mlsanityData to 7 Oct 2026

TabPFGen -- Tabular Data Generation with TabPFN

arXiv 2406.05216 ↗First posted 7 Jun 2024cs.LGcited by 26

Not on the map. Why?

Abstract (arXiv)

Advances in deep generative modelling have not translated well to tabular data. We argue that this is caused by a mismatch in structure between popular generative models and discriminative models of tabular data. We thus devise a technique to turn TabPFN -- a highly performant transformer initially designed for in-context discriminative tabular tasks -- into an energy-based generative model, which we dub TabPFGen. This novel framework leverages the pre-trained TabPFN as part of the energy function and does not require any additional training or hyperparameter tuning, thus inheriting TabPFN's in-context learning capability. We can sample from TabPFGen analogously to other energy-based models. We demonstrate strong results on standard generative modelling tasks, including data augmentation, class-balancing, and imputation, unlocking a new frontier of tabular data generation.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 22 of its 42 references that are in the map. First posted on arXiv 7 Jun 2024.

Builds on

22 of 42 references.

References · 22

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  3. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  4. 2019Modeling Tabular data using Conditional GANcited by 695
  5. 2022TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Secondcited by 643
  6. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 635
  7. 2021Implicit Behavioral Cloningcited by 442
  8. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 402
  9. 2022TabDDPM: Modelling Tabular Data with Diffusion Modelscited by 373
  10. 2021Transformers Can Do Bayesian Inferencecited by 338
  11. 2022Language Models are Realistic Tabular Data Generatorscited by 290
  12. 2016A Theory of Generative ConvNetcited by 174
10 more
  1. 2023REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformerscited by 93
  2. 2022Diffusion models for missing value imputation in tabular datacited by 77
  3. 2023Synthcity: facilitating innovative use cases of synthetic data in different data modalitiescited by 76
  4. 2020Trust Issues: Uncertainty Estimation Does Not Enable Reliable OOD Detection On Medical Tabular Datacited by 52
  5. 2020Sequential Deep Learning for Credit Risk Monitoring with Tabular Financial Datacited by 37
  6. 2016Survey of resampling techniques for improving classification performance in unbalanced datasetscited by 32
  7. 2017Learning Energy-Based Models as Generative ConvNets via Multi-grid Modeling and Samplingcited by 32
  8. 2023On the Usefulness of Synthetic Tabular Data Generationcited by 12
  9. 2022Generative Trees: Adversarial and Copycatcited by 7
  10. 2022Use Classifier as Generatorcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 12; 2026: 9.

26 papers.

Sort:

By area:

  1. 2025TabPFN-2.5: Advancing the State of the Art in Tabular Foundation Modelscited by 115
  2. 2024TabDPT: Scaling Tabular Foundation Models on Real Datacited by 97
  3. 2025A Closer Look at TabPFN v2: Understanding Its Strengths and Extending Its Capabilitiescited by 38
  4. 2025Representation Learning for Tabular Data: A Comprehensive Surveycited by 36
  5. 2025TabPFN Unleashed: A Scalable and Effective Solution to Tabular Classification Problemscited by 33
  6. 2024TabEBM: A Tabular Data Augmentation Method with Distinct Class-Specific Energy-Based Modelscited by 15
  7. 2025A Survey on Deep Learning Approaches for Tabular Data Generation: Utility, Alignment, Fidelity, Privacy, Diversity, and Beyondcited by 13
  8. 2025Effortless, Simulation-Efficient Bayesian Inference using Tabular Foundation Modelscited by 13
  9. 2024Unmasking Trees for Tabular Datacited by 4
  10. 2026TACTIC for Navigating the Unknown: Tabular Anomaly deteCTion via In-Context inferencecited by 4
  11. 2025When Tables Leak: Attacking String Memorization in LLM-Based Tabular Data Generationcited by 3
  12. 2026Improving TabPFN's Synthetic Data Generation by Integrating Causal Structurecited by 2
14 more
  1. 2024TREB: a BERT attempt for imputing tabular data imputationcited by 1
  2. 2024NRGBoost: Energy-Based Generative Boosted Treescited by 1
  3. 2025metabeta -- A fast neural model for Bayesian mixed-effects regressioncited by 1
  4. 2026Privately Fine-Tuned LLMs Preserve Temporal Dynamics in Tabular Datacited by 1
  5. 2026A Sobering Look at Tabular Data Generation via Probabilistic Circuitscited by 1
  6. 2026GEAR: Generative Expansion and Real Anchoring for Two-Stage Distillation of Tabular Foundation Modelscited by 1
  7. 2025Guided Data Generation for Understanding Model Behaviorcited by 0
  8. 2025RN-F: A Novel Approach for Mitigating Contaminated Data in Large Language Modelscited by 0
  9. 2025Privacy-Preserving Tabular Synthetic Data Generation Using TabularARGNcited by 0
  10. 2025GEM-T: Generative Tabular Data via Fitting Momentscited by 0
  11. 2026TabPFN for Zero-shot Parametric Engineering Design Generationcited by 0
  12. 2026Causal-Aware Foundation-Model for Bilevel Optimization in Discrete Choice Settingscited by 0
  13. 2026Correcting Class Imbalance in Prior-Data Fitted Networks for Tabular Classificationcited by 0
  14. 2026CDMD: A Cross-Dataset Mixed-Type Diffusion Model for Tabular Datacited by 0