# Unlocking the Latent Canvas: Eliciting and Benchmarking Symbolic Visual Expression in LLMs

arXiv: https://arxiv.org/abs/2603.14505 · HTML: https://mlsanity.com/paper/2603.14505/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 36 references that are in the map.
- First posted on arXiv 15 Mar 2026.

## Builds on (most cited first, 27 of 27)

- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://mlsanity.com/paper/2209.06794/) (2022)
- [Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models](https://mlsanity.com/paper/2303.04671/) (2023)
- [ViperGPT: Visual Inference via Python Execution for Reasoning](https://mlsanity.com/paper/2303.08128/) (2023)
- [Your Diffusion Model is Secretly a Zero-Shot Classifier](https://mlsanity.com/paper/2303.16203/) (2023)
- [Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action](https://mlsanity.com/paper/2312.17172/) (2023)
- [Generating Images with Multimodal Language Models](https://mlsanity.com/paper/2305.17216/) (2023)
- [StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners](https://mlsanity.com/paper/2306.00984/) (2023)
- [DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation](https://mlsanity.com/paper/2007.11301/) (2020)
- [StarVector: Generating Scalable Vector Graphics Code from Images and Text](https://mlsanity.com/paper/2312.11556/) (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)
- [LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer](https://mlsanity.com/paper/2502.01105/) (2025)
- [Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models](https://mlsanity.com/paper/2411.16602/) (2024)
- [CLIPVG: Text-Guided Image Manipulation Using Differentiable Vector Graphics](https://mlsanity.com/paper/2212.02122/) (2022)
- [I Spy a Metaphor: Large Language Models and Diffusion Models Co-Create Visual Metaphors](https://mlsanity.com/paper/2305.14724/) (2023)
- [Sketch-in-Latents: Eliciting Unified Reasoning in MLLMs](https://mlsanity.com/paper/2512.16584/) (2025)
- [AI Governance and Accountability: An Analysis of Anthropic's Claude](https://mlsanity.com/paper/2407.01557/) (2024)
- [ASCIIBench: Evaluating Language-Model-Based Understanding of Visually-Oriented Text](https://mlsanity.com/paper/2512.04125/) (2025)
- [SIGMA: Selective-Interleaved Generation with Multi-Attribute Tokens](https://mlsanity.com/paper/2602.07564/) (2026)
- [Evaluating Machine Learning Approaches for ASCII Art Generation](https://mlsanity.com/paper/2503.14375/) (2025)
- [How Large Language Models Need Symbolism](https://mlsanity.com/paper/2509.21404/) (2025)

## Built on by (most cited first, 2 of 2)

- [CANVAS: Consistency-Aware Navigation via Visual Adaptive Sampling for Long-Context Text-to-SVG Generation](https://mlsanity.com/paper/2608.30689/) (2026)
- [Autoregressive Mosaics: Probing 2D Spatial Reasoning in Text-Only Language Models](https://mlsanity.com/paper/2608.30751/) (2026)

## Abstract (arXiv)

Current multimodal approaches predominantly treat visual generation as an external process, relying on pixel rendering or code execution, thereby overlooking the native visual representation capabilities latent within Large Language Models (LLMs). In this work, we unlock this potential through ASCII art, a compact, efficient, and text-native visual format. We introduce SVE-ASCII, a unified framework designed to elicit and benchmark Symbolic Visual Expression directly within the pure text space. To address the scarcity of systematic resources, we construct ASCIIArt-7K, a high-quality dataset synthesized via a novel "Seed-and-Evolve" pipeline that augments human-curated anchors through in-context stylistic editing. We further implement a unified instruction-tuning strategy that jointly optimizes for both Generation (Text-to-ASCII) and Understanding (ASCII-to-Text). Crucially, our experiments reveal a critical phenomenon regarding task duality: while it is established that perception aids generation, we provide compelling evidence that generative training significantly enhances visual comprehension. This confirms a mutually reinforcing cycle in symbolic visual processing, a relationship previously hypothesized but rarely empirically demonstrated in the visual domain. We release our dataset, the ASCIIArt-Bench benchmark, and the SVE-ASCII model, establishing a robust baseline for native text-based visual intelligence.