Tabular ICL

ICL: In-Context Learning

Tabular in-context learning studies models that infer a table’s prediction rule from labeled examples supplied at inference time, often using foundation models pretrained on synthetic or real tabular tasks. Common approaches include prior-fitted transformers, retrieval and context-selection methods, and test-time adaptation; performance is often compared on suites such as TabArena, TALENT, and OpenML. Work now extends beyond classification and regression to anomaly detection, imputation, generation, survival analysis, and streaming settings. A central tension is how to scale context and broaden task coverage while controlling inference cost and ensuring robustness to distribution shift, noisy examples, and privacy risks.

Latest papers

108 papers28 papers in the last four weeks, up 211% on the four weeks before. 0.2% of all new papers.

TabPFN-3: Technical Report
May 13, 2026Léo Grinsztajn, Klemens Flöge, Oscar Key +38Tabular Foundation Models Efficient Neural Network Inference
VIP-COP: Context Optimization for Tabular Foundation Models
May 13, 2026Yilong Chen, Xueying Ding, Leman AkogluIn-Context Example Selection Tabular Foundation Models
Carnegie Mellon University
PromptDx: Differentiable Prompt Tuning for Multimodal In-Context Alzheimer's Diagnosis
May 9, 2026Lujia Zhong, Yihao Xia, Shuo Huang +2Multimodal ICL Medical Diagnosis
Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California · Ming Hsieh Department of Electrical and Computer Engineering, Viterbi School of Engineering, University of Southern California · Alfred E. Mann Department of Biomedical Engineering, Viterbi School of Engineering, University of Southern California
Toward Privileged Foundation Models:LUPI for Accelerated and Improved Learning
May 8, 2026Xueying Ding, Leman AkogluTabular Foundation Models Learning Using Privileged Information
Carnegie Mellon University
Is One Layer Enough? Understanding Inference Dynamics in Tabular Foundation Models
May 7, 2026Amir Rezaei Balef, Mykhailo Koshil, Katharina EggenspergerTabular Foundation Models Transformer Interpretability
TU Dortmund University, Dortmund, Germany · Lamarr Institute for Machine Learning and Artificial Intelligence, Dortmund, Germany · University of Tübingen, Tübingen, Germany
In-Context Positive-Unlabeled Learning
May 7, 2026Siyan Liu, Yi Chang, Manli Cheng +2Binary Classification Weakly Supervised Learning
Department of Statistics and Actuarial Science, University of Waterloo
Breaking the Quality-Privacy Tradeoff in Tabular Data Generation via In-Context Learning
May 6, 2026Xinyan Han, Yan Lu, Xiaoyu Lin +5Synthetic Data Augmentation Privacy-Preserving ML
1Tsinghua University · 2Southeast University · 3Siemens China
Mitigating Label Shift in Tabular In-Context Learning via Test-Time Posterior Adjustment
May 6, 2026Seunghan LeeDistribution Shift Robustness Tabular Foundation Models
LG AI Research, Seoul, South Korea.
Tabular foundation models for in-context prediction of molecular properties
Apr 17, 2026Karim K. Ben Hicham, Jan G. Rittig, Martin Grohe +1Tabular Foundation Models Molecular Property Prediction
RWTH Aachen University, Process Systems Engineering (AVT.SVT), Aachen, Germany. · Lehrstuhl Informatik 7, RWTH Aachen University, Aachen, Germany. · JARA-CSD, Aachen, Germany. +1
Noise Immunity in In-Context Tabular Learning: An Empirical Robustness Analysis of TabPFN's Attention Mechanisms
Apr 6, 2026James Hu, Mahdi GhelichiTabular ML Tabular ICL
Model Development Innovation, Risk Management TD Bank, Toronto, Canada
Retrieval-aligned Tabular Foundation Models Enable Robust Clinical Risk Prediction in Electronic Health Records Under Real-world Constraints
Apr 2, 2026Minh-Khoi Pham, Thang-Long Nguyen Ho, Thao Thi Phuong Dao +8Tabular Foundation Models Retrieval-Augmented ICL
School of Computing, Dublin City University, Dublin, Ireland · ADAPT Centre, Dublin City University, Dublin, Ireland · University of Science, Vietnam National University, Ho Chi Minh City, Vietnam +5
Active In-Context Learning for Tabular Foundation Models
Mar 28, 2026Wilailuck Treerath, Fabrizio PittorinoActive Learning Tabular ICL
Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milano, Italy
Multitask-Informed Prior for In-Context Learning on Tabular Data: Application to Steel Property Prediction
Mar 24, 2026Dimitrios Sinodinos, Bahareh Nikpour, Jack Yi Wei +5Multi-Task Learning Tabular Foundation Models
Dep. of Electrical and Computer Engineering, McGill University · Mila – Québec AI Institute · Dep. of Mining and Materials Engineering, McGill University +1
ICLAD: In-Context Learning for Unified Tabular Anomaly Detection Across Supervision Regimes
Mar 19, 2026Jack Yi Wei, Narges ArmanfardTabular Anomaly Detection Tabular Foundation Models
Department of Electrical and Computer Engineering, McGill University, Canada · Mila - Quebec Artificial Intelligence Institute, Montreal, Canada
TACTIC for Navigating the Unknown: Tabular Anomaly deteCTion via In-Context inference
Mar 15, 2026Patryk Marszałek, Tomasz Kuśmierczyk, Marek ŚmiejaTabular Anomaly Detection Anomaly Detection
Faculty of Mathematics and Computer Science, Jagiellonian University, Kraków, Poland · Doctoral School of Exact and Natural Sciences, Jagiellonian University, Kraków, Poland
Evaluating SAP RPT-1 for Enterprise Business Process Prediction: In-Context Learning vs. Traditional Machine Learning on Structured SAP Data
Feb 22, 2026Amit LalTabular Foundation Models Tabular Prediction
Microsoft Corporation
TabSieve: Explicit In-Table Evidence Selection for Tabular Prediction
Feb 12, 2026Yongyao Wang, Ziqi Miao, Lu Yang +4In-Context Example Selection Reinforcement Learning
Gaoling School of Artificial Intelligence, Renmin University of China · Shanghai AI Laboratory
TabICLv2: A better, faster, scalable, and open tabular foundation model
Feb 11, 2026Jingang Qu, David Holzmüller, Gaël Varoquaux +1Synthetic Data Pretraining Tabular Foundation Models
SODA Team, INRIA Saclay, Palaiseau, France · Probabl, France

