[PDG 476] PaperBanana: Automating Academic Illustration for AI Scientists

Link to article: https://arxiv.org/pdf/2601.23265
Title: PaperBanana: Automating Academic Illustration for AI Scientists
Content: PaperBanana is an agentic framework that automates the creation of publication-ready academic illustrations—addressing a major research bottleneck—by orchestrating specialized agents with modern vision-language and image-generation models to retrieve references, plan, render, and iteratively refine figures via self-critique. The authors also introduce PaperBananaBench (292 NeurIPS 2025–curated methodology-diagram test cases) and report experiments showing PaperBanana outperforms strong baselines on faithfulness, conciseness, readability, and aesthetics, while also generalizing to high-quality statistical plots.
Slack link: ml-ka.slack.com, channel: #pdg. Please join us -- if you cannot join, please message us here or to mlpaperdiscussiongroupka@gmail.com.

In the Paper Discussion Group (PDG) we discuss recent and fundamental papers in the area of machine learning on a weekly basis. If you are interested, please read the paper beforehand and join us for the discussion. If you have not fully understood the paper, you can still participate – everyone is welcome! You can join the discussion or simply listen in. The discussion is in German or English depending on the participants.