# Generating Benchmark Health Data Using a Tabular Diffusion Transformer

arXiv: https://arxiv.org/abs/2608.14496 · HTML: https://mlsanity.com/paper/2608.14496/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Flow matching, time series and science, one of 14 directions in Diffusion models.
- Builds on 23 of its 42 references that are in the map.
- First posted on arXiv 14 Aug 2026.

## Placed in

- Diffusion models / [Flow matching, time series and science](https://mlsanity.com/diffusion/flow-matching-time-series-and-science/)

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [OpenML: networked science in machine learning](https://mlsanity.com/paper/1407.7722/) (2014)
- [TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data](https://mlsanity.com/paper/2005.08314/) (2020)
- [TabDDPM: Modelling Tabular Data with Diffusion Models](https://mlsanity.com/paper/2209.15421/) (2022)
- [Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space](https://mlsanity.com/paper/2310.09656/) (2023)
- [PMLB: A Large Benchmark Suite for Machine Learning Evaluation and Comparison](https://mlsanity.com/paper/1703.00512/) (2017)
- [Why Tabular Foundation Models Should Be a Research Priority](https://mlsanity.com/paper/2405.01147/) (2024)
- [Reduced, Reused and Recycled: The Life of a Dataset in Machine Learning Research](https://mlsanity.com/paper/2112.01716/) (2021)
- [XTab: Cross-table Pretraining for Tabular Transformers](https://mlsanity.com/paper/2305.06090/) (2023)
- [Scientific Machine Learning Benchmarks](https://mlsanity.com/paper/2110.12773/) (2021)
- [Adversarial random forests for density estimation and generative modeling](https://mlsanity.com/paper/2205.09435/) (2022)
- [Of Quantiles and Expectiles: Consistent Scoring Functions, Choquet Representations, and Forecast Rankings](https://mlsanity.com/paper/1503.08195/) (2015)
- [Towards Cross-Table Masked Pretraining for Web Data Mining](https://mlsanity.com/paper/2307.04308/) (2023)
- [CTSyn: A Foundation Model for Cross Tabular Data Generation](https://mlsanity.com/paper/2406.04619/) (2024)
- [Robust Variational Autoencoder for Tabular Data with Beta Divergence](https://mlsanity.com/paper/2006.08204/) (2020)
- [A Consensus Privacy Metrics Framework for Synthetic Data](https://mlsanity.com/paper/2503.04980/) (2025)
- [Generative and reproducible benchmarks for comprehensive evaluation of machine learning classifiers](https://mlsanity.com/paper/2107.06475/) (2021)

## Abstract (arXiv)

Cross-Tabular Data Generation (CTDG) seeks to learn a generative model from multiple heterogeneous tables and produce new synthetic tabular datasets. However, existing synthetic tabular data generation methods are largely restricted to single-input-table scenarios and struggle to effectively handle multiple heterogeneous tables with diverse feature sets. To address this limitation, we propose a two-stage framework for cross-tabular data generation. In the first stage, each heterogeneous raw table is transformed into a standardized statistical table with the same set of columns across all tables. Each statistical table captures the marginal distributions of the original columns and the pairwise correlations among them. In the second stage, a diffusion transformer model is trained to capture structural patterns across these homogeneous statistical tables and to generate synthetic statistical tables. Synthetic raw tables are subsequently reconstructed from the generated statistical tables via multivariate Gaussian sampling followed by an inverse probability integral transform. This two-stage CTDG framework enables the learning of a unified generative model from multiple heterogeneous tables and supports the generation of an unlimited number of realistic synthetic heterogeneous tables. Experimental results demonstrate high fidelity in the learned statistical representations and a favorable fidelity-diversity trade-off in the generated synthetic data, validating the effectiveness of the proposed approach.