Prior-Data Fitted Networks

Also known as PFN

Ask about this topic

Overview

PFNs are models, often transformers, trained on many synthetic datasets so they can make predictions for a new dataset from its examples, without task-specific optimization. Their synthetic priors encode possible data-generating processes, and researchers adapt them for tabular prediction, time-series forecasting, survival analysis, causal inference, graph learning, and Bayesian optimization. Common approaches include amortizing Bayesian posterior prediction, designing structured or hybrid priors, and adapting pretrained representations or inference procedures to new tasks. A central challenge is that performance and uncertainty depend on how well the training prior matches deployment data: models can be fast and effective in familiar settings yet retain errors on rare or misspecified cases.

Latest papers

CardsList

48 papers14 papers in the last four weeks, against 1 the four weeks before. 0.1% of all new papers.

  1. Transformers Can Learn Posterior Predictive Distributions In-Context

    May 26, 2026Gyeonghun Kang, Changwoo J. Lee, Xiang ChengBayesian InferenceTransformer Attention

    Department of Statistical Science, Duke University, Durham, NC, USA · Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA

  2. Correcting Class Imbalance in Prior-Data Fitted Networks for Tabular Classification

    May 20, 2026Samuel McDowell, Nathan Stromberg, Lalitha SankarClass-Imbalanced LearningTabular Classification

    School of Electrical, Computer and Energy Engineering · Arizona State University, Tempe, AZ

  3. When Tabular Foundation Models Meet Strategic Tabular Data: A Prior Alignment Approach

    May 19, 2026Xinpeng Lv, Yunxin Mao, Renzhe Xu +13Tabular Foundation ModelsStrategic Classification

    College of Computer, National University of Defense Technology, Changsha, China · Institute for Theoretical Computer Science, Shanghai University of Finance and Economics, Shanghai, China · State Key Lab of General AI, School of Intelligence Science and Technology, Peking University, Beijing, China +3

  4. SurvivalPFN: Amortizing Survival Prediction via In-Context Bayesian Inference

    May 15, 2026Shi-ang Qi, Vahid Balazadeh, Michael Cooper +2Amortized InferenceSurvival Analysis

    Vector Institute · University of Toronto · University of Alberta +1

  5. PFN-TS: Thompson Sampling for Contextual Bandits via Prior-Data Fitted Networks

    May 11, 2026Yan Shuo Tan, Kenyon Ng, Ruizhe Deng +3Thompson SamplingPrior-Data Fitted Networks

    National University of Singapore · Monash University · Renmin University of China +1

  6. Pre-trained Tabular Foundation Models as Versatile Summary Networks for Neural Posterior Estimation

    May 8, 2026Elliot Pickens, Chiraag Gohel, Sidharth SatyaTabular Foundation ModelsSimulation-Based Inference

    University of Pennsylvania · The George Washington University · Brown University

  7. Decoupled PFNs: Identifiable Epistemic-Aleatoric Decomposition via Structured Synthetic Priors

    May 7, 2026Richard Bergna, Stefan Depeweg, José Miguel Hernández-LobatoUncertainty QuantificationBayesian Optimization

    University of Cambridge · 2Siemens AG

  8. Evaluating TabPFN for Mild Cognitive Impairment to Alzheimer's Disease Conversion in Data Limited Settings

    Apr 29, 2026Brad Ye, Bulent Soykan, Gulsah Hancerliogullari Koksalmis +2Tabular Foundation ModelsAlzheimer's Disease

    Department of Medicine, University of Central Florida College of Medicine, Orlando, FL, USA · NIMBUS Lab, University of Central Florida · Department of Mechanical, Industrial & Manufacturing Eng., The University of Toledo, Toledo, OH, USA +3

  9. Prior-Fitted Functional Flow: In-Context Generative Models for Pharmacokinetics

    Apr 19, 2026César Ojeda, Niklas Hartung, Wilhelm Huisinga +6Probabilistic Time Series ForecastingHealthcare

    University of Potsdam, Germany · Technical University Berlin, Germany · Freie Universität Berlin, Germany +2

  10. Zero-shot Multivariate Time Series Forecasting Using Tabular Prior Fitted Networks

    Apr 9, 2026Mayuka Jayawardhana, Nihal Sharma, Kazem Meidani +3Multivariate Time Series ForecastingTime Series Forecasting

    University of Maryland · Capital One

  11. Survival In-Context: Amortized Bayesian Survival Analysis via Prior-Fitted Networks

    Mar 31, 2026Dmitrii Seletkov, Paul Hager, Georgios Kaissis +3Survival AnalysisPrior-Data Fitted Networks

    Institute of Diagnostic and Interventional Radiology, Technical University of Munich, Germany · Chair for AI in Healthcare and Medicine, Technical University of Munich, Germany · Hasso Plattner Institute for Digital Engineering, University of Potsdam, Germany +3

  12. Time-Aware Prior Fitted Networks for Zero-Shot Forecasting with Exogenous Variables

    Mar 16, 2026Andres Potapczynski, Ravi Kiran Selvam, Tatiana Konstantinova +7Exogenous Time Series ForecastingTime Series Forecasting

    Amazon Science, New York University · Amazon Science

  13. Frequentist Consistency of Prior-Data Fitted Networks for Causal Inference

    Mar 12, 2026Valentyn Melnychuk, Vahid Balazadeh, Stefan Feuerriegel +1Causal Effect EstimationPrior-Data Fitted Networks

    LMU Munich & Munich Center for Machine Learning (MCML), Munich, Germany · University of Toronto & Vector Institute, Toronto, Canada

  14. MultiModalPFN: Extending Prior-Data Fitted Networks for Multimodal Tabular Learning

    Feb 23, 2026Wall Kim, Chaeyoung Song, Hanul KimTabular Foundation ModelsMultimodal Foundation Models

    Samsung Electronics, Hwaseong, South Korea · Seoul National University of Science and Technology, Seoul, South Korea

  15. Mechanistic Evidence for Spectral Structures in Prior-Data Fitted Networks

    Jan 29, 2026Kaustubh Sharma, Srijan Tiwari, Ojasva Nema +1Prior-Data Fitted NetworksNeural Network Interpretability

    Indian Institute of Technology Roorkee, India

  16. TabClustPFN: A Prior-data Fitted Network for Tabular Data Clustering

    Jan 29, 2026Tianqi Zhao, Guanyang Wang, Yan Shuo Tan +1Cluster Number EstimationClustering

    Renmin University of China · Rutgers University · National University of Singapore +1

  17. MapPFN: Learning Causal Perturbation Maps in Context

    Jan 28, 2026Marvin Sextro, Weronika Kłos, Gabriel DernbachSingle-Cell Perturbation ModelingCausal Intervention

    Machine Learning Group, Technische Universität Berlin, Berlin, Germany · Berlin Institute for the Foundations of Learning and Data (BIFOLD) · Aignostics, Berlin, Germany +1

  18. GraphPFN: A Prior-Data Fitted Graph Foundation Model

    Sep 25, 2025Dmitry Eremeev, Oleg Platonov, Gleb Bazhenov +2Synthetic Data PretrainingIn-Context Learning

    1HSE University · 2Yandex Research