arXiv AI June 11, 2026 By Jamie Heredge, Mattia J. Villani, Pranav Deshpande, Akshay Seshadri, Niraj Kumar

CRUMB: Efficient Prior Fitted Network Inference via Distributionally Matched Context Batching

arXiv:2606. 11473v1 Announce Type: cross Abstract: Prior-fitted networks (PFNs) are a promising class of tabular foundation models that perform in-context learning, whereby the entire labelled training set is supplied as context, and predictions for test queries are produced in a single forward pass.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 8

TabSwift: An Efficient Tabular Foundation Model with Row-Wise Attention

arXiv:2606. 07345v1 Announce Type: new Abstract: Tabular foundation models, exemplified by TabPFN, perform prediction via in-context learning, inferring test labels directly from labeled training examples.

By Si-Yang Liu, Han-Jia Ye

llms

arXiv Machine Learning

Aug 4

TabDPT-Turbo: Efficient In-Context Learning for Tabular Prediction

arXiv:2608. 01400v1 Announce Type: new Abstract: Tabular foundation models, driven by in-context learning, have rapidly grown in quality and popularity.

By Rasa Hosseinzadeh, Alex Labach, Zexin Xue, Shuyi Han, Valentin Thomas, Anthony L. Caterini

llms efficiency

arXiv Machine Learning

1d ago

Localized TabICLv2: Scaling Tabular In-Context Learning through k-NN

arXiv:2608. 16429v1 Announce Type: new Abstract: Foundational models for tabular data have made significant progress in recent years, with TabICLv2 reporting state-of-the-art performance on several tabular classification tasks.

By Beimnet Bekele Guta

llms fine-tuning benchmarks

arXiv Machine Learning

22h ago

Understanding the Surprising Generalization Properties of Tabular Foundation Models

arXiv:2608. 17957v1 Announce Type: new Abstract: Tabular Foundation Models (TFMs) increasingly rely on in-context learning, where a model receives labelled examples at inference time and predicts labels for new inputs without updating its weights.

By Nour Shaheen, Junwei Ma, Alex Labach, Frank Hutter, Valentin Thomas, Anthony L. Caterini

llms

arXiv AI

Jul 23

LISA: Linear-Indexed Sparse Attention for Efficient Long-Context Reasoning

arXiv:2607. 19358v1 Announce Type: new Abstract: Recent advances in long chain-of-thought reasoning models such as DeepSeek-R1 have led to increasingly longer inference context lengths under the test-time scaling paradigm.

By Yu Zhao, Zekun Zhang, Fan Jiang, Bo Zeng, Linlong Xu, Shimin Shan, Yu Liu, Longyue Wang, Weihua Luo

efficiency benchmarks

arXiv AI

6d ago

Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge

arXiv:2608. 12218v1 Announce Type: cross Abstract: Large language models are increasingly trained and deployed with long contexts that span documents, code repositories, and interaction histories.

By Arda Uzunoglu, Benjamin van Durme, Daniel Khashabi

llms fine-tuning

Related stories

TabSwift: An Efficient Tabular Foundation Model with Row-Wise Attention

TabDPT-Turbo: Efficient In-Context Learning for Tabular Prediction

Localized TabICLv2: Scaling Tabular In-Context Learning through k-NN

Understanding the Surprising Generalization Properties of Tabular Foundation Models

LISA: Linear-Indexed Sparse Attention for Efficient Long-Context Reasoning

Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge