---
title: "VRD-IU: Lessons from Visually Rich Document Intelligence and Understanding"
authors:
  - "Yihao Ding"
  - "Soyeon Caren Han"
  - "Yan Li"
  - "Josiah Poon"
doi: "10.24963/ijcai.2025/1258"
url: "https://ijcai.org/proceedings/2025/1258"
pdf: "https://ijcai.org/proceedings/2025/1258.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "11039-11043"
track: "Demo Track"
keywords:
  - "Natural Language Processing: NLP: Applications"
  - "Natural Language Processing: NLP: Information extraction"
---

# VRD-IU: Lessons from Visually Rich Document Intelligence and Understanding

Yihao Ding, Soyeon Caren Han, Yan Li, Josiah Poon

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 11039-11043. DOI: [10.24963/ijcai.2025/1258](https://doi.org/10.24963/ijcai.2025/1258)

## Abstract

Visually Rich Document Understanding (VRDU) has emerged as a critical field in document intelligence, enabling automated extraction of key information from complex documents across domains such as medical, financial, and educational applications. However, form-like documents pose unique challenges due to their complex layouts, multi-stakeholder involvement, and high structural variability. Addressing these issues, the VRD-IU Competition was introduced, focusing on extracting and localizing key information from multi-format forms within the Form-NLU dataset, which includes digital, printed, and handwritten documents.
This paper presents insights from the competition, which featured two tracks: Track A, emphasizing entity-based key information retrieval, and Track B, targeting end-to-end key information localization from raw document images. With over 20 participating teams, the competition showcased various state-of-the-art methodologies, including hierarchical decomposition, transformer-based retrieval, multimodal feature fusion, and advanced object detection techniques. The top-performing models set new benchmarks in VRDU, providing valuable insights into document intelligence.