Happy to share that our paper on Diffusion Models for Synthetic Tabular Data Generation is published and available online! 🥳 Elina Telesheva is the first author and our former student. The paper is based on her master's thesis. Congrats, Elina! 👏 Generating high-quality synthetic data is crucial for many data science tasks. However, tabular data is particularly challenging because it contains both numerical and categorical features. In this paper, we investigate modern approaches for tabular data generation. We evaluate several modifications of a state-of-the-art model and examine how they affect the quality of synthesized datasets. Comprehensive experiments on five publicly available datasets show that our proposed model retains the quality of the original model while requiring less time to generate synthetic samples. To cite this article: Telesheva, E., Hushchyn, M. Diffusion Models for Synthetic Tabular Data Generation. Dokl. Math. 112, 581–591 (2025). https://doi.org/10.1134/S1064562425700553