Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.16470 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912721112399872 |
|---|---|
| author | Chiliński, Mateusz Ołtusek, Julita Jaśkowski, Wojciech |
| author_facet | Chiliński, Mateusz Ołtusek, Julita Jaśkowski, Wojciech |
| contents | 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 deployable on resource-constrained hardware, weighting only 6.6 GiB, making it suitable for deployment on devices with limited resources, such as A10 GPUs with 24 GB of memory. Arctic-Extract can process up to 125 A4 pages on those GPUs, making suitable for long document processing. This paper highlights Arctic-Extract's training protocols and evaluation results, demonstrating its strong performance in document understanding. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_16470 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Arctic-Extract Technical Report Chiliński, Mateusz Ołtusek, Julita Jaśkowski, Wojciech Computation and Language Computer Vision and Pattern Recognition 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 deployable on resource-constrained hardware, weighting only 6.6 GiB, making it suitable for deployment on devices with limited resources, such as A10 GPUs with 24 GB of memory. Arctic-Extract can process up to 125 A4 pages on those GPUs, making suitable for long document processing. This paper highlights Arctic-Extract's training protocols and evaluation results, demonstrating its strong performance in document understanding. |
| title | Arctic-Extract Technical Report |
| topic | Computation and Language Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.16470 |