Tencent open-sources 3B SVG model HiVG to make tokens geometry-aware

SVG性能比肩GPT/Claude，腾讯开源3B模型HiVG，让Token「懂几何」

Tencent Hunyuan open-sourced the 3B-parameter HiVG, claiming 62.7%-63.8% shorter SVG sequences via hierarchical tokenization and better SVG generation metrics than GPT-5.2, Claude-4.5-Sonnet, and some 8B open models. The post reports 0.896 SSIM, 0.114 LPIPS, and 0.957 CLIP-S on Image-to-SVG; the core method packs drawing commands plus coordinates into segment tokens and uses HMN to initialize coordinate embeddings. The part to watch is token design, not parameter count; paper, code, and project page are public.

Why it matters: Tencent's HiVG earns HKR-H and HKR-K: a 3B open model claims GPT/Claude-level SVG results, and the article includes 62.7%-63.8% token compression plus SSIM 0.896, LPIPS 0.114, and CLIP-S 0.957. HKR-R is weaker because SVG generation remains niche, so it lands at the low end of `f