Frontier Results
Image-to-SVG
Token Compression
3B parameters. SVG quality that rivals the closed-source giants.
Convert any image into a clean, editable SVG — structure, layout, and detail faithfully preserved.
2.76× token sequence compression. Sub-second generation vs. minutes for closed-source models.
HiVG transforms raw SVG code through two levels of tokenization. Click each stage to see the transformation.
Tokenizer
Tokens
Tokens
String
Tokenizer
Learning
Output
HiVG's pipeline begins with a Hierarchical SVG Tokenizer that decomposes raw SVG into atomic tokens, then learns Structure Segments to compress sequences. A 3B-parameter language model generates SVG token sequences, which are detokenized back into clean SVG output.
Hierarchical SVG Tokenizer
A two-level tokenization scheme that preserves the full geometric semantics of SVG commands. Level 1 (Atomic) decomposes raw SVG into typed tokens — structure, commands, coordinates, and attributes. Level 2 (Segment) merges each drawing command with its parameters into a single compact token.
Structure Segment Learning
Learns segment tokens directly from the SVG corpus. Each segment merges a drawing command (e.g., Bézier curve, arc, line) with its coordinate parameters into one token, capturing renderable geometric primitives while discarding invalid combinations.
@article{xing2026hivg,
title={Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modeling},
author={Xing, Ximing and Xue, Ziteng and Li, Zhenxi and Liang, Weicong and Wang, Linqing and Yang, Zhantao and Hang, Tiankai and Yin, Zijin and Lu, Qinglin and Wang, Chunyu and Yu, Qian},
journal={arXiv preprint arXiv:2604.05072},
year={2026},
}