Cancer research encompasses data across various scales, modalities, and resolutions, from
screening and diagnostic imaging to digitized histopathology slides to various types of …

Self-supervised pre-training techniques have achieved remarkable progress in Document
AI. Most multimodal pre-trained models use a masked language modeling objective to learn …

Multimodal learning, which aims to understand and analyze information from multiple
modalities, has achieved substantial progress in the supervised regime in recent years …

Understanding document images (eg, invoices) is a core but challenging task since it
requires complex functions such as reading text and a holistic understanding of the …

Abstract We propose Universal Document Processing (UDOP), a foundation Document AI
model which unifies text, image, and layout modalities together with varied task formats …

Pre-trained large language models (LLMs) have recently achieved better generalization and
sample efficiency in autonomous web navigation. However, the performance on real-world …

Image Transformer has recently achieved significant progress for natural image
understanding, either using supervised (ViT, DeiT, etc.) or self-supervised (BEiT, MAE, etc.) …

Structured document understanding has attracted considerable attention and made
significant progress recently, owing to its crucial role in intelligent document processing …

Visual information extraction (VIE) plays an important role in Document Intelligence.
Generally, it is divided into two tasks: semantic entity recognition (SER) and relation …

Key information extraction (KIE) from document images requires understanding the
contextual and spatial semantics of texts in two-dimensional (2D) space. Many recent …