Özer Cem KELAHMETKELAHMET
Glossary · Deep learning

What is TabICL? Definition and meaning

A tabular foundation model that adds column-then-row attention to scale in-context learning to bigger datasets.

Definition

TabICL: A tabular foundation model that adds column-then-row attention to scale in-context learning to bigger datasets.

In short: In-context learning for larger tables.

When it is used

Prediction on tables too large for the first generation of in-context models.

Where it fits

TabICL belongs to Large tabular foundation models in the Deep learning topic. These are the other terms in the same group:

  • Tabular foundation models: A large neural network pretrained across many tables so it can predict, impute or score new tables with little or no task-specific training.
  • In-context learning: The ability of a trained model to perform a new task from examples or instructions in its input, without changing its weights.
  • TabPFN: A transformer pre-trained on synthetic datasets that predicts in a single forward pass with in-context learning.
  • TabSTAR: A tabular model that reads textual features through a pretrained language encoder together with numbers.
  • XTab: A framework that pre-trains shared transformer layers across many tables with table-specific embeddings.
  • SAINT: A transformer that attends across features and across rows, with contrastive pre-training.
  • FT-Transformer: Turns each feature into an embedding and processes them with a transformer.
  • TabNet: A deep model that selects features step by step with sequential attention.
  • Masked cell modeling: The tabular counterpart of masked language modelling: random cells are masked and the model reconstructs them.
  • Imputation networks: Models trained to predict missing cells from the observed cells of the same row and table.

Learn more

The full guide to TabICL explains how it works, when to use it and how it compares with the alternatives, with examples. The glossary lists every term on the site from A to Z.

Previous term: t-SNE · Next term: TabNet

Last updated Nov 18, 2026
Type to search.
    ↑↓ navigate↵ open