TabArena launches a dynamic, updatable benchmarking system for tabular ML that shows boosted trees remain competitive, deep learning matches them under larger budgets with ensembling, foundation models excel on small data, and cross-model ensembles advance SOTA while flagging validation overfitting.
ArXiv preprint , volume =
12 Pith papers cite this work, alongside 2 external citations. Polarity classification is still indexing.
12
Pith papers citing it
2
external citations · external index
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
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.
Theoretical characterization of the inlier-memorization effect in simple autoencoders, deriving its emergence, strength, and persistence from data distribution and initialization, plus guidelines achieving SOTA on ADBench.
TabPFN-MT is a multitask in-context learner for tabular data that sets a new state-of-the-art on deep multitask learning for datasets under 1000 samples while reducing inference cost from O(T) to O(1) passes.
Tabular foundation models suffer from test-time adversarial vulnerabilities that degrade accuracy and enable transferable attacks, but incremental adversarial in-context learning improves robustness on multiple benchmarks.
POLAR uses pretrained predictive foundation models as fixed belief-state encoders and trains only a lightweight policy head on top for amortised Bayesian experimental design, optimisation, and active learning.
CRUMB speeds up PFN inference on large tabular datasets by clustering queries and selecting MMD-matched context subsets, outperforming prior selection methods on the 51-dataset TabArena benchmark across three architectures while handling covariate drift.
Tabular foundation models, used zero-shot, match or beat tuned gradient boosting on average in credit PD and LGD benchmarks, with a larger edge on small datasets.
SQuARE is a hybrid retrieval system that uses a complexity score to route tabular queries between chunk-based and SQL-based paths, outperforming single-strategy baselines and GPT-4o on precision and accuracy for complex spreadsheets.
CoMET achieves strong multimodal classification performance by composing frozen modality encoders, PCA compression, and tabular foundation models without any training, reaching state-of-the-art on diverse benchmarks including large-scale hierarchical tasks.
TabPFNv2.5 delivers 40x faster inference than Random Forest at 97% binary accuracy on TON IoT data, enabling a hybrid pipeline for real-time IoT threat screening in smart cities.
TabPFN maintains high ROC-AUC and structured attention under controlled additions of irrelevant features, nonlinear correlations, and mislabeled targets in binary classification.
citing papers explorer
-
TabArena: A Living Benchmark for Machine Learning on Tabular Data
TabArena launches a dynamic, updatable benchmarking system for tabular ML that shows boosted trees remain competitive, deep learning matches them under larger budgets with ensembling, foundation models excel on small data, and cross-model ensembles advance SOTA while flagging validation overfitting.
-
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.
-
What Drives the Inlier-Memorization Effect? A Theory of Outlier Detection via Early Training Dynamics
Theoretical characterization of the inlier-memorization effect in simple autoencoders, deriving its emergence, strength, and persistence from data distribution and initialization, plus guidelines achieving SOTA on ADBench.
-
TabPFN-MT: A Natively Multitask In-Context Learner for Tabular Data
TabPFN-MT is a multitask in-context learner for tabular data that sets a new state-of-the-art on deep multitask learning for datasets under 1000 samples while reducing inference cost from O(T) to O(1) passes.
-
On the Robustness of Tabular Foundation Models: Test-Time Attacks and In-Context Defenses
Tabular foundation models suffer from test-time adversarial vulnerabilities that degrade accuracy and enable transferable attacks, but incremental adversarial in-context learning improves robustness on multiple benchmarks.
-
Efficient Adaptive Data Acquisition via Pretrained Belief Representations
POLAR uses pretrained predictive foundation models as fixed belief-state encoders and trains only a lightweight policy head on top for amortised Bayesian experimental design, optimisation, and active learning.
-
CRUMB: Efficient Prior Fitted Network Inference via Distributionally Matched Context Batching
CRUMB speeds up PFN inference on large tabular datasets by clustering queries and selecting MMD-matched context subsets, outperforming prior selection methods on the 51-dataset TabArena benchmark across three architectures while handling covariate drift.
-
Foundation Models for Credit Risk Prediction: A Game Changer?
Tabular foundation models, used zero-shot, match or beat tuned gradient boosting on average in credit PD and LGD benchmarks, with a larger edge on small datasets.
-
SQuARE: Structured Query & Adaptive Retrieval Engine For Tabular Formats
SQuARE is a hybrid retrieval system that uses a complexity score to route tabular queries between chunk-based and SQL-based paths, outperforming single-strategy baselines and GPT-4o on precision and accuracy for complex spreadsheets.
-
Modular Multimodal Classification Without Fine-Tuning: A Simple Compositional Approach
CoMET achieves strong multimodal classification performance by composing frozen modality encoders, PCA compression, and tabular foundation models without any training, reaching state-of-the-art on diverse benchmarks including large-scale hierarchical tasks.
-
Optimizing IoT Intrusion Detection with Tabular Foundation Models for Smart City Forensics
TabPFNv2.5 delivers 40x faster inference than Random Forest at 97% binary accuracy on TON IoT data, enabling a hybrid pipeline for real-time IoT threat screening in smart cities.
-
Noise Immunity in In-Context Tabular Learning: An Empirical Robustness Analysis of TabPFN's Attention Mechanisms
TabPFN maintains high ROC-AUC and structured attention under controlled additions of irrelevant features, nonlinear correlations, and mislabeled targets in binary classification.