metadata
license: bsd-3-clause
pipeline_tag: tabular-classification
TabICL: A Tabular Foundation Model for In-Context Learning on Large Data
TabICL is an in-context learning classification model designed for tabular data like TabPFN, but is pre-trained on much larger datasets (up to 60K samples) and can handle even larger datasets thanks to its memory-efficient inference code.
If you use TabICL for research purposes, please cite our paper.