The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
Cross-referenced across 55 tracked directories
#3523
Popularity Rank
1 / 55
Listed In
Emerging
Adoption Stage
5/13/2025
Created
8,872
GitHub Stars
Score: 100/100
0 dependency vulnerabilities found
Run an AI-powered security scan to analyze this package's source code for vulnerabilities, prompt injection vectors, data exfiltration risks, and behavior mismatches.
Scans fetch actual source code from the GitHub repository, not just the README.
Christoph Auer <cau@zurich.ibm.com>, Michele Dolfi <dol@zurich.ibm.com>, Maxim Lysak <mly@zurich.ibm.com>, Nikos Livathinos <nli@zurich.ibm.com>, Ahmed Nassar <ahn@zurich.ibm.com>, Panos Vagenas <pva@zurich.ibm.com>, Peter Staar <taa@zurich.ibm.com>
SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications.
...more"Outclassing Frontier LLMs in Information Extraction"
A document understanding API
Generate consolidated text files from websites for LLM training and inference – Powered by Firecrawl
751
Forks
73
Open Issues
12/17/2025
Last Commit
Recently added to the ecosystem