Qwen-2.5-7B trained with reinforcement learning against SigLIP visual similarity scores writes SVG drawings that match text captions about as well as frontier models on several automated metrics.
Empowering llms to understand and generate complex vector graphics
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Symbolic Graphics Programming with Large Language Models
Qwen-2.5-7B trained with reinforcement learning against SigLIP visual similarity scores writes SVG drawings that match text captions about as well as frontier models on several automated metrics.