bytedance/Dolphin
The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
The project lists 3 contributors on GitHub.
Gained 81% fewer stars in the last 90 days than in the 90 days before.
Use Cases & Benefits
- Parses complex document images into structured data using a two-stage analyze-then-parse multimodal model.
- Delivers efficient and accurate document parsing with a lightweight architecture and parallel element decoding.
- Use for extracting structured content from scanned PDFs and images in natural reading order.
- Use for parsing individual document elements like tables, formulas, and text paragraphs separately.
- Use for integrating document image parsing into Python workflows with Hugging Face Transformer support.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
Other
GitHub could not identify this license; read the LICENSE file before depending on it.
Community files
- README: present
Watch-outs
- License not identified by GitHub; read the LICENSE file before depending on it.
- No commits in the last six months (last push Mar 2026).
- No GitHub releases; pin a commit or tag instead of a release.
General guidance from repository metadata, not legal advice. How we score
From the README
Dolphin (Document Image Parsing via Heterogeneous Anchor Prompting) is a novel multimodal document image parsing model following an analyze-then-parse paradigm. This repository contains the demo code and pre-trained models for Dolphin.
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:
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.
Try our demo on Demo-Dolphin.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
Forks
772-2
Open issues
78+1
Compared with peers in Computer Vision
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| mudler/LocalAI | 50.2K | +176 | 59 | 12 days ago |
| PaddlePaddle/PaddleOCR | 92.3K | — | 47 | 147 days ago |
| d2l-ai/d2l-en | 30.0K | — | 45 | — |
| lukas-blecher/LaTeX-OCR | 16.6K | — | 18 | — |
| bytedance/Dolphin | 9.1K | — | 7 | — |
| SharpAI/DeepCamera | 3.1K | — | 31 | 227 days ago |
| Category median | 30.0K | — | 45 | — |
Also by bytedance
Other repositories from this maintainer that GStars tracks
- Python84.6K stars
deer-flow
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
- TypeScript39.4K stars
UI-TARS-desktop
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
- Python12.2K stars
trae-agent
Trae Agent is an LLM-based agent for general purpose software engineering tasks.
- Python11.7K stars
UI-TARS
Pioneering Automated GUI Interaction with Native Agents
- Go9.7K stars
sonic
A blazingly fast JSON serializing & deserializing library
Discover Repositories
Search across tracked repositories by name or description