The paper introduces Retro, a tabular foundation model that uses retrospective inference to revisit and recombine intermediate representations during inference. Retro employs Attention Residuals to select which past information to reuse and query-conditioned Gated Attention to shape the contextual update for each query. Experiments on TabArena, TALENT, and RelArena show Retro achieves top‑three performance and lies on the Pareto frontier, demonstrating that reusing intermediate representations can better exploit depth in tabular foundation models.
By Hao-Run Cai, Si-Yang Liu, Zi-Jian Cheng, Kun-Yang Yu, Jin-Hao Sheng, Guo Yu, Chonghan Liu, Zhi Zhou, Jun-Peng Jiang, Lan-Zhe Guo, Han-Jia Ye
The paper shows that Tabular Foundation Models (TFMs) are highly overparameterized, with up to 96% of transformer blocks removable without significant loss in performance. Using a closed‑form, label‑free affine translator, the authors demonstrate that halving the depth of eight leading TFMs costs at most $0.002$ median AUROC, while a single‑block TabPFN‑3 remains competitive. Removing depth saves up to 1.5 B parameters, speeds GPU inference up to 6×, and reduces memory usage by 6× with negligible accuracy loss.
By Irene Cannistraci, Julia E. Vogt
arXiv:2605.12904v2 Announce Type: replace
Abstract: Tabular foundation models (TFMs) have emerged as a powerful paradigm for in-context learning on structured data, enabling direct prediction on new...
By Yilong Chen, Xueying Ding, Leman Akoglu
arXiv:2609.36883v1 Announce Type: new
Abstract: Tabular foundation models (TFMs) are increasingly popular because they deliver strong predictions on new datasets through in-context learning, without...
By Tianqi Zhao, Tianyi Zhuang, Shuo Duan, Guanyang Wang, Yan Shuo Tan, Qiong Zhang
OrionMoE-v1.0 is a compact tabular foundation model that uses a dual‑axis Transformer and a sparse mixture‑of‑experts architecture to perform in‑context learning on labeled support tables. It selectively activates experts along the feature axis, guided by both individual feature representations and overall dataset context, enabling adaptive computation across diverse tabular problems. Pretrained on synthetic classification tasks, it achieves competitive performance on multiple benchmarks, especially on small‑context, high‑dimensional, and class‑imbalanced datasets.
By Mohamed Bouadi, Nassim Bouarour, Aditya Tanna, Vinay Kumar Sankarapu
The paper investigates how synthetic pretraining priors used in tabular foundation models (TFMs) influence downstream performance. By reconstructing the synthetic data generators of four TFMs and comparing their generated tasks to two popular tabular benchmarks using structural descriptors, the authors measure structural coverage and normalized density. They find that some generators provide broader and denser support for benchmark tasks, and that stronger synthetic-to-benchmark support generally correlates with better model performance.
By He Zhao, Ryan Thompson, Daniel M. Steinberg, Ashfaqur Rahman, Edwin V. Bonilla, Cheng Soon Ong
arXiv:2610.14998v1 Announce Type: cross
Abstract: Tabular foundation models adapt to new datasets through in-context learning (ICL), and, like most transformers, they tie computational depth to the n...
By Tejas Vaidhya, Gaurav Sahu, Irina Rish
The paper investigates how test‑time compute techniques—adaptation, aggregation, and context construction—can improve predictions of pretrained tabular foundation models (TFMs). It introduces DiagScale, a lightweight adaptation method that trains a minuscule fraction of parameters yet matches full fine‑tuning gains, and shows that selective aggregation of predictions from diverse preprocessing variants can reduce error, while broader context expansion offers inconsistent benefits. The study concludes that adaptation and selective aggregation consistently yield benchmark‑level improvements, but their combined use demands more computation, guiding strategy selection based on available resources.
By Kanghui Ning, Marin Bilo\v{s}, James T. Wilson, Yilang Zhang, Kashif Rasul, Dongjin Song, Anderson Schneider, Yuriy Nevmyvaka
arXiv:2608. 10837v1 Announce Type: cross Abstract: The strong performance of foundation models for tabular tasks comes at substantial inference costs.
By Mykhailo Koshil, Matthias Feurer, Katharina Eggensperger
The paper introduces RefineICL, an attention‑gated, feed‑forward‑network‑free framework that refines representations in situ for tabular foundation models. By using support labels to guide episode‑specific updates, the method transfers learned corrections to unlabeled queries without altering model parameters, achieving state‑of‑the‑art performance on AMLB29 and TabArena benchmarks. Experiments and internal interventions demonstrate that intermediate support updates are essential for constructing task‑specific predictors in context.
By Tian Zhou, Beverly Jin, Linxiao Yang, Xue Wang, Wenwei Wang, Bingqing Peng, Mengni Ye, Jinjie Gu, Liang Sