Tabular foundation models excel on tiny- to medium-sized IID data but are outperformed by traditional tree-based and deep learning models on non-IID, large, and high-dimensional datasets, based on evaluations across 11 models and 142 datasets in the new BeyondArena benchmark.
Tactic for navigating the unknown: Tabular anomaly detection via in-context inference.arXiv preprint arXiv:2603.14171, 2026
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A task-agnostic encoder with task-specific decoders enables in-context learning across classification, regression, anomaly detection, clustering, entity matching, and entity classification on tabular data, achieving SOTA on several tasks.
citing papers explorer
-
Beyond IID: How General Are Tabular Foundation Models, Really?
Tabular foundation models excel on tiny- to medium-sized IID data but are outperformed by traditional tree-based and deep learning models on non-IID, large, and high-dimensional datasets, based on evaluations across 11 models and 142 datasets in the new BeyondArena benchmark.
-
FlexTab: A Flexible Encoder-Decoder Architecture for In-Context Learning Across Diverse Tabular Tasks
A task-agnostic encoder with task-specific decoders enables in-context learning across classification, regression, anomaly detection, clustering, entity matching, and entity classification on tabular data, achieving SOTA on several tasks.