In this work, we introduce Mini-Gemini, a simple and effective framework enhancing multi-
modality Vision Language Models (VLMs). Despite the advancements in VLMs facilitating …

We call on the Document AI (DocAI) community to re-evaluate current methodologies and
embrace the challenge of creating more practically-oriented benchmarks. Document …

Existing work on DocVQA only considers single-page documents. However, in real
applications documents are mostly composed of multiple pages that should be processed …

Visual question answering on document images that contain textual, visual, and layout
information, called document VQA, has received much attention recently. Although many …

There are already some text-based visual question answering (TextVQA) benchmarks for
developing machine's ability to answer questions based on texts in images in recent years …

Geometry problem solving (GPS) is a high-level mathematical reasoning requiring the
capacities of multi-modal fusion and geometric knowledge application. Recently, neural …

Pretraining has proven successful in Document Intelligence tasks where deluge of
documents are used to pretrain the models only later to be finetuned on downstream tasks …

Recent advancements in Multimodal Large Language Models (LLMs) have focused
primarily on scaling by increasing text-image pair data and enhancing LLMs to improve …

Abstract Video Question Answering methods focus on common-sense reasoning and visual
cognition of objects or persons and their interactions over time. Current VideoQA …

In this report we present results of the ICDAR 2021 edition of the Document Visual Question
Challenges. This edition complements the previous tasks on Single Document VQA and …