The paper proposes using an abstract graphics language as an intermediate representation for generating vector graphics from text. They introduce a large-scale dataset and a new model that outperforms existing models in terms of similarity to human-created figures. The framework and datasets are publicly available.

https://arxiv.org/abs//2310.00367

YouTube: https://www.youtube.com/@ArxivPapers

TikTok: https://www.tiktok.com/@arxiv_papers

Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016

Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers