ainewsblitz.com

Breaking

HiVG Introduces Hierarchical SVG Tokenization, Claiming to Beat GPT-5 and Gemini 2.5 on Image-to-SVG

HiVG Introduces Hierarchical SVG Tokenization, Claiming to Beat GPT-5 and Gemini 2.5 on Image-to-SVG
  • Media Generation
  • Open Source
  • Foundation Models

HiVG, a newly released framework for converting images into clean, editable SVGs, uses a hierarchical tokenization scheme that its authors say outperforms all seven proprietary models tested — including GPT-5 and Gemini 2.5 — on image-to-SVG generation. The project, released with an open-weight 3B-parameter model under an MIT license, targets a persistent weakness in modern vector-graphics generation: the tendency of large language models to garble the numerical coordinates that define an SVG's geometry.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,934 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year