We call on the Document AI (DocAI) community to re-evaluate current methodologies and
embrace the challenge of creating more practically-oriented benchmarks. Document …

This work presents DocPedia, a novel large multimodal model (LMM) for versatile OCR-free
document understanding, capable of parsing images up to 2,560$\times $2,560 resolution …

Screen user interfaces (UIs) and infographics, sharing similar visual language and design
principles, play important roles in human communication and human-machine interaction …

Abstract Existing studies apply Large Language Model (LLM) to knowledge-based Visual
Question Answering (VQA) with encouraging results. Due to the insufficient input …

Document Visual Question Answering (DocVQA) is a fast growing branch of document
understanding. Despite the fact that documents contain sensitive or copyrighted information …

Layout-aware pre-trained models has achieved significant progress on document image
question answering. They introduce extra learnable modules into existing language models …

The increasing prevalence of Visually-rich Documents (VRDs) in diverse domains has led to
a growing interest in Visually-rich Document Understanding (VrDU). Researchers have …

Document layout analysis is a known problem to the documents research community and
has been vastly explored yielding a multitude of solutions ranging from text mining, and …

This paper highlights the need to bring document classification benchmarking closer to real-
world applications, both in the nature of data tested (X: multi-channel, multi-paged, multi …

The rebroadcasting of screen-recaptured document images introduces a significant risk to
the confidential documents processed in government departments and commercial …