{"ID":5346756,"CreatedAt":"2026-06-30T04:09:55.830587294Z","UpdatedAt":"2026-07-02T14:12:34.668891255Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.30336","arxiv_id":"2606.30336","title":"FlexTab: A Flexible Encoder-Decoder Architecture for In-Context Learning Across Diverse Tabular Tasks","abstract":"We introduce FlexTab, a flexible encoder-decoder architecture for in-context learning on tabular data that pairs a single, task-agnostic encoder with a suite of task-specific decoders. Unlike existing tabular in-context learners, which entangle feature representations with a specific prediction target, our design produces \\textit{target-agnostic} row embeddings that can be leveraged across a wide range of downstream tasks within a table-native in-context learning setup. We demonstrate this flexibility on six distinct problems: classification, regression, anomaly detection, clustering, entity matching, and entity classification in relational databases. Both the encoder and the task-specific decoders are trained on a large corpus of real-world, unlabeled tables. FlexTab achieves state-of-the-art performance on classification, regression, anomaly detection and entity matching, while remaining competitive with specialized models on entity classification in a relational setting. These results demonstrate that a single shared encoder, paired with task-specific decoders, can serve as an effective general-purpose backbone for diverse tabular prediction problems. The inference code and checkpoints will be made publicly available at https://github.com/SAP-samples/flextab.","short_abstract":"We introduce FlexTab, a flexible encoder-decoder architecture for in-context learning on tabular data that pairs a single, task-agnostic encoder with a suite of task-specific decoders. Unlike existing tabular in-context learners, which entangle feature representations with a specific prediction target, our design produ...","url_abs":"https://arxiv.org/abs/2606.30336","url_pdf":"https://arxiv.org/pdf/2606.30336v1","authors":"[\"Marek Polewczyk\",\"Maximilian Schambach\",\"Marco Spinaci\",\"Sam Thelin\",\"Johannes Höhne\"]","published":"2026-06-29T14:14:34Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false,"code_links":[{"ID":613756,"CreatedAt":"2026-06-30T04:09:55.830587294Z","UpdatedAt":"2026-06-30T04:09:55.830587294Z","DeletedAt":null,"paper_id":5346756,"paper_url":"https://arxiv.org/abs/2606.30336","paper_title":"FlexTab: A Flexible Encoder-Decoder Architecture for In-Context Learning Across Diverse Tabular Tasks","repo_url":"https://github.com/SAP-samples/flextab","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}