DisciplineGen-1M is a million-scale multidisciplinary dataset for text-to-image generation and editing, paired with a discipline-informed model that improves results on discipline-specific benchmarks.
Internsvg: Towards unified svg tasks with multimodal large language models
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
representative citing papers
AmodalSVG produces semantically separate and geometrically complete SVG layers from natural images by using VLM-guided semantic layer peeling for amodal completion followed by adaptive vectorization.
HiVG introduces hierarchical SVG tokenization with atomic and segment tokens plus HMN initialization to enable more efficient and stable autoregressive generation of vector graphics programs.
Reason-SVG adds a Drawing-with-Thought reasoning stage and GRPO-based reinforcement learning with a hybrid reward to improve LLM and VLM performance on accurate SVG generation.
CSL recovers mark type (0.822), visualization role (0.853), and data role (0.860) macro accuracy from 102 SVGs via cohort decomposition and hybrid grounding, outperforming non-cohort baseline.
GenClaw introduces a three-stage code-driven workflow for agentic image generation that inserts programmatic sketches between linguistic reasoning and pixel synthesis.
SVG synthesis is cast as step-wise generation conditioned on intermediate rendered canvases, trained with Visual Self-Feedback and filtered by Render-and-Verify, claiming gains on MMSVGBench.
A vision-language model for robust image vectorization via rounded polygon primitives and input degradation simulation.
citing papers explorer
-
DisciplineGen-1M: A Large-Scale Dataset for Multidisciplinary Visual Generation and Editing
DisciplineGen-1M is a million-scale multidisciplinary dataset for text-to-image generation and editing, paired with a discipline-informed model that improves results on discipline-specific benchmarks.
-
AmodalSVG: Amodal Image Vectorization via Semantic Layer Peeling
AmodalSVG produces semantically separate and geometrically complete SVG layers from natural images by using VLM-guided semantic layer peeling for amodal completion followed by adaptive vectorization.
-
Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modeling
HiVG introduces hierarchical SVG tokenization with atomic and segment tokens plus HMN initialization to enable more efficient and stable autoregressive generation of vector graphics programs.
-
Reason-SVG: Enhancing Structured Reasoning for Vector Graphics Generation with Reinforcement Learning
Reason-SVG adds a Drawing-with-Thought reasoning stage and GRPO-based reinforcement learning with a hybrid reward to improve LLM and VLM performance on accurate SVG generation.
-
Cohort-based Semantic Labeling: AI-Enabled Recovery of Visualization Semantics from Deployed SVGs
CSL recovers mark type (0.822), visualization role (0.853), and data role (0.860) macro accuracy from 102 SVGs via cohort decomposition and hybrid grounding, outperforming non-cohort baseline.
-
GenClaw: Code-Driven Agentic Image Generation
GenClaw introduces a three-stage code-driven workflow for agentic image generation that inserts programmatic sketches between linguistic reasoning and pixel synthesis.
-
Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedback
SVG synthesis is cast as step-wise generation conditioned on intermediate rendered canvases, trained with Visual Self-Feedback and filtered by Render-and-Verify, claiming gains on MMSVGBench.
-
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.