Table of Contents

Namespace AiDotNet.Document.VisionLanguage

Classes

DocOwl<T>

DocOwl (mPLUG-DocOwl) for document understanding with multimodal large language model.

InfographicVQA<T>

InfographicVQA for visual question answering on infographics.

UDOP<T>

UDOP (Unifying Vision, Text, and Layout for Universal Document Processing) neural network.