# DiffMath: Symbol- and Graph-Aware Latent Diffusion Transformer for Handwritten Mathematical Expression Generation

arXiv: https://arxiv.org/abs/2606.19939 · HTML: https://mlsanity.com/paper/2606.19939/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 33 of its 54 references that are in the map.
- First posted on arXiv 18 Jun 2026.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 30 of 33)

- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [Generating Sequences With Recurrent Neural Networks](https://mlsanity.com/paper/1308.0850/) (2013)
- [Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models](https://mlsanity.com/paper/2501.01423/) (2025)
- [Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer](https://mlsanity.com/paper/2511.22699/) (2025)
- [ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text Generation](https://mlsanity.com/paper/2003.10557/) (2020)
- [Syntax-Aware Network for Handwritten Mathematical Expression Recognition](https://mlsanity.com/paper/2203.01601/) (2022)
- [Image Over Text: Transforming Formula Recognition Evaluation with Character Detection Matching](https://mlsanity.com/paper/2409.03643/) (2024)
- [Handwriting Transformers](https://mlsanity.com/paper/2104.03964/) (2021)
- [When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognition](https://mlsanity.com/paper/2207.11463/) (2022)
- [Disentangling Writer and Character Styles for Handwriting Generation](https://mlsanity.com/paper/2303.14736/) (2023)
- [Handwritten Mathematical Expression Recognition with Bidirectionally Trained Transformer](https://mlsanity.com/paper/2105.02412/) (2021)
- [Handwritten Text Generation from Visual Archetypes](https://mlsanity.com/paper/2303.15269/) (2023)
- [SLOGAN: Handwriting Style Synthesis for Arbitrary-Length and Out-of-Vocabulary Text](https://mlsanity.com/paper/2202.11456/) (2022)
- [Probing the Latent Hierarchical Structure of Data via Diffusion Models](https://mlsanity.com/paper/2410.13770/) (2024)
- [CoMER: Modeling Coverage for Transformer-based Handwritten Mathematical Expression Recognition](https://mlsanity.com/paper/2207.04410/) (2022)
- [MathWriting: A Dataset For Handwritten Mathematical Expression Recognition](https://mlsanity.com/paper/2404.10690/) (2024)
- [One-Shot Diffusion Mimicker for Handwritten Text Generation](https://mlsanity.com/paper/2409.04004/) (2024)
- [PosFormer: Recognizing Complex Handwritten Mathematical Expression with Position Forest Transformer](https://mlsanity.com/paper/2407.07764/) (2024)
- [DiffusionPen: Towards Controlling the Style of Handwritten Text Generation](https://mlsanity.com/paper/2409.06065/) (2024)
- [Zero-Shot Styled Text Image Generation, but Make It Autoregressive](https://mlsanity.com/paper/2503.17074/) (2025)
- [Beyond Isolated Words: Diffusion Brush for Handwritten Text-Line Generation](https://mlsanity.com/paper/2508.03256/) (2025)
- [TAMER: Tree-Aware Transformer for Handwritten Mathematical Expression Recognition](https://mlsanity.com/paper/2408.08578/) (2024)
- [Decoupling Layout from Glyph in Online Chinese Handwriting Generation](https://mlsanity.com/paper/2410.02309/) (2024)

## Abstract (arXiv)

Handwritten Mathematical Expression Generation (HMEG) is challenging due to the complex two-dimensional layouts and long-range structural dependencies of mathematical expressions. Existing methods typically rely on explicit spatial supervision, such as symbol-level bounding boxes, which incurs high annotation costs and limits scalability. In this work, we propose DiffMath, a symbol- and graph-aware latent diffusion framework that leverages the hierarchical structure inherent in LaTeX as a structural prior, eliminating the need for positional supervision. First, we design a Relational Abstract Syntax Tree (RelAST), a generation-oriented representation that distills MathML trees into compact triplet sequences [S, R, D], where each token directly encodes a symbol identity, spatial relation, or nesting depth. Second, we introduce MathVAE, which learns structure-preserving latent representations through symbol-aware and relation-aware perceptual regularization, ensuring that the latent space captures both character semantics and spatial topology. Third, MathDiT performs conditional denoising in this structured latent space, further guided by a global symbol-count prior via Adaptive Layer Normalization (AdaLN) to improve structural coherence. Experiments show that DiffMath produces structurally consistent handwritten expressions, achieves superior performance over existing methods, and improves the accuracy of downstream OCR models through synthetic data augmentation.