VIGA introduces a training-free interleaved multimodal reasoning loop that improves vision-as-inverse-graphics accuracy over one-shot baselines on BlenderGym, SlideBench, and new BlenderBench.
Empowering llms to understand and generate complex vector graphics
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
GeoSVG-RL uses RL with six geometric reward dimensions from rendered SVGs to improve structural accuracy over standard language model training for diagram generation.
SVGFusion introduces a Vector-Pixel Fusion VAE and Vector Space Diffusion Transformer to generate high-quality editable SVGs from text, claiming SOTA results on a new 240k human-designed SVG dataset.
A vision-language model for robust image vectorization via rounded polygon primitives and input degradation simulation.
citing papers explorer
-
Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning
VIGA introduces a training-free interleaved multimodal reasoning loop that improves vision-as-inverse-graphics accuracy over one-shot baselines on BlenderGym, SlideBench, and new BlenderBench.
-
GeoSVG-RL: Geometry-Aware Reinforcement Learning for Layout-Constrained Text-to-SVG Diagram Generation
GeoSVG-RL uses RL with six geometric reward dimensions from rendered SVGs to improve structural accuracy over standard language model training for diagram generation.
-
SVGFusion: A VAE-Diffusion Transformer for Vector Graphic Generation
SVGFusion introduces a Vector-Pixel Fusion VAE and Vector Space Diffusion Transformer to generate high-quality editable SVGs from text, claiming SOTA results on a new 240k human-designed SVG dataset.
-
VectorArk: Learning Practical Image Vectorization with Rounded Polygon Representation
A vision-language model for robust image vectorization via rounded polygon primitives and input degradation simulation.