5 papers · 1 filter
Statistically Indistinguishable, Operationally Distinct: A Formal Barrier for Tabular Foundation Models
Tassilo Klein, Johannes Hoffart
Tabular foundation models cannot reason about data produced by running systems without access to the rules that govern them. We make this statement falsifiable. The \emph{Operation…
Tabular Foundation Model for Generative Modelling
Xiangjian Jiang, Mingxuan Liu, Nikola Simidjievski +2
Generative modelling is a demanding test of foundation models, because it requires robust, holistic representation learning for a given data modality, rather than optimisation for…
Position: Foundation Models for Tabular Data within Systemic Contexts Need Grounding
Tassilo Klein, Johannes Hoffart
This position paper argues that foundation models for tabular data face inherent limitations when isolated from operational context - the procedural logic, declarative rules, and d…
SALT: Sales Autocompletion Linked Business Tables Dataset
Tassilo Klein, Clemens Biehl, Margarida Costa +3
Foundation models, particularly those that incorporate Transformer architectures, have demonstrated exceptional performance in domains such as natural language processing and image…
PORTAL: Scalable Tabular Foundation Models via Content-Specific Tokenization
Marco Spinaci, Marek Polewczyk, Johannes Hoffart +3
Self-supervised learning on tabular data seeks to apply advances from natural language and image domains to the diverse domain of tables. However, current techniques often struggle…