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

arXiv: https://arxiv.org/abs/2606.11473 · HTML: https://mlsanity.com/paper/2606.11473/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 9 Jun 2026.

## Builds on (most cited first, 21 of 21)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second](https://mlsanity.com/paper/2207.01848/) (2022)
- [TabICL: A Tabular Foundation Model for In-Context Learning on Large Data](https://mlsanity.com/paper/2502.05564/) (2025)
- [When Do Neural Nets Outperform Boosted Trees on Tabular Data?](https://mlsanity.com/paper/2305.02997/) (2023)
- [TabArena: A Living Benchmark for Machine Learning on Tabular Data](https://mlsanity.com/paper/2506.16791/) (2025)
- [TabICLv2: A better, faster, scalable, and open tabular foundation model](https://mlsanity.com/paper/2602.11139/) (2026)
- [Why Tabular Foundation Models Should Be a Research Priority](https://mlsanity.com/paper/2405.01147/) (2024)
- [Mitra: Mixed Synthetic Priors for Enhancing Tabular Foundation Models](https://mlsanity.com/paper/2510.21204/) (2025)
- [Retrieval & Fine-Tuning for In-Context Tabular Models](https://mlsanity.com/paper/2406.05207/) (2024)
- [TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks](https://mlsanity.com/paper/2402.11137/) (2024)
- [A Closer Look at TabPFN v2: Understanding Its Strengths and Extending Its Capabilities](https://mlsanity.com/paper/2502.17361/) (2025)
- [Mixture of In-Context Prompters for Tabular PFNs](https://mlsanity.com/paper/2405.16156/) (2024)
- [Drift-Resilient TabPFN: In-Context Learning Temporal Distribution Shifts on Tabular Data](https://mlsanity.com/paper/2411.10634/) (2024)
- [In-Context Data Distillation with TabPFN](https://mlsanity.com/paper/2402.06971/) (2024)
- [Scaling TabPFN: Sketching and Feature Selection for Tabular Prior-Data Fitted Networks](https://mlsanity.com/paper/2311.10609/) (2023)
- [TabPFN-Wide: Continued Pre-Training for Extreme Feature Counts](https://mlsanity.com/paper/2510.06162/) (2025)
- [TabFlex: Scaling Tabular Learning to Millions with Linear Attention](https://mlsanity.com/paper/2506.05584/) (2025)
- [Chunked TabPFN: Exact Training-Free In-Context Learning for Long-Context Tabular Data](https://mlsanity.com/paper/2509.00326/) (2025)
- [Realistic Evaluation of TabPFN v2 in Open Environments](https://mlsanity.com/paper/2505.16226/) (2025)
- [A Scalable Approach to Covariate and Concept Drift Management via Adaptive Data Segmentation](https://mlsanity.com/paper/2411.15616/) (2024)
- [uLEAD-TabPFN: Uncertainty-aware Dependency-based Anomaly Detection with TabPFN](https://mlsanity.com/paper/2604.20255/) (2026)

## Built on by (most cited first, 2 of 2)

- [LoGIC: Budgeted Context Construction for Node-Level Graph In-Context Learning with Tabular Foundation Models](https://mlsanity.com/paper/2609.05955/) (2026)
- [Compile the Table: Query-Calibrated Operator Compression for Tabular In-Context Learning](https://mlsanity.com/paper/2610.11784/) (2026)

## Abstract (arXiv)

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. However, the quadratically scaling self-attention mechanism in many PFN architectures makes inference prohibitive for very large training datasets. We propose CRUMB (Clustered Retrieval Using Minimised-MMD Batching), a three-stage inference wrapper that (i) clusters the test queries, (ii) selects a small, distributionally matched training subset for each cluster by greedily minimising the maximum mean discrepancy (MMD), and (iii) runs exact PFN inference on each reduced-context batch. CRUMB is architecture-agnostic and requires no retraining. On the 51-dataset TabArena benchmark, evaluated across three PFN architectures (TabPFNv2, TabICLv1, TabICLv2), we show that CRUMB outperforms similar state-of-the-art context selection strategies. We also show that CRUMB is resilient to covariate drift, as the MMD-minimisation step naturally helps align the training context distribution to match the current test batch distributions.