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.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.