arXiv:2608. 10628v1 Announce Type: cross Abstract: Long-document understanding often requires reasoning over many visually rich pages, making inference costly and prone to context rot.
arXiv:2601. 13591v2 Announce Type: replace Abstract: Recent LLM-based data agents aim to automate data science tasks ranging from data analysis to deep learning.
arXiv:2608. 14075v1 Announce Type: new Abstract: Scientific figures and tables encode essential experimental evidence, yet remain difficult for digital libraries and multimodal AI systems to retrieve and interpret.
arXiv:2607. 18514v1 Announce Type: cross Abstract: Visual diagrams, figures, and tables are central to scientific papers, and convey information beyond what is captured in text.
arXiv:2607. 16560v1 Announce Type: new Abstract: We propose a language representation for multimodal data in which any observation, whether image, video, or text, is expressed as a bag of atomic propositions, simple statements about the entities, actions, and relations in a scene.
arXiv:2608. 12898v1 Announce Type: cross Abstract: Document parsing aims to transform unstructured documents into structured and machine-readable representations.
arXiv:2606. 02162v1 Announce Type: cross Abstract: Document type classification in visually rich documents remains challenging, as relevant information is distributed across textual, visual, and layout modalities.
Key Information Extraction (KIE) converts visually rich documents into structured data, but practical deployment remains challenging: strong performance often relies on costly on-server Large Multimodal Models (LMMs), while compact locally deployable models lack sufficient KIE supervision. We present SAYRE, a scene-aware document synthesis framework for generating scalable KIE training data without hand-crafted template design.