# CANVAS: Consistency-Aware Navigation via Visual Adaptive Sampling for Long-Context Text-to-SVG Generation

arXiv: https://arxiv.org/abs/2608.30689 · HTML: https://mlsanity.com/paper/2608.30689/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 29 references that are in the map.
- First posted on arXiv 31 Aug 2026.

## Builds on (most cited first, 25 of 25)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders](https://mlsanity.com/paper/2106.14843/) (2021)
- [VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models](https://mlsanity.com/paper/2211.11319/) (2022)
- [StarVector: Generating Scalable Vector Graphics Code from Images and Text](https://mlsanity.com/paper/2312.11556/) (2023)
- [Reasoning with Sampling: Your Base Model is Smarter Than You Think](https://mlsanity.com/paper/2510.14901/) (2025)
- [SVGDreamer: Text Guided SVG Generation with Diffusion Model](https://mlsanity.com/paper/2312.16476/) (2023)
- [IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformers](https://mlsanity.com/paper/2304.14400/) (2023)
- [OmniSVG: A Unified Scalable Vector Graphics Generation Model](https://mlsanity.com/paper/2504.06263/) (2025)
- [Empowering LLMs to Understand and Generate Complex Vector Graphics](https://mlsanity.com/paper/2412.11102/) (2024)
- [DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models](https://mlsanity.com/paper/2306.14685/) (2023)
- [Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models](https://mlsanity.com/paper/2411.16602/) (2024)
- [Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening](https://mlsanity.com/paper/2601.21590/) (2026)
- [StrokeNUWA: Tokenizing Strokes for Vector Graphic Synthesis](https://mlsanity.com/paper/2401.17093/) (2024)
- [SVGBuilder: Component-Based Colored SVG Generation with Text-Guided Autoregressive Transformers](https://mlsanity.com/paper/2412.10488/) (2024)
- [SVGen: Interpretable Vector Graphics Generation with Large Language Models](https://mlsanity.com/paper/2508.09168/) (2025)
- [Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedback](https://mlsanity.com/paper/2604.20730/) (2026)
- [Reason-SVG: Enhancing Structured Reasoning for Vector Graphics Generation with Reinforcement Learning](https://mlsanity.com/paper/2505.24499/) (2025)
- [SVGThinker: Instruction-Aligned and Reasoning-Driven Text-to-SVG Generation](https://mlsanity.com/paper/2509.24299/) (2025)
- [LaDe: Unified Multi-Layered Graphic Media Generation and Decomposition](https://mlsanity.com/paper/2603.17965/) (2026)
- [Sampling for Quality: Training-Free Reward-Guided LLM Decoding via Sequential Monte Carlo](https://mlsanity.com/paper/2604.16453/) (2026)
- [IntroSVG: Learning from Rendering Feedback for Text-to-SVG Generation via an Introspective Generator-Critic Framework](https://mlsanity.com/paper/2603.09312/) (2026)
- [Vector Grimoire: Codebook-based Shape Generation under Raster Image Supervision](https://mlsanity.com/paper/2410.05991/) (2024)
- [Drift is a Sampling Error: SNR-Aware Power Distributions for Long-Horizon Robotic Planning](https://mlsanity.com/paper/2605.09537/) (2026)
- [Unlocking the Latent Canvas: Eliciting and Benchmarking Symbolic Visual Expression in LLMs](https://mlsanity.com/paper/2603.14505/) (2026)
- [Unsupervised edge map scoring: a statistical complexity approach](https://mlsanity.com/paper/1302.5186/) (2013)

## Abstract (arXiv)

Autoregressive large models have recently advanced Text-to-SVG generation from simple icons to complex, long-context graphics, yet standard autoregressive decoding often fails to maintain global consistency across geometry, layout, occlusion, and composition. We introduce CANVAS (Consistency-Aware Navigation via Visual Adaptive Sampling), a training-free, render-aware inference framework that combines power-sharpened trajectory likelihood with visual feedback from rendered futures and derives a stroke-wise navigation rule. It effectively estimates each candidate stroke's future value under a limited generation and rendering budget and adaptively allocates samples according to candidate uncertainty, decision influence, and rollout cost. Experiments across multiple autoregressive SVG backbones and complementary benchmarks demonstrate improvements in global consistency, which includes sound geometric relationships, spatial layouts, occlusion ordering, and overall composition, without additional training, demonstrating the effectiveness and generalization ability of our framework.