Uni-Parser Technical Report
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914389668397056 |
|---|---|
| author | Fang, Xi Tao, Haoyi Yang, Shuwen Huang, Chaozheng Zhong, Suyang Lu, Haocheng Lyu, Han Wang, Junjie Li, Xinyu Zhang, Linfeng Ke, Guolin |
| author_facet | Fang, Xi Tao, Haoyi Yang, Shuwen Huang, Chaozheng Zhong, Suyang Lu, Haocheng Lyu, Han Wang, Junjie Li, Xinyu Zhang, Linfeng Ke, Guolin |
| contents | This technical report introduces Uni-Parser, an industrial-grade document parsing engine tailored for scientific literature and patents, delivering high throughput, robust accuracy, and cost efficiency. Unlike pipeline-based document parsing methods, Uni-Parser employs a modular, loosely coupled multi-expert architecture that preserves fine-grained cross-modal alignments across text, equations, tables, figures, and chemical structures, while remaining easily extensible to emerging modalities. The system incorporates adaptive GPU load balancing, distributed inference, dynamic module orchestration, and configurable modes that support either holistic or modality-specific parsing. Optimized for large-scale cloud deployment, Uni-Parser achieves a processing rate of up to 20 PDF pages per second on 8 x NVIDIA RTX 4090D GPUs, enabling cost-efficient inference across billions of pages. This level of scalability facilitates a broad spectrum of downstream applications, ranging from literature retrieval and summarization to the extraction of chemical structures, reaction schemes, and bioactivity data, as well as the curation of large-scale corpora for training next-generation large language models and AI4Science models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_15098 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Uni-Parser Technical Report Fang, Xi Tao, Haoyi Yang, Shuwen Huang, Chaozheng Zhong, Suyang Lu, Haocheng Lyu, Han Wang, Junjie Li, Xinyu Zhang, Linfeng Ke, Guolin Computer Vision and Pattern Recognition This technical report introduces Uni-Parser, an industrial-grade document parsing engine tailored for scientific literature and patents, delivering high throughput, robust accuracy, and cost efficiency. Unlike pipeline-based document parsing methods, Uni-Parser employs a modular, loosely coupled multi-expert architecture that preserves fine-grained cross-modal alignments across text, equations, tables, figures, and chemical structures, while remaining easily extensible to emerging modalities. The system incorporates adaptive GPU load balancing, distributed inference, dynamic module orchestration, and configurable modes that support either holistic or modality-specific parsing. Optimized for large-scale cloud deployment, Uni-Parser achieves a processing rate of up to 20 PDF pages per second on 8 x NVIDIA RTX 4090D GPUs, enabling cost-efficient inference across billions of pages. This level of scalability facilitates a broad spectrum of downstream applications, ranging from literature retrieval and summarization to the extraction of chemical structures, reaction schemes, and bioactivity data, as well as the curation of large-scale corpora for training next-generation large language models and AI4Science models. |
| title | Uni-Parser Technical Report |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.15098 |