Since a vast number of tables can be easily collected from web pages, spreadsheets, PDFs,
and various other document types, a flurry of table pre-training frameworks have been …

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

The ever-growing abundance of data found in heterogeneous sources, such as scientific
publications, has forced the development of automated techniques for data extraction. While …

This work presents a sparse-attention Transformer architecture for modeling documents that
contain large tables. Tables are ubiquitous on the web, and are rich in information. However …

Tables are often created with hierarchies, but existing works on table reasoning mainly focus
on flat tables and neglect hierarchical tables. Hierarchical tables challenge existing methods …

Enterprise documents such as forms, invoices, receipts, reports, contracts, and other similar
records, often carry rich semantics at the intersection of textual and spatial modalities. The …

Tables contain a significant portion of the world's structured information. The ability to
efficiently and accurately understand, process, reason about, analyze, and generate tabular …

Understanding documents with rich layouts and multi-modal components is a long-standing
and practical task. Recent Large Vision-Language Models (LVLMs) have made remarkable …

Peer review is a key component of the publishing process in most fields of science.
Increasing submission rates put a strain on reviewing quality and efficiency, motivating the …

We present a review of the methods behind the top 40 highest accuracies achieved on the
ILSVRC 2012 Imagenet validation set as ranked on Papers with Code. A significant …