# Tabular Foundation Models Are Effectively Shallow

arXiv: https://arxiv.org/abs/2610.13253 · HTML: https://mlsanity.com/paper/2610.13253/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 41 references that are in the map.
- First posted on arXiv 9 Oct 2026.

## Builds on (most cited first, 30 of 30)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [Are Sixteen Heads Really Better than One?](https://mlsanity.com/paper/1905.10650/) (2019)
- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [TabNet: Attentive Interpretable Tabular Learning](https://mlsanity.com/paper/1908.07442/) (2019)
- [ShortGPT: Layers in Large Language Models are More Redundant Than You Expect](https://mlsanity.com/paper/2403.03853/) (2024)
- [SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training](https://mlsanity.com/paper/2106.01342/) (2021)
- [TabICL: A Tabular Foundation Model for In-Context Learning on Large Data](https://mlsanity.com/paper/2502.05564/) (2025)
- [The Unreasonable Ineffectiveness of the Deeper Layers](https://mlsanity.com/paper/2403.17887/) (2024)
- [When Do Neural Nets Outperform Boosted Trees on Tabular Data?](https://mlsanity.com/paper/2305.02997/) (2023)
- [OpenML Benchmarking Suites](https://mlsanity.com/paper/1708.03731/) (2017)
- [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)
- [TabDPT: Scaling Tabular Foundation Models on Real Data](https://mlsanity.com/paper/2410.18164/) (2024)
- [LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence](https://mlsanity.com/paper/2509.03505/) (2025)
- [Mitra: Mixed Synthetic Priors for Enhancing Tabular Foundation Models](https://mlsanity.com/paper/2510.21204/) (2025)
- [Skip-Attention: Improving Vision Transformers by Paying Less Attention](https://mlsanity.com/paper/2301.02240/) (2023)
- [Block-Recurrent Dynamics in Vision Transformers](https://mlsanity.com/paper/2512.19941/) (2025)
- [Distilling to Hybrid Attention Models via KL-Guided Layer Selection](https://mlsanity.com/paper/2512.20569/) (2025)
- [Orion-MSP: Multi-Scale Sparse Attention for Tabular In-Context Learning](https://mlsanity.com/paper/2511.02818/) (2025)
- [nanoTabPFN: A Lightweight and Educational Reimplementation of TabPFN](https://mlsanity.com/paper/2511.03634/) (2025)
- [ReplaceMe: Network Simplification via Depth Pruning and Transformer Block Linearization](https://mlsanity.com/paper/2505.02819/) (2025)
- [Early Stopping Tabular In-Context Learning](https://mlsanity.com/paper/2506.21387/) (2025)
- [Orion-Bix: Bi-Axial Attention for Tabular In-Context Learning](https://mlsanity.com/paper/2512.00181/) (2025)
- [Is One Layer Enough? Understanding Inference Dynamics in Tabular Foundation Models](https://mlsanity.com/paper/2605.06510/) (2026)
- [End-to-End Compression for Tabular Foundation Models](https://mlsanity.com/paper/2602.05649/) (2026)
- [TabFM: A Zero-Shot Foundation Model for Tabular Data](https://mlsanity.com/paper/2609.37959/) (2026)
- [TACTICL: Task-Aware Compression of Tabular ICL Models](https://mlsanity.com/paper/2608.10837/) (2026)
- [TOAST: Transformer Optimization using Adaptive and Simple Transformations](https://mlsanity.com/paper/2410.04941/) (2024)
- [Distilling Tabular Foundation Models for Structured Health Data](https://mlsanity.com/paper/2605.18702/) (2026)

## Abstract (arXiv)

In-context-learning Tabular Foundation Models (TFMs) are uniquely suited to scenarios with limited resources or privacy constraints, as they solve new tasks without additional training. However, their architecture consists of multiple transformer blocks, resulting in high computational and memory footprints. Meanwhile, traditional alternatives like Gradient-Boosted Decision Trees (GBDTs) remain highly competitive and run efficiently on CPUs, suggesting that tabular tasks may not inherently require deep architectures. This contrast raises a fundamental question: can TFMs be simplified by removing architectural redundancies without sacrificing performance? To answer this, we introduce a closed-form, label-free affine translator that replaces a contiguous window of up to 96% of the blocks, leaving the rest unchanged. Evaluating eight frontier TFMs on 171 classification datasets, we reveal that tabular transformers are vastly overparameterized: replacing half of a model's blocks costs at most 0.002 median AUROC across all architectures, with the half-depth TabFM still outperforming every other full-depth TFMs and tuned GBDTs. Furthermore, different model families are overparameterized in different ways: TabPFN-3 relies on its encoders, maintaining performance regardless of which single block is retained. Other single-axis models spread computation thinly, needing only their first block, while dual-axis models concentrate it in one critical block. Ultimately, removing depth saves up to 1.5B parameters, speeds up GPU inference by up to 6× at a median cost of 0.03 AUROC, while a single-block TabPFN-3 serves cached queries 2.4× faster using 6× less memory at negligible cost.