aiqbench analysis
The paper proposes a shared encoder with task-specific decoders for in-context learning on tables, aiming for one backbone across classification, regression, anomaly detection, and retrieval. Its claims of state-of-the-art results are benchmark-based and self-reported, so readers should check the evaluation setup and baselines before drawing conclusions. The public code and checkpoints make it straightforward to test whether the target-agnostic embeddings hold up outside the paper's reported tasks.
FlexTab: A Flexible Encoder-Decoder Architecture for In-Context Learning Across Diverse Tabular Tasks
arXiv:2606.30336v3 Announce Type: replace 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 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 seven distinct problems: classification, regression, anomaly detection, clustering, entity matching, retrieval, and entity classification in relational databases. Both the encoder and the task-specific decoders are trained on tasks generated from a large corpus of real-world, unlabeled tables. FlexTab achieves state-of-the-art performance on classification, regression, anomaly detection, entity matching, and retrieval, 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 are publicly available at: https://github.com/SAP-samples/flextab .
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 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 seven distinct problems: classification, regression, anomaly detection, clustering, entity matching, retrieval, and entity classification in relational databases. Both the encoder and the task-specific decoders are trained on tasks generated from a large corpus of real-world, unlabeled tables. FlexTab achieves state-of-the-art performance on classification, regression, anomaly detection, entity matching, and retrieval, 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 are publicly available at: this https URL .
Machine Learning (cs.LG)
arXiv:2606.30336 [cs.LG]
(or arXiv:2606.30336v3 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2606.30336 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 259 words
Related coverage
ARC-Encoder: learning compressed text representations for large language models
arXiv · Jul 31, 2026
Complete Guide to Thinking Machines Inkling
Analytics Vidhya · Jul 20, 2026
Build a Physical AI model factory with NVIDIA Cosmos 3 on SageMaker HyperPod
AWS · Sep 4, 2026
NVIDIA Nemotron 3 Nano Omni Powers Multimodal Agent Reasoning in a Single Efficient Open Model
NVIDIA · Apr 28, 2026