TabPFN-2.5
PulseAugur coverage of TabPFN-2.5 — every cluster mentioning TabPFN-2.5 across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Tabular foundation models show profit advantage over tuned GBDTs for telecom churn
A new evaluation of tabular foundation models (TFMs) suggests they can outperform tuned gradient boosting models (GBDTs) in predicting customer churn for telecommunications companies. The study re-examined several TFMs,…
-
New foundation models and benchmarks advance tabular data generation and analysis
Researchers have introduced several new foundation models and techniques for tabular data generation and analysis. TabFORGE, TabMosaic, and TabGift are new models designed for generating high-quality synthetic tabular d…
-
New TS2TabPFN framework advances time series analysis using foundation models
Researchers have introduced TS2TabPFN, a novel framework designed to enhance time series classification (TSC) and extrinsic regression (TSER) tasks. This approach bridges the gap between traditional feature engineering …
-
TS2TabPFN framework combines feature extraction with foundation model for time series tasks
Researchers have introduced TS2TabPFN, a novel framework designed to enhance time series classification (TSC) and extrinsic regression (TSER) tasks. This approach integrates explicit feature extraction with TabPFN 2.5, …
-
Relational Transformer outperforms other deep learning models for databases
A new benchmarking study has evaluated deep learning models for relational databases, finding that the Relational Transformer (RT) approach generally outperforms other methods. The research systematically compared RT ag…
-
TabPFN-3 advances tabular data prediction with speed and scale
A new technical report introduces TabPFN-3, an advanced foundation model for tabular data that significantly enhances performance and speed. This model scales to datasets with up to 1 million training rows and offers su…
-
TabPFN-3 model boosts tabular data prediction and speed
A new technical report introduces TabPFN-3, an advanced foundation model for tabular data that significantly enhances performance and speed. This model scales to datasets with up to 1 million training rows and reduces t…