The ability to train generative models that produce realistic, safe and useful tabular data is essential for data privacy, imputation, oversampling, explainability or simulation. However, generating tabular data is not straightforward due to its heterogeneity, non-smooth distributions, complex dependencies and imbalanced categorical features. Although diverse methods have been proposed in the literature, there is a need for a unified evaluation, under the same conditions, on a variety of datasets. This study addresses this need by fully considering the optimization of: hyperparameters, feature encodings, and architectures. We investigate the impact of dataset-specific tuning on five recent model families for tabular data generation through an extensive benchmark on 16 datasets. These datasets vary in terms of size (an average of 80,000 rows), data types, and domains. We also propose a reduced search space for each model that allows for quick optimization, achieving nearly equivalent performance at a significantly lower cost. Our benchmark demonstrates that, for most models, large-scale dataset-specific tuning substantially improves performance compared to the original configurations. Furthermore, we confirm that diffusion-based models generally outperform other models on tabular data. However, this advantage is not significant when the entire tuning and training process is restricted to the same GPU budget.
MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image
Technion – Israel Institute of Technology（技术ion – 以色列理工学院）；Prior Labs（Prior实验室）；NVIDIA；SODA Team, INRIA Saclay, Palaiseau（SODA团队，INRIA萨克莱，帕莱索）；University of Freiburg（弗赖堡大学）；Probabl；ELLIS Institute Tübingen（图宾根ELLIS研究所）
TFMPathy: Tabular Foundation Model for Privacy-Aware, Generalisable Empathy Detection from Videos
School of Electrical Engineering, Computing and Mathematical Sciences, Curtin University（Curtin大学电气工程、计算与数学科学学院）；The Australian National University（澳大利亚国立大学）；North South University（北南大学）；University of ÓBuda（奥布达大学）
XGenBoost: Synthesizing Small and Large Tabular Datasets with XGBoost
Public Health \& Primary Care, Leiden University Medical Center, Leiden, The Netherlands；Research；Development, Statistics Netherlands (CBS), The Hague, The Netherlands；Leiden Institute of Advanced Computer Science, Leiden University, Leiden, The Netherlands
MediTab: Scaling Medical Tabular Data Predictors via Data Consolidation, Enrichment, and Refinement
GE Healthcare（GE医疗）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Carle Illinois College of Medicine, University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校卡尔伊利诺伊医学院）
Tabular foundation model for GEOAI benchmark problems BM/AirportSoilProperties/2/2025
Department of Civil and Environmental Engineering, Tohoku University（土屋大学土木环境工程系）；Research Organization of Information and Systems, The Institute of Statistical Mathematics（信息与系统研究所，统计数学研究所）；The Graduate University for Advanced Studies, Department of Statistical Science（高级研究大学，统计科学系）
Causal Data Augmentation for Robust Fine-Tuning of Tabular Foundation Models
Department of Computer Science University of Freiburg（计算机科学系弗赖堡大学）；University of Freiburg（弗赖堡大学）；Prior Labs ELLIS Institute Tübingen University of Freiburg（Prior实验室ELLIS研究所弗赖堡大学）
KnowsTFM: Knowledge-Informed Fine-Tuning of Small Tabular Foundation Models
Jožef Stefan Institute and Postgraduate School（乔塞夫·斯蒂芬研究所和研究生学院）；Department of Computer Science and Technology, University of Cambridge, UK（剑桥大学计算机科学与技术系）；Télécom Paris, Institut Polytechnique de Paris, FR（巴黎电信学院，巴黎理工学院）
Data-efficient flood depth prediction through domain-aware coreset selection and tabular foundation models
Urban Resilience.AI Lab（Urban Resilience.AI实验室）；Zachry Department of Civil and Environmental Engineering, Texas A&M University（Zachry土木与环境工程系，德克萨斯A&M大学）；Department of Computer Science and Engineering, Texas A&M University（计算机科学与工程系，德克萨斯A&M大学）；Resilitix Intelligence LLC；Institute for a Disaster Resilient Texas, Texas A&M University（德克萨斯灾难韧性研究所，德克萨斯A&M大学）
LAIR-Net: Leaky Alignment-Impulse Residual Networks for Tabular Regression
Indian Institute of Technology Guwahati（印度技术学院加瓦哈蒂分校）；SAFIR, Sorbonne University Abu Dhabi（阿布扎比索邦大学 SAFIR）；Indian Institute of Technology Bombay（印度技术学院孟买分校）
ZEUS: Zero-shot Embeddings for Unsupervised Separation of Tabular Data
Faculty of Mathematics and Computer Science, Jagiellonian University（数学与计算机科学学院，杰团大学）；Doctoral School of Exact and Natural Sciences, Jagiellonian University（精确与自然科学博士学院，杰团大学）
Rethinking Pre-Training in Tabular Data: A Neighborhood Embedding Perspective
School of Artificial Intelligence, Nanjing University（南京大学人工智能学院）；The Ohio State University（俄亥俄州立大学）；China National Key Laboratory for Novel Software Technology（计算机软件新技术国家重点实验室）
School of Artificial Intelligence, Jilin University（吉林大学人工智能学院）；CSIRO’s Data61（CSIRO数据61）；Monash University（墨尔本大学）；International Center of Future Science, Jilin University（吉林大学未来科学国际中心）；Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, MOE, China（知识驱动人机智能工程研究中心，教育部，中国）
Multitask-Informed Prior for In-Context Learning on Tabular Data: Application to Steel Property Prediction
Dep. of Electrical and Computer Engineering, McGill University（麦吉尔大学电气与计算机工程系）；Mila – Québec AI Institute（魁北克AI研究所）；Dep. of Mining and Materials Engineering, McGill University（麦吉尔大学采矿与材料工程系）；Algoma Steel Inc.（阿尔戈马钢铁公司）
On the Uncertainty Quantification Ability of Tabular Foundation Models
Department of Mechanical and Aerospace Engineering, University of California, Irvine（加州大学欧文分校机械与航空航天工程系）；Department of Civil and Environmental Engineering, University of California, Irvine（加州大学欧文分校土木与环境工程系）
