Related papers: TextlessRAG: End-to-End Visual Document RAG by Spe…

Learning from Text-Attributed Graphs (TAGs) has attracted significant attention due to its wide range of real-world applications. The rapid evolution of language models (LMs) has revolutionized the way we process textual data, which…

Recent advances in deep learning for sequential data have given rise to fast and powerful models that produce realistic videos of talking humans. The state of the art in talking face generation focuses mainly on lip-syncing, being…

A crucial component for the scene text based reasoning required for TextVQA and TextCaps datasets involve detecting and recognizing text present in the images using an optical character recognition (OCR) system. The current systems are…

Visual Document Retrieval (VDR) typically operates as text-to-image retrieval using specialized bi-encoders trained to directly embed document images. We revisit a zero-shot generate-and-encode pipeline: a vision-language model first…

With the rapid development of large-scale language models, Retrieval-Augmented Generation (RAG) has been widely adopted. However, existing RAG paradigms are inevitably influenced by erroneous retrieval information, thereby reducing the…

Most organizational data in this world are stored as documents, and visual retrieval plays a crucial role in unlocking the collective intelligence from all these documents. However, existing benchmarks focus on English-only document…

Recent advancements in Large language models (LLMs) have demonstrated remarkable capabilities across diverse domains. While they exhibit strong zero-shot performance on various tasks, LLMs' effectiveness in music-related applications…

Tabular data is frequently captured in image form across a wide range of real-world scenarios such as financial reports, handwritten records, and document scans. These visual representations pose unique challenges for machine understanding,…

Open-domain long-form text generation requires generating coherent, comprehensive responses that address complex queries with both breadth and depth. This task is challenging due to the need to accurately capture diverse facets of input…

PDF files are primarily intended for human reading rather than automated processing. In addition, the heterogeneous content of PDFs, such as text, tables, and images, poses significant challenges for parsing and information extraction. To…

Large Language Models (LLMs) are adept at generating responses based on information within their context. While this ability is useful for interacting with structured data like code files, another popular method, Retrieval-Augmented…

Large Language Models (LLMs) are capable of natural language understanding and generation. But they face challenges such as hallucination and outdated knowledge. Fine-tuning is one possible solution, but it is resource-intensive and must be…

In this paper, we introduce Technical-Embeddings, a novel framework designed to optimize semantic retrieval in technical documentation, with applications in both hardware and software development. Our approach addresses the challenges of…

Retrieval-Augmented Generation (RAG) has become the standard approach for grounding large language models in information that was not available during training. While existing datasets and benchmarks focus on web or other public sources,…

Document visual question answering (DocVQA) pipelines that answer questions from documents have broad applications. Existing methods focus on handling single-page documents with multi-modal language models (MLMs), or rely on text-based…

Textual graph-based retrieval-augmented generation (GraphRAG) has emerged as a powerful paradigm for enhancing large language models (LLMs) in domain-specific question answering. While existing approaches primarily focus on zero-shot…

NoSQL databases have become increasingly popular due to their outstanding performance in handling large-scale, unstructured, and semi-structured data, highlighting the need for user-friendly interfaces to bridge the gap between…

Due to recent advancements in Large Audio-Language Models (LALMs) that demonstrate remarkable performance across a range of sound-, speech- and music-related tasks, there is a growing interest in proposing benchmarks to assess these models.…

We propose a new method to measure the task-specific accuracy of Retrieval-Augmented Large Language Models (RAG). Evaluation is performed by scoring the RAG on an automatically-generated synthetic exam composed of multiple choice questions…

Graph-based Retrieval-Augmented Generation (GraphRAG) advances flat document retrieval by structuring knowledge as relational graphs, enabling more coherent and effective reasoning. However, applying it to specific domains like legal…