Diagram Generation

2 items

RESEARCHarXiv CS.AI·8d ago

PhyDrawGen: Physically Grounded Diagram Generation from Natural Language

PhyDrawGen is a neuro-symbolic pipeline designed to generate physically accurate physics diagrams from natural language text, outperforming existing models in adhering to physical laws. It leverages a large language model for scene graph extraction and a deterministic solver to enforce physical and geometric constraints.

Diagram Generation Physics AI large language models

NEWSDEV.to AI·4/25/2026

PaperBanana: Automate Your Academic Illustrations with AI!

PaperBanana is an open-source, community-driven implementation that automates the generation of academic illustrations, diagrams, and plots from text descriptions. It uses a sophisticated multi-agent AI pipeline supporting multiple LLM and VLM providers, significantly reducing the time researchers spend creating visual aids.

academic tools Open Source Diagram Generation AI