Jo-Pan/FlowLearn

Evaluating Large Vision-Language Models on Flowchart Understanding. Published in ECAI 2024.

13
/ 100
Experimental

This project offers a specialized dataset and framework for evaluating how well Large Vision-Language Models (LVLMs) understand flowcharts. It takes in complex scientific and simulated flowcharts, complete with detailed annotations, and helps researchers understand which LVLMs are best at interpreting them. This is for AI researchers and scientists developing or applying LVLMs to improve automated comprehension of visual diagrams.

No commits in the last 6 months.

Use this if you are a researcher or developer focused on enhancing the ability of AI models to interpret and extract information from flowcharts, especially in scientific contexts.

Not ideal if you are looking for a tool to generate flowcharts or a ready-to-use application for extracting information from flowcharts without engaging in model development or evaluation.

AI-evaluation scientific-diagrams model-benchmarking visual-language-processing chart-comprehension
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

10

Forks

Language

Python

License

Last pushed

Sep 25, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/Jo-Pan/FlowLearn"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.