Neural sequence models based on the transformer architecture have demonstrated
remarkable\emph {in-context learning}(ICL) abilities, where they can perform new tasks …

Tabular data is one of the most commonly used types of data in machine learning. Despite
recent advances in neural nets (NNs) for tabular data, there is still an active discussion on …

The vast majority of time-series forecasting approaches require a substantial training
dataset. However, many real-life forecasting applications have very little initial observations …

Tabular data, spreadsheets organized in rows and columns, are ubiquitous across scientific
fields, from biomedicine to particle physics to economics and climate science,. The …

While tabular classification has traditionally relied on from-scratch training, a recent
breakthrough called prior-data fitted networks (PFNs) challenges this approach. Similar to …

Intelligent fault detection and classification is a cornerstone of prognostic and health
management of rotating machinery (RM) research. Correctly classifying and predicting RM …

Abstract The recently developed Prior-Data Fitted Networks (PFNs) have shown very
promising results for applications in low-data regimes. The TabPFN model, a special case of …

In engineering design, navigating complex decision-making landscapes demands a
thorough exploration of the design, performance, and constraint spaces, often impeded by …

Recent foundational models for tabular data, such as TabPFN, have demonstrated
remarkable effectiveness in adapting to new tasks through in-context learning. However …

TabPFN [Hollmann et al., 2023], a Transformer model pretrained to perform in-context
learning on fresh tabular classification problems, was presented at the last ICLR conference …