JunyiYe/TextFlow

[NAACL 2025] Beyond End-to-End VLMs: Leveraging Intermediate Text Representations for Superior Flowchart Understanding

36
/ 100
Emerging

This helps researchers in AI and natural language processing to better understand and work with flowcharts presented as images. It takes a flowchart image as input and converts it into a structured text representation like Mermaid or Graphviz, then uses that text to answer questions about the flowchart. The output is a clear, textual explanation or answer, offering more control and insight into the reasoning process. This is for researchers and developers working on AI models for visual understanding.

No commits in the last 6 months.

Use this if you need a more transparent and controllable way to process and reason about information contained in flowchart images, especially when developing or evaluating AI models.

Not ideal if you're an end-user simply looking to create flowcharts or get quick answers without needing to delve into the underlying AI mechanisms.

AI-research NLP-development visual-question-answering flowchart-analysis model-explainability
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

20

Forks

3

Language

Python

License

MIT

Last pushed

Aug 23, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/JunyiYe/TextFlow"

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