mPLUG-PaperOwl

github.com/x-plug/mplug-docowl

Multimodal LLM for scientific charts and diagrams understanding/generation

Sourced from

  • Awesome AI for Sciencegithub.com/x-plug/mplug-docowl

Related resources

Multi-agent system with Parser-Planner-Painter architecture converting `paper.pdf` to editable `poster.pptx`, outperforms GPT-4o with 87% fewer tokens