Model Releases
Towards Universal Tabular Embeddings: A Benchmark Across Data Tasks
arXiv:2604.21696v1 Announce Type: new Abstract: Tabular foundation models aim to learn universal representations of tabular data that transfer across tasks and domains, enabling applications such as t
arXiv:2604.21696v1 Announce Type: new Abstract: Tabular foundation models aim to learn universal representations of tabular data that transfer across tasks and domains, enabling applications such as table retrieval, semantic search and table-based prediction. Despite the growing number of such models, it remains unclear which approach works best in practice, as existing methods are often evaluated under task-specific settings that make direct comparison difficult. To address this, we introduce TEmBed, the Tabular Embedding Test Bed, a comprehensive benchmark for systematically evaluating tabular embeddings across four representation levels: cell, row, column, and table. Evaluating a diverse set of tabular representation learning models, we show that which model to use depends on the task and representation level. Our results offer practical guidance for selecting tabular embeddings in real-world applications and lay the groundwork for developing more general-purpose tabular representation models.
Related
- PiCa: Parameter-Efficient Fine-Tuning with Column Space Projection
- Auto-FP: An Experimental Study of Automated Feature Preprocessing for Tabular Data
- Synthetic Tabular Generators Fail to Preserve Behavioral Fraud Patterns: A Benchmark on Temporal, Velocity, and Multi-Account Signals
- Fine-tuning Factor Augmented Neural Lasso for Heterogeneous Environments
Source: arXiv cs.LG | 2026-04-24