Lang-SVG: Hierarchical Image Vectorization with Language Priors
cs.CV
Submitted: 2026-11-11
Updated: 2026-11-11
Project page: https://xiliu8006.github.io/Lang-SVG
Terminology
Sources
- OmniSVG: A Unified Scalable Vector Graphics Generation Model
- Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models
- VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation
- 3DCodeVerse: Exploring 3D Worlds as Code
- PhySimCode: A Benchmark and Evaluation Method for Physics Video to Code Generation
- Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning
- Reinforcement Learning from Intermediate Renders for Image-to-Code Generation
- GenClaw: Code-Driven Agentic Image Generation
- Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks
- AmodalSVG: Amodal Image Vectorization via Semantic Layer Peeling
- InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Models
- UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- GPT-4 Technical Report
- Qwen3 Technical Report
- Seeing or Knowing? Visual Context Sensitivity in Multimodal Large Language Models
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs