Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917227282825216 |
|---|---|
| author | Yin, Kun Wu, Yunfei Liu, Bing Cai, Zhongpeng Li, Xiaotian Chen, Huang Li, Xin Cao, Haoyu Liu, Yinsong Jiang, Deqiang Sun, Xing Wu, Yunsheng Li, Qianyu Guo, Antai Liao, Yanzhen Qu, Yanqiu Lin, Haodong He, Chengxu Liu, Shuangyin |
| author_facet | Yin, Kun Wu, Yunfei Liu, Bing Cai, Zhongpeng Li, Xiaotian Chen, Huang Li, Xin Cao, Haoyu Liu, Yinsong Jiang, Deqiang Sun, Xing Wu, Yunsheng Li, Qianyu Guo, Antai Liao, Yanzhen Qu, Yanqiu Lin, Haodong He, Chengxu Liu, Shuangyin |
| contents | This paper presents Youtu-Parsing, an efficient and versatile document parsing model designed for high-performance content extraction. The architecture employs a native Vision Transformer (ViT) featuring a dynamic-resolution visual encoder to extract shared document features, coupled with a prompt-guided Youtu-LLM-2B language model for layout analysis and region-prompted decoding. Leveraging this decoupled and feature-reusable framework, we introduce a high-parallelism decoding strategy comprising two core components: token parallelism and query parallelism. The token parallelism strategy concurrently generates up to 64 candidate tokens per inference step, which are subsequently validated through a verification mechanism. This approach yields a 5--11x speedup over traditional autoregressive decoding and is particularly well-suited for highly structured scenarios, such as table recognition. To further exploit the advantages of region-prompted decoding, the query parallelism strategy enables simultaneous content prediction for multiple bounding boxes (up to five), providing an additional 2x acceleration while maintaining output quality equivalent to standard decoding. Youtu-Parsing encompasses a diverse range of document elements, including text, formulas, tables, charts, seals, and hierarchical structures. Furthermore, the model exhibits strong robustness when handling rare characters, multilingual text, and handwritten content. Extensive evaluations demonstrate that Youtu-Parsing achieves state-of-the-art (SOTA) performance on both the OmniDocBench and olmOCR-bench benchmarks. Overall, Youtu-Parsing demonstrates significant experimental value and practical utility for large-scale document intelligence applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_20430 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding Yin, Kun Wu, Yunfei Liu, Bing Cai, Zhongpeng Li, Xiaotian Chen, Huang Li, Xin Cao, Haoyu Liu, Yinsong Jiang, Deqiang Sun, Xing Wu, Yunsheng Li, Qianyu Guo, Antai Liao, Yanzhen Qu, Yanqiu Lin, Haodong He, Chengxu Liu, Shuangyin Computer Vision and Pattern Recognition This paper presents Youtu-Parsing, an efficient and versatile document parsing model designed for high-performance content extraction. The architecture employs a native Vision Transformer (ViT) featuring a dynamic-resolution visual encoder to extract shared document features, coupled with a prompt-guided Youtu-LLM-2B language model for layout analysis and region-prompted decoding. Leveraging this decoupled and feature-reusable framework, we introduce a high-parallelism decoding strategy comprising two core components: token parallelism and query parallelism. The token parallelism strategy concurrently generates up to 64 candidate tokens per inference step, which are subsequently validated through a verification mechanism. This approach yields a 5--11x speedup over traditional autoregressive decoding and is particularly well-suited for highly structured scenarios, such as table recognition. To further exploit the advantages of region-prompted decoding, the query parallelism strategy enables simultaneous content prediction for multiple bounding boxes (up to five), providing an additional 2x acceleration while maintaining output quality equivalent to standard decoding. Youtu-Parsing encompasses a diverse range of document elements, including text, formulas, tables, charts, seals, and hierarchical structures. Furthermore, the model exhibits strong robustness when handling rare characters, multilingual text, and handwritten content. Extensive evaluations demonstrate that Youtu-Parsing achieves state-of-the-art (SOTA) performance on both the OmniDocBench and olmOCR-bench benchmarks. Overall, Youtu-Parsing demonstrates significant experimental value and practical utility for large-scale document intelligence applications. |
| title | Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.20430 |