tabular foundation models
PulseAugur coverage of tabular foundation models — every cluster mentioning tabular foundation models across labs, papers, and developer communities, ranked by signal.
- 2026-05-18 research_milestone A new paper details a method for distilling tabular foundation models for structured health data. source
5 day(s) with sentiment data
-
New attack reveals privacy risks in tabular foundation models
Researchers have identified significant privacy vulnerabilities in tabular foundation models, particularly within their attention layers. A new attack, AMIA, leverages transformer attention patterns to effectively perfo…
-
New CURE policy enhances tabular foundation models for stream learning
Researchers have developed a new context management policy called CURE for tabular foundation models (TFMs) operating on data streams. This policy addresses the challenge of maintaining an effective context for TFMs, wh…
-
Tabular foundation models improve flood depth prediction efficiency
Researchers have developed a novel method for predicting flood depths more efficiently and accurately. This approach utilizes a domain-aware coreset construction pipeline that conditions a tabular foundation model durin…
-
Tabular foundation models show promise for time-series prediction
Researchers are exploring the application of tabular foundation models (TFMs) to complex time-series prediction tasks, particularly in prognostics and health management (PHM) and survival analysis. These models, adapted…
-
New models and methods boost tabular foundation model efficiency
Researchers are developing new tabular foundation models (TFMs) to improve efficiency and performance. TabSwift enhances the TabPFN architecture with row-wise attention and learnable tokens for competitive accuracy and …
-
Tabular Foundation Models Show Performance-Uncertainty Trade-off
A new research paper highlights a critical trade-off in Tabular Foundation Models (TFMs), where high predictive performance comes at the cost of unreliable uncertainty quantification. The study, which compared TFMs agai…
-
New adapter enhances economic validity of tabular foundation models
Researchers have developed a novel two-stage adapter to improve the economic validity of tabular foundation models used for discrete choice prediction. These models, while accurate, often produce predictions that contra…
-
New LUCoS method improves tabular foundation model context selection
A new research paper introduces LUCoS, a method for unsupervised context selection in tabular foundation models. LUCoS addresses the challenge of selecting instances for labeling in low-label tabular learning by utilizi…
-
Tabular foundation models show promise for NIR chemical sensing calibration
Researchers have explored the use of tabular foundation models, specifically TabPFN, as a novel calibration strategy for near-infrared (NIR) chemical sensing. In a study involving 66 NIR datasets, TabPFN demonstrated st…
-
New studies probe tabular foundation model mechanisms and ensembling
Two new research papers delve into the intricacies of tabular foundation models (TFMs), exploring their performance and ensemble strategies. The first paper provides a mechanistic study, analyzing how different TFM arch…
-
Data sampling boosts TFM credit risk prediction performance
A new research paper explores how data presentation strategies significantly impact the performance of Tabular Foundation Models (TFMs) for credit risk prediction. The study found that resampling techniques, such as bal…
-
Distillation transfers TFM performance to faster, smaller health data models
Researchers have developed a method to distill knowledge from large, computationally expensive tabular foundation models (TFMs) into smaller, faster models for structured health data. This technique, tested across 19 he…
-
New benchmarks advance tabular ML for imbalanced, string, and multimodal data
Researchers have introduced new benchmarks to advance tabular machine learning. TILBench addresses imbalanced learning across diverse data characteristics, revealing that no single method is universally superior. STRABL…
-
SAP buys Prior Labs for $1.16B to boost AI data analysis
SAP has acquired Prior Labs, a startup focused on Tabular Foundation models, for $1.16 billion. This move aims to enhance SAP's structured data analysis capabilities and establish a European AI hub. The acquisition is a…
-
New framework uses privileged info to speed up tabular foundation models
Researchers have introduced PIQL, a novel framework designed to accelerate and enhance the learning capabilities of tabular foundation models (TFMs). PIQL integrates privileged information (PI), such as aggregate datase…
-
New adapter TFM-Retouche improves tabular foundation models without fine-tuning
Researchers have developed TFM-Retouche, a novel adapter designed to enhance tabular foundation models (TFMs) without requiring computationally expensive full fine-tuning. This lightweight, architecture-agnostic adapter…
-
Tabular foundation models show inference redundancy, synthetic data gap
Two new research papers explore the intricacies of tabular foundation models. One study investigates the inference dynamics within these models, revealing significant depthwise redundancy and proposing a more efficient …
-
AI model detects empathy from video with strong privacy protections
Researchers have developed a method called TFMPathy to detect empathy from video interactions while preserving user privacy. This approach uses summary statistics of temporal visual features, such as facial landmarks an…
-
RamanBench benchmark standardizes ML for spectroscopy
Researchers have introduced RamanBench, a comprehensive benchmark designed to standardize machine learning applications in Raman spectroscopy. This new benchmark integrates 74 datasets, totaling over 325,000 spectra, to…
-
Tabular foundation models enable real-time knowledge tracing with 53x speedup
Researchers have introduced a new approach to knowledge tracing called "live knowledge tracing," which utilizes tabular foundation models (TFMs) for real-time adaptation. This method bypasses traditional offline trainin…