mlsanityData to 7 Oct 2026

Balanced Adaptive Prototype Selection for Scalable TabPFN Inference on Large-Scale Tabular Data

arXiv 2608.12989 ↗First posted 13 Aug 2026cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Pretrained tabular foundation models have demonstrated strong predictive capability; however, their application to large-scale datasets remains constrained by the limited inference context. This paper introduces Balanced Adaptive Prototype Selection (BAPS), a framework for constructing compact, information-preserving contexts for scalable TabPFN inference. Without modifying or retraining the pretrained model, BAPS jointly preserves representative structure, informative decision boundaries, local density, class balance, and feature-space diversity. Experiments on the million-row HIGGS and SUSY datasets show that 512 prototypes retain strong predictive performance and reliable calibration, corresponding to an approximately 1,953-fold context compression. All experiments were conducted on an Intel Core i7 CPU with 16 GB RAM and no GPU acceleration. These findings establish effective context construction as a practical mechanism for extending pretrained tabular foundation models to million-scale datasets.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 14 of its 23 references that are in the map. First posted on arXiv 13 Aug 2026.

Builds on

14 of 23 references.

References · 14

  1. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  2. 2021Revisiting Deep Learning Models for Tabular Datacited by 725
  3. 2022TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Secondcited by 643
  4. 2019TabNet: Attentive Interpretable Tabular Learningcited by 640
  5. 2021Deep Neural Networks and Tabular Data: A Surveycited by 489
  6. 2021Transformers Can Do Bayesian Inferencecited by 338
  7. 2021SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Trainingcited by 310
  8. 2025TabICL: A Tabular Foundation Model for In-Context Learning on Large Datacited by 267
  9. 2019Neural Oblivious Decision Ensembles for Deep Learning on Tabular Datacited by 200
  10. 2024TabM: Advancing Tabular Deep Learning with Parameter-Efficient Ensemblingcited by 105
  11. 2024Why Tabular Foundation Models Should Be a Research Prioritycited by 103
  12. 2024Retrieval & Fine-Tuning for In-Context Tabular Modelscited by 58
2 more
  1. 2021DANets: Deep Abstract Networks for Tabular Data Classification and Regressioncited by 50
  2. 2024TuneTables: Context Optimization for Scalable Prior-Data Fitted Networkscited by 47

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Compile the Table: Query-Calibrated Operator Compression for Tabular In-Context Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026TabSwift: An Efficient Tabular Foundation Model with Row-Wise Attention
  2. 2026TabPFN-3: Technical Report
  3. 2025Chunked TabPFN: Exact Training-Free In-Context Learning for Long-Context Tabular Data
  4. 2026VIP-COP: Context Optimization for Tabular Foundation Models
  5. 2026LAB-Tab: LLM-Augmented Bayesian Network Adaptation for Few-Shot Tabular Generation
  6. 2025Strengthening LLMs for Tabular Prediction with Structural Priors
  7. 2025On Finetuning Tabular Foundation Models
  8. 2026TabSieve: Explicit In-Table Evidence Selection for Tabular Prediction