Reproduce “Do You Miss the Nights We Spent Crafting Figures? Rethinking Teaser and Framework Figures in the Age of Generative AI” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Xiaoqi Zhao, Youwei Pang, Kailai Zhou
The authors compare source-constrained revisions of motivation and framework figures using model ratings before and after revision. Clarity rates how readily figures communicate their message; aesthetic coherence rates how well design elements work together. Among 369 revisions passing fidelity checks, mean clarity rose 0.428 points and aesthetic coherence fell 0.111 on a 1–5 scale; these are model ratings, not human comprehension results.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.