# TikZero: Zero-Shot Text-Guided Graphics Program Synthesis

arXiv: https://arxiv.org/abs/2503.11509 · HTML: https://mlsanity.com/paper/2503.11509/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 63 of its 94 references that are in the map.
- First posted on arXiv 14 Mar 2025.

## Builds on (most cited first, 30 of 63)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs](https://mlsanity.com/paper/2406.16860/) (2024)
- [CogView: Mastering Text-to-Image Generation via Transformers](https://mlsanity.com/paper/2105.13290/) (2021)
- [MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance](https://mlsanity.com/paper/1909.02622/) (2019)
- [LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment](https://mlsanity.com/paper/2310.01852/) (2023)
- [What matters when building vision-language models?](https://mlsanity.com/paper/2405.02246/) (2024)
- [CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers](https://mlsanity.com/paper/2204.14217/) (2022)
- [How is ChatGPT's behavior changing over time?](https://mlsanity.com/paper/2307.09009/) (2023)
- [UltraEdit: Instruction-based Fine-Grained Image Editing at Scale](https://mlsanity.com/paper/2407.05282/) (2024)
- [CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders](https://mlsanity.com/paper/2106.14843/) (2021)

## Built on by (most cited first, 24 of 24)

- [PaperBanana: Automating Academic Illustration for AI Scientists](https://mlsanity.com/paper/2601.23265/) (2026)
- [AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations](https://mlsanity.com/paper/2602.03828/) (2026)
- [VinciCoder: Unifying Multimodal Code Generation via Coarse-to-fine Visual Reinforcement Learning](https://mlsanity.com/paper/2511.00391/) (2025)
- [AutoFigure-Edit: Generating Editable Scientific Illustration](https://mlsanity.com/paper/2603.06674/) (2026)
- [TikZilla: Scaling Text-to-TikZ with High-Quality Data and Reinforcement Learning](https://mlsanity.com/paper/2603.03072/) (2026)
- [Automatic Method Illustration Generation for AI Scientific Papers via Drawing Middleware Creation, Evolution, and Orchestration](https://mlsanity.com/paper/2603.29590/) (2026)
- [PaperX: A Unified Framework for Multimodal Academic Presentation Generation with Scholar DAG](https://mlsanity.com/paper/2602.03866/) (2026)
- [Deltaynamics: Language-Based Representation for Inferring Rigid-Body Dynamics From Videos](https://mlsanity.com/paper/2605.20576/) (2026)
- [S1-Omni-Image: A Unified Model for Scientific Image Understanding, Generation, and Editing](https://mlsanity.com/paper/2606.24441/) (2026)
- [MultiMat: Multimodal Program Synthesis for Procedural Materials using Large Multimodal Models](https://mlsanity.com/paper/2509.22151/) (2025)
- [PRISM: A Benchmark for Programmatic Spatial-Temporal Reasoning](https://mlsanity.com/paper/2605.19382/) (2026)
- [Who Annotates in NLP? A Large-scale Assessment of Human Annotation Reporting between 2018 and 2025](https://mlsanity.com/paper/2606.02255/) (2026)
- [SciForma: Structure-Faithful Generation of Scientific Diagrams](https://mlsanity.com/paper/2607.18091/) (2026)
- [Edit2TikZ: A Comprehensive and Challenging Benchmark for Scientific Figure Editing with TikZ](https://mlsanity.com/paper/2608.13441/) (2026)
- [EdiTikZ: Scientific Figure Editing from Revision Trajectories](https://mlsanity.com/paper/2609.01409/) (2026)
- [Text to Automata Diagrams: Comparing TikZ Code Generation with Direct Image Synthesis](https://mlsanity.com/paper/2603.07936/) (2026)
- [CodeMMR: Bridging Natural Language, Code, and Image for Unified Retrieval](https://mlsanity.com/paper/2604.15663/) (2026)
- [Code as Representation: A Compilable Parsing Paradigm for Academic Documents](https://mlsanity.com/paper/2608.17550/) (2026)
- [PaperBanana-Interact: Scientific Diagram Refinement with Multi-Turn Human Feedback](https://mlsanity.com/paper/2608.30241/) (2026)
- [SciGen-Verifier: A Multimodal Reasoner for Explainable Verification in Scientific Image Generation](https://mlsanity.com/paper/2609.33399/) (2026)
- [Reinforcement Learning from Intermediate Renders for Image-to-Code Generation](https://mlsanity.com/paper/2609.34587/) (2026)
- [Zero-Shot Visualization: Exploring Text Corpora with User-Prompted Axes](https://mlsanity.com/paper/2610.06889/) (2026)
- [MathVis: Can AI Reason through Drawing? A Benchmark for Mathematical Figure Generation](https://mlsanity.com/paper/2610.12954/) (2026)
- [Learning after Execution with Action-Specific Credit](https://mlsanity.com/paper/2610.14573/) (2026)

## Abstract (arXiv)

Automatically synthesizing figures from text captions is a compelling capability. However, achieving high geometric precision and editability requires representing figures as graphics programs in languages like TikZ, and aligned training data (i.e., graphics programs with captions) remains scarce. Meanwhile, large amounts of unaligned graphics programs and captioned raster images are more readily available. We reconcile these disparate data sources by presenting TikZero, which decouples graphics program generation from text understanding by using image representations as an intermediary bridge. It enables independent training on graphics programs and captioned images and allows for zero-shot text-guided graphics program synthesis during inference. We show that our method substantially outperforms baselines that can only operate with caption-aligned graphics programs. Furthermore, when leveraging caption-aligned graphics programs as a complementary training signal, TikZero matches or exceeds the performance of much larger models, including commercial systems like GPT-4o. Our code, datasets, and select models are publicly available.