tabular-data

This paper proposes the Multi-Branch Neural Decision Tree with Adaptive Pruning (MBNDT), a decision tree model that improves classification accuracy under depth constraints through adaptive multi-way splits, achieving superior performance on OpenML benchmarks.

Entropic Scree is a new diagnostic tool for assessing signal strength and structure in dirty tabular data using mutual information, with a preprint and upcoming Python and R packages.

This paper introduces ClusterAttention, a training-free method to speed up bidirectional attention in transformers by using recursive clustering for block-sparse attention, achieving 2-6x speedups on tabular data and 1.8x on video generation while maintaining high accuracy.

This paper evaluates self-supervised pretraining for tabular models under label scarcity and missing data, finding mixed efficacy but reliable improvements under test-time missingness.

Tydra is a hybrid Transformer-SSM architecture for tabular data that reduces inference time by 30% compared to TabPFN while maintaining similar predictive performance and outperforming Hydra.

This paper investigates unsupervised anomaly detection using flow matching on tabular data, focusing on contaminated training sets and comparing different scoring methods for robustness.

The paper proposes LLM-Detector, a framework that uses large language models with in-context learning to perform tabular anomaly detection without fine-tuning, demonstrating consistent improvements over existing methods on multiple datasets.

The Entropic Scree is an information-theoretic upgrade to PCA for robust rank estimation and dimensionality reduction on messy tabular data, with open-sourced code and a preprint released.

The Entropic Scree is a non-parametric, information-theoretic diagnostic framework that maps intrinsic rank and informational gravity in complex tabular data, addressing limitations of standard PCA and other baselines.

This paper proposes FairTFM, a training strategy to incorporate fairness constraints into tabular foundation models, enabling fair predictions via in-context learning without task-specific retraining.

This paper revisits energy-based models for tabular anomaly detection, demonstrating that combining Deep Boltzmann Machine energy scores with autoencoder reconstruction scores significantly improves performance on benchmark datasets.

CoMedBench is a reproducible benchmark evaluating synthetic medical data generators across 37 dataset-task pairs, showing that synthetic training data preserves most downstream signal on tabular tasks but temporal ICU tasks remain generator-sensitive.

This paper identifies common failure modes in tree-search-based autoresearch agents applied to tabular datasets, such as repeated bug resolution, poor hyperparameter tuning, and ineffective exploration, and proposes targeted interventions like a global debug consultant and refined tree-search algorithms to recover wasted compute and improve performance without changing the underlying language model.

TailBooster is a dual-layer generative framework that synthesizes operationally valid extreme air-transport events using statistical tail extraction and autoencoder-based cleaning, significantly improving extreme-event prediction accuracy.

This paper introduces GRACE, a framework that uses LLM-generated semantic descriptions at the attribute-value level to create unified metric spaces for clustering mixed tabular data, achieving scalability comparable to statistical baselines while improving clustering accuracy.

The paper proposes BC-ICL, a bootstrap-conditioned action selection method that leverages pretrained tabular foundation models with in-context learning for contextual bandits, improving exploration and regret performance under strict online protocols.

This paper systematically evaluates 15 machine learning models, including the TabPFN foundation model, for post-wildfire debris-flow prediction using USGS basin-scale data, finding TabPFN achieves the best performance (threat score 0.637) and that synthetic data augmentation improves most models.

This paper introduces TS2TabPFN, a framework that combines explicit feature extraction with the TabPFN 2.5 tabular foundation model for time series classification and extrinsic regression. Experiments show it outperforms state-of-the-art models in TSER and achieves competitive results in TSC.

This tweet highlights the new DataSpace benchmark for data agents, showing that harness choice significantly impacts accuracy across multimodal models and agent harnesses, with the best accuracy reaching 66.34% and the benchmark remaining unsaturated.

A new arXiv paper systematically tests five hypotheses for why large language models fail at tabular prediction, finding that dimensionality is the decisive factor: LLM accuracy degrades as input dimension grows, unlike classical baselines that stay flat or improve.