arXiv:2603. 10582v2 Announce Type: replace Abstract: Ensembling is commonly used in machine learning on tabular data to boost predictive performance and robustness, but larger ensembles often lead to increased hardware demand.
arXiv:2607. 05380v1 Announce Type: new Abstract: In deep learning for tabular data, efficient ensembles of multilayer perceptrons (MLPs) have recently emerged as effective and practical architectures.
arXiv:2607. 10077v1 Announce Type: new Abstract: Tabular learning is still dominated by gradient-boosted decision trees (GBDTs), while recent deep learning approaches have become increasingly competitive.
TabICLv2 is a new state‑of‑the‑art tabular foundation model that outperforms existing methods on regression and classification tasks. It relies on a synthetic data generation engine for diverse pretraining, architectural innovations such as a scalable softmax attention, and optimized training protocols that replace AdamW with the Muon optimizer. On the TabArena and TALENT benchmarks, TabICLv2 surpasses the current best model, RealTabPFN‑2.5, without any tuning, while also being faster and capable of handling million‑scale datasets with limited GPU memory.
arXiv:2608. 12989v1 Announce Type: new Abstract: Pretrained tabular foundation models have demonstrated strong predictive capability; however, their application to large-scale datasets remains constrained by the limited inference context.
The paper surveys tabular imbalanced learning and introduces TILBench, a benchmark evaluating over 40 methods on 57 datasets. It presents a unified taxonomy of approaches and shows that no single method dominates across all settings, with performance depending on dataset regimes and computational constraints. Practical recommendations for method selection and future research directions are provided.
arXiv:2601.13111v3 Announce Type: replace-cross Abstract: Realistic text-to-SQL workflows often require joining multiple tables. As a result, accurately retrieving the relevant set of tables becomes...
arXiv:2606. 02384v1 Announce Type: new Abstract: Progress in tabular machine learning has largely focused on increasingly sophisticated model architectures.
arXiv:2606. 09323v1 Announce Type: new Abstract: Tabular encoders are usually evaluated inside task-specific end-to-end pipelines, so models from different training paradigms are difficult to compare directly even when they operate on similar tabular signals.
arXiv:2606. 02106v1 Announce Type: new Abstract: We present a single classification pipeline that combines an Equiangular Tight Frame (ETF) preprocessing stage with a tabular foundation model for in-context inference, applied identically across modalities once data is mapped to fixed vector representations.
arXiv:2606. 30410v1 Announce Type: cross Abstract: Foundation models for predictive machine learning on tabular data have recently gained significant traction in academia and industry.
MetaSE is an active ensemble framework that selects a small set of reliable models for mobile sensing tasks, reducing computational cost while maintaining accuracy. It leverages short-term persistence in model reliability, uses post-execution evidence to prune unreliable members, and only triggers lightweight routing when replacements are needed. Experiments on four human activity recognition datasets and four model architectures show MetaSE outperforms a fixed three-model ensemble and matches the accuracy of more expensive adaptive and full-ensemble approaches, achieving 2.7× speedup and 69% memory savings on a Raspberry Pi 4B.
arXiv:2608. 01090v1 Announce Type: new Abstract: Spiking Neural Networks (SNNs) are attractive for resource-constrained remote-sensing systems, but reliable out-of-distribution (OOD) detection remains challenging.