The paper introduces a platform that renders web pages using FitLayout and captures their visual and structural properties in an RDF-based representation. The system offers a REST API for pipeline control, SPARQL queries for data retrieval, and a Python client to integrate with machine learning workflows. It demonstrates how rendered pages can be converted into graph representations to train graph neural networks for key content recognition, highlighting reproducibility and dataset sharing.
arXiv:2610.33929v1 Announce Type: new Abstract: Large language models have made remarkable strides in website development, enabling complete and interactive web experiences to be built from natural-l...
arXiv:2610.20335v1 Announce Type: new Abstract: Document understanding systems are typically evaluated as separate components via layout analysis, optical text recognition, reading-order prediction,...
Document understanding systems are typically evaluated as separate components via layout analysis, optical text recognition, reading-order prediction, and image captioning. This separation leaves scie...
AmbiHTMLBench is a new benchmark that evaluates how well models can convert real-world documents into executable HTML while preserving content, organization, and visual appearance. It contains 1,115 pages with structured annotations and uses both objective metrics (table fidelity, text error, layout consistency) and a reference-anchored subjective protocol (LLM judges aligned with human preferences). Results show that different systems excel in objective versus subjective measures, and fine‑tuning a small expert model improves performance, highlighting the benchmark’s role as a diagnostic tool for advanced document parsing.
arXiv:2607. 20477v1 Announce Type: new Abstract: {\em Text-Attributed Graphs} (TAGs) have emerged as an expressive data model for integrating graph topology with rich textual semantics.
arXiv:2606. 28344v1 Announce Type: cross Abstract: Augmenting large language models (LLMs) with retrieved web text has become a dominant paradigm, yet the web is not natively textual: existing systems depend on complex parsing pipelines that linearize HTML and discard layout, visual structure, and formatting.
arXiv:2606. 32016v1 Announce Type: new Abstract: Multimodal graph foundation models aim to learn reusable knowledge from graphs enriched with text, images, attributes, and relational topology, thereby supporting diverse graph-centric and modality-centric tasks.
arXiv:2608. 16628v1 Announce Type: new Abstract: Modern Multimodal Retrieval-Augmented Generation (M-RAG) systems are fundamentally limited by the binary connectivity paradigm of traditional simple graphs, which fails to capture the intricate, high-order correlations among heterogeneous entities, such as the N-ary relationships between a visual chart, its scattered textual descriptions, and underlying numerical data.
arXiv:2607. 19128v1 Announce Type: new Abstract: Vision-language models (VLMs) provide a unified representation space for textual and visual information, yet their potential as general-purpose backbones for graph-structured data remains largely unexplored.
Visual document retrieval has recently become increasingly important in applications such as enterprise search, scientific literature discovery, and retrieval-augmented generation. These applications depend on efficiently identifying query-relevant pages across large collections of visually rich documents.
arXiv:2405. 03650v4 Announce Type: replace-cross Abstract: We study Generated Contents Enrichment (GCE), a conditional image-generation task in which a sparse scene description is first enriched through an explicit scene representation and then rendered into semantically richer visual content.
KGATE is a modular Python library for training knowledge graph embedding (KGE) models, built on PyTorch Geometric and TorchKGE. It allows users to assemble or plug in components such as initializers, encoders, decoders, losses, negative samplers, and evaluation metrics, and includes a preprocessing step to prevent data leakage. Benchmarks against six existing KGE libraries show that KGATE’s training time is comparable to the fastest while offering a broader set of features.