimodal large language models (MLLMs). While visual search offers a promising solution, existing methods struggle with the trade-off between coverage and efficiency.…

Over the last few years, multi-vector retrieval methods, spearheaded by ColBERT, have become an increasingly popular approach to Neural IR. By storing representations at the token level rather than at the document level, these methods have…

Visual-semantic embedding enables various tasks such as image-text retrieval, image captioning, and visual question answering. The key to successful visual-semantic embedding is to express visual and textual data properly by accounting for…

Traditional information extraction systems face challenges with text only language models as it does not consider infographics (visual elements of information) such as tables, charts, images etc. often used to convey complex information to…

In the field of instruction-following large vision-language models (LVLMs), the efficient deployment of these models faces challenges, notably due to the high memory demands of their key-value (KV) caches. Conventional cache management…

Recent "Thinking with Video" approaches use Video Generation Models (VGMs) for visual reasoning by producing temporally coherent Chain-of-Frames as reasoning artifacts. Even strong VGMs, however, exhibit two recurring failure modes on…