paper-with-me

홈 › Papers

Arctic-TILT. Business Document Understanding at Sub-Billion Scale

2024-08-08 · Łukasz Borchmann, Michał Pietruszka, Wojciech Jaśkowski, Dawid Jurkiewicz, Piotr Halama, Paweł Józiak, Łukasz Garncarek, Paweł Liskowski, Karolina Szyndler, Andrzej Gretkowski, Julita Ołtusek, Gabriela Nowakowska, Artur Zawłocki, Łukasz Duhr, Paweł Dyda, Michał Turski

The vast portion of workloads employing LLMs involves answering questions grounded on PDF or scan content. We introduce the Arctic-TILT achieving accuracy on par with models 1000$\times$ its size on these use cases. It can be fine-tuned and deployed on a single 24GB GPU, lowering operational costs while processing Visually Rich Documents with up to 400k tokens. The model establishes state-of-the-art results on seven diverse Document Understanding benchmarks, as well as provides reliable confidence scores and quick inference, which are essential for processing files in large-scale or time-sensitive enterprise environments.

📄 PDF Abstract BibTeX arXiv:2408.04632

Code (0)

등록된 구현이 없습니다.

Tasks

document understandingGPU

Similar Papers 제목 키워드 기반

Arctic-Extract Technical Report

2025-11-20 · Mateusz Chiliński, Julita Ołtusek, Wojciech Jaśkowski arxiv

Arctic-Extract is a state-of-the-art model designed for extracting structural data (question answering, entities and tables) from scanned or digital-born business documents. Despite its SoTA capabilities, the model is de…

Question Answering

Radar Odometry Subject to High Tilt Dynamics of Subarctic Environments

2026-04-21 · Matěj Boxan, William Larrivée-Hardy, François Pomerleau arxiv

Rotating FMCW radar odometry methods often assume flat ground conditions. While this assumption is sufficient in many scenarios, including urban environments or flat mining setups, the highly dynamic terrain of subarctic…

Radar odometry

Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer

2021-02-18 · Rafał Powalski, Łukasz Borchmann, Dawid Jurkiewicz, Tomasz Dwojak 외

We address the challenging problem of Natural Language Comprehension beyond plain-text documents by introducing the TILT neural network architecture which simultaneously learns layout information, visual features, and te…

DecoderDocument Image Classificationdocument understandingVisual Question Answering+1

A Survey of Deep Learning Approaches for OCR and Document Understanding

2020-11-27 · Nishant Subramani, Alexandre Matton, Malcolm Greaves, Adrian Lam

Documents are a core part of many businesses in many fields such as law, finance, and technology among others. Automatic understanding of documents such as invoices, contracts, and resumes is lucrative, opening up many n…

document understandingOptical Character Recognition (OCR)

Construction and Applications of Billion-Scale Pre-Trained Multimodal Business Knowledge Graph

2022-09-30 · Shumin Deng, Chengming Wang, Zhoubo Li, Ningyu Zhang 외

Business Knowledge Graphs (KGs) are important to many enterprises today, providing factual knowledge and structured data that steer many products and make them more intelligent. Despite their promising benefits, building…

Knowledge Graphs