PriorLabs/TabPFN
Summary
TabPFN is introduced as a foundation model specifically designed for tabular data by PriorLabs.
Similar Articles
TabPFN-3: Technical Report
TabPFN-3 is a new foundation model for tabular data, pretrained on synthetic data, that scales to 1M training rows while reducing training and inference time, achieving state-of-the-art performance on tabular prediction, time series, and relational data.
TabPFN-3 just released: a pre-trained tabular foundation model for up to 1M rows [R][N]
TabPFN-3, a pre-trained tabular foundation model, was released with support for up to 1 million rows on a single GPU, 10x-1000x faster inference, and a 93% win rate over classical ML in benchmarks.
GOTabPFN: From Feature Ordering to Compact Tokenization for Tabular Foundation Models on High-Dimensional Data
This paper introduces GOTabPFN, a method that combines Graph-guided Ordering with Local Refinement (GO-LR) and Neuro-Inspired Subunit Compression (NSC) to make small tabular foundation models effective for high-dimensional, low-sample-size prediction without retraining large backbones.
When Tabular Foundation Models Meet Strategic Tabular Data: A Prior Alignment Approach
This paper studies whether tabular foundation models based on pretrained prior-data fitted networks (PFNs) can generalize to strategic tabular data where individuals modify features after deployment. It proposes Strategic Prior-data Fitted Network (SPN), an inference-time framework that aligns PFN predictions with the post-manipulation distribution without retraining.
TabPFN-MT: A Natively Multitask In-Context Learner for Tabular Data
TabPFN-MT extends PFNs to multitask in-context learning for tabular data, achieving state-of-the-art on small-to-medium datasets while reducing inference cost from O(T) to O(1) forward passes.