Total runs:
111.0K
Run Growth:
29.5K
Growth Rate:
26.60%
Sponsored by
Topview AI
ByteDance / Dolphin
Model's Last Updated: July 16 2025
image-text-to-text
Introduction of Dolphin
Model Details of Dolphin
Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting
Model Description
Dolphin ( Do cument Image P arsing via H eterogeneous Anchor Prompt in g) is a novel multimodal document image parsing model that follows an analyze-then-parse paradigm. It addresses the challenges of complex document understanding through a two-stage approach designed to handle intertwined elements such as text paragraphs, figures, formulas, and tables.
📑 Overview
Document image parsing is challenging due to its complexly intertwined elements such as text paragraphs, figures, formulas, and tables. Dolphin addresses these challenges through a two-stage approach:
- 🔍 Stage 1 : Comprehensive page-level layout analysis by generating element sequence in natural reading order
- 🧩 Stage 2 : Efficient parallel parsing of document elements using heterogeneous anchors and task-specific prompts
Dolphin achieves promising performance across diverse page-level and element-level parsing tasks while ensuring superior efficiency through its lightweight architecture and parallel parsing mechanism.
Model Architecture
Dolphin is built on a vision-encoder-decoder architecture using transformers:
- Vision Encoder : Based on Swin Transformer for extracting visual features from document images
- Text Decoder : Based on MBart for decoding text from visual features
- Prompt-based interface : Uses natural language prompts to control parsing tasks
The model is implemented as a Hugging Face
VisionEncoderDecoderModel
for easy integration with the Transformers ecosystem.
Usage
Our demo will be released in these days. Please keep tuned! 🔥
Please refer to our GitHub repository for detailed usage.
- Page-wise parsing : for an entire document image
- Element-wise parsing : for an element (paragraph, table, formula) image
License
This model is released under the MIT License.
Citation
@inproceedings{dolphin2025,
title={Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting},
author={Feng, Hao and Wei, Shu and Fei, Xiang and Shi, Wei and Han, Yingdong and Liao, Lei and Lu, Jinghui and Wu, Binghong and Liu, Qi and Lin, Chunhui and Tang, Jingqun and Liu, Hao and Huang, Can},
year={2025},
booktitle={Proceedings of the 65rd Annual Meeting of the Association for Computational Linguistics (ACL)}
}
Acknowledgements
This model builds on several open-source projects including:
Runs of ByteDance Dolphin on huggingface.co
868
Total runs
2
24-hour runs
9
3-day runs
38
7-day runs
412
30-day runs
More Information About Dolphin huggingface.co Model
Url of Dolphin
Dolphin huggingface.co Url
Provider of Dolphin huggingface.co
Other API from ByteDance
Updated:June 12 2025
Total runs:
86.2K
Run Growth:
-21.3K
Growth Rate:
-24.75%
Total runs:
30.3K
Run Growth:
11.1K
Growth Rate:
36.78%
Total runs:
21.5K
Run Growth:
-24.3K
Growth Rate:
-112.68%
Total runs:
14.7K
Run Growth:
2.3K
Growth Rate:
15.53%
Total runs:
13.9K
Run Growth:
7.6K
Growth Rate:
54.18%
Total runs:
11.6K
Run Growth:
6.0K
Growth Rate:
51.69%
Total runs:
1.0K
Run Growth:
-247
Growth Rate:
-24.63%
Total runs:
395
Run Growth:
358
Growth Rate:
90.63%
Total runs:
291
Run Growth:
-358
Growth Rate:
-123.02%
Total runs:
136
Run Growth:
36
Growth Rate:
26.47%
Total runs:
110
Run Growth:
-76
Growth Rate:
-69.09%
Total runs:
103
Run Growth:
40
Growth Rate:
38.83%
Total runs:
80
Run Growth:
-3
Growth Rate:
-3.75%
Total runs:
78
Run Growth:
-40
Growth Rate:
-51.28%
Total runs:
57
Run Growth:
-14
Growth Rate:
-24.56%
Total runs:
35
Run Growth:
9
Growth Rate:
25.71%
Total runs:
31
Run Growth:
-8
Growth Rate:
-25.81%
Total runs:
23
Run Growth:
-22
Growth Rate:
-95.65%
Total runs:
12
Run Growth:
-12
Growth Rate:
-100.00%
Total runs:
5
Run Growth:
-14
Growth Rate:
-280.00%
Total runs:
3
Run Growth:
-12
Growth Rate:
-400.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%