Related papers: TabArena: A Living Benchmark for Machine Learning …

While traditional tree-based ensemble methods have long dominated tabular tasks, deep neural networks and emerging foundation models have challenged this primacy, yet no consensus exists on a universally superior paradigm. Existing…

Recent work on deep learning for tabular data demonstrates the strong performance of deep tabular models, often bridging the gap between gradient boosted decision trees and neural networks. Accuracy aside, a major advantage of neural models…

As AI agents expand into high-stakes domains like network system operations, evaluating their real-world reliability becomes increasingly critical. However, existing benchmarks risk contamination due to static design, show high statistical…

Building a deep research agent today is an exercise in glue code: the same backbone evaluated on the same benchmark can report different accuracies in different papers because harness and tool registry all differ, and integrating a new…

Tabular foundation models such as TabPFN have revolutionized predictive machine learning for tabular data. At the same time, the driving factors of this revolution are hard to understand. Existing open-source tabular foundation models are…

Deep learning (DL) models for tabular data problems (e.g. classification, regression) are currently receiving increasingly more attention from researchers. However, despite the recent efforts, the non-DL algorithms based on gradient-boosted…

Large language models (LLMs) are becoming increasingly capable mathematical collaborators, but static benchmarks are no longer sufficient for evaluating progress: they are often narrow in scope, quickly saturated, and rarely updated. This…

Foundation models for tabular data, like TabPFN, achieve strong performance on small datasets when pre-trained solely on synthetic data. We show that this performance can be significantly boosted by a targeted continued pre-training phase.…

We present SciArena, an open and collaborative platform for evaluating foundation models on scientific literature-grounded tasks. Unlike traditional benchmarks for scientific literature understanding and synthesis, SciArena engages the…

Foundation models for tabular data are rapidly evolving, with increasing interest in extending them to support additional modalities such as free-text features. However, existing benchmarks for tabular data rarely include textual columns,…

Tabular foundation models aim to learn universal representations of tabular data that transfer across tasks and domains, enabling applications such as table retrieval, semantic search and table-based prediction. Despite the growing number…

Survival analysis on tabular data is a well-studied problem. However, existing deep learning methods are often highly task-specific, which can limit the transfer of new approaches from other domains and introduce constraints that may affect…

Every year, millions of patients pass through emergency departments and intensive care units, where clinicians must make high-stakes decisions under time pressure and uncertainty. Machine learning could support prediction of deterioration,…

Hollmann et al. (Nature 637 (2025) 319-326) recently introduced TabPFN, a transformer-based deep learning model for regression and classification on tabular data, which they claim "outperforms all previous methods on datasets with up to…

This paper presents TableQuery, a novel tool for querying tabular data using deep learning models pre-trained to answer questions on free text. Existing deep learning methods for question answering on tabular data have various limitations,…

We present TableBank, a new image-based table detection and recognition dataset built with novel weak supervision from Word and Latex documents on the internet. Existing research for image-based table detection and recognition usually…

In practice, we are often faced with small-sized tabular data. However, current tabular benchmarks are not geared towards data-scarce applications, making it very difficult to derive meaningful conclusions from empirical comparisons. We…

We propose a novel high-performance and interpretable canonical deep tabular data learning architecture, TabNet. TabNet uses sequential attention to choose which features to reason from at each decision step, enabling interpretability and…

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 a supervised prediction target alone. While recent work on…

TabPFN has emerged as a promising in-context learning model for tabular data, capable of directly predicting the labels of test samples given labeled training examples. It has demonstrated competitive performance, particularly on…