# CDMD: A Cross-Dataset Mixed-Type Diffusion Model for Tabular Data

arXiv: https://arxiv.org/abs/2609.39124 · HTML: https://mlsanity.com/paper/2609.39124/

## 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 31 of its 33 references that are in the map.
- First posted on arXiv 30 Sep 2026.

## Placed in

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

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [Simple and Effective Masked Diffusion Language Models](https://mlsanity.com/paper/2406.07524/) (2024)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second](https://mlsanity.com/paper/2207.01848/) (2022)
- [Deep Neural Networks and Tabular Data: A Survey](https://mlsanity.com/paper/2110.01889/) (2021)
- [TabDDPM: Modelling Tabular Data with Diffusion Models](https://mlsanity.com/paper/2209.15421/) (2022)
- [Language Models are Realistic Tabular Data Generators](https://mlsanity.com/paper/2210.06280/) (2022)
- [TabICL: A Tabular Foundation Model for In-Context Learning on Large Data](https://mlsanity.com/paper/2502.05564/) (2025)
- [How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models](https://mlsanity.com/paper/2102.08921/) (2021)
- [Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space](https://mlsanity.com/paper/2310.09656/) (2023)
- [Why Tabular Foundation Models Should Be a Research Priority](https://mlsanity.com/paper/2405.01147/) (2024)
- [LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence](https://mlsanity.com/paper/2509.03505/) (2025)
- [Synthcity: facilitating innovative use cases of synthetic data in different data modalities](https://mlsanity.com/paper/2301.07573/) (2023)
- [TabDiff: a Mixed-type Diffusion Model for Tabular Data Generation](https://mlsanity.com/paper/2410.20626/) (2024)
- [Making Pre-trained Language Models Great on Tabular Prediction](https://mlsanity.com/paper/2403.01841/) (2024)
- [Beyond Privacy: Navigating the Opportunities and Challenges of Synthetic Data](https://mlsanity.com/paper/2304.03722/) (2023)
- [TabPFGen -- Tabular Data Generation with TabPFN](https://mlsanity.com/paper/2406.05216/) (2024)
- [A Comprehensive Survey of Synthetic Tabular Data Generation](https://mlsanity.com/paper/2504.16506/) (2025)
- [Towards Cross-Table Masked Pretraining for Web Data Mining](https://mlsanity.com/paper/2307.04308/) (2023)
- [TabEBM: A Tabular Data Augmentation Method with Distinct Class-Specific Energy-Based Models](https://mlsanity.com/paper/2409.16118/) (2024)
- [A Survey on Deep Learning Approaches for Tabular Data Generation: Utility, Alignment, Fidelity, Privacy, Diversity, and Beyond](https://mlsanity.com/paper/2503.05954/) (2025)
- [CTSyn: A Foundation Model for Cross Tabular Data Generation](https://mlsanity.com/paper/2406.04619/) (2024)
- [LaTable: Towards Large Tabular Models](https://mlsanity.com/paper/2406.17673/) (2024)
- [TabFORGE: A Tabular Foundation Model for Generative Modelling](https://mlsanity.com/paper/2605.09424/) (2026)
- [TabDLM: Free-Form Tabular Data Generation via Joint Numerical-Language Diffusion](https://mlsanity.com/paper/2602.22586/) (2026)

## Abstract (arXiv)

Generative models for tabular data are typically trained separately for each dataset, limiting knowledge transfer and requiring the storage of many specialized models. In this paper, we introduce CDMD, a tabular diffusion model trained jointly across heterogeneous datasets with different schemas and variable numbers of numerical and categorical features. Unlike existing cross-dataset tabular diffusion models that operate in continuous representation spaces, CDMD defines diffusion directly over the mixed-type feature space and is trained end-to-end. To accommodate heterogeneous categorical domains, we introduce a schema-restricted reverse-process parameterization for masked diffusion models, in which the output space dynamically adapts to each feature's vocabulary. We then compose numerical and categorical feature-level diffusion processes into a schema-dependent row-level process. A shared schema-aware Transformer denoiser captures dependencies between features and parameterizes the reverse process across varying schemas. On seven real-world datasets, a single jointly trained CDMD achieves the highest average generation quality among strong single-dataset and cross-dataset baselines, while using substantially fewer total parameters than the collection of separately trained models. Furthermore, pre-training on a corpus of 337 datasets improves generation on previously unseen datasets under both limited target data and limited adaptation epochs. These results demonstrate the potential of direct mixed-type diffusion for shared and transferable tabular data generation. Our code is available at https://github.com/ketatam/cdmd.