May 13, 2026J/K move · Enter open · S save

TabPFN-3: Technical Report

Léo Grinsztajn, Klemens Flöge, Oscar Key, Felix Birkel+37

Tabular Foundation Models Efficient Neural Network Inference Inference-Time Scaling Tabular ICL Tabular Prediction

Open paper AskPDF arXiv

Tabular data underpins most high-value prediction problems in science and industry, and TabPFN has driven the foundation model revolution for this modality. Designed with feedback from our users, TabPFN-3 builds on this foundation to scale state-of-the-art performance to datasets with 1M training rows and substantially reduce training and inference time. Pretrained exclusively on synthetic data from our prior, TabPFN-3 dramatically pushes the frontier of tabular prediction and brings substantial gains on time series, relational, and tabular-text data. On the standard tabular benchmark TabArena, a forward pass of TabPFN-3 outperforms all other models, including tuned and ensembled baselines, by a significant margin, and pareto-dominates the speed/performance frontier. On more diverse datasets, TabPFN-3 ranks first on datasets with many classes, and beats 8-hour-tuned gradient-boosted-tree baselines on datasets up to 1M training rows and 200 features. TabPFN-3 introduces test-time compute scaling to tabular foundation models. Our API offering TabPFN-3-Plus (Thinking) exploits this to beat all non-TabPFN models by over 200 Elo on TabArena, rising to 420 Elo on the largest data subset, and outperforms AutoGluon 1.5 extreme while being 10x faster, without using LLMs, real data, internet search or any other model besides TabPFN. TabPFN-3 extends the capabilities of our models, enabling SOTA prediction on relational data (new SOTA foundation model on RelBenchV1) and tabular-text data (SOTA on TabSTAR via TabPFN-3-Plus); and improves existing integrations: a specialized checkpoint, TabPFN-TS-3, ranks 2nd on the time-series benchmark fev-bench, and SHAP-value computation is up to 120x faster. TabPFN-3 achieves this performance while being up to 20x faster than TabPFN-2.5. In addition, a reduced KV cache and row-chunking scale to 1M rows on one H100 with fast inference speed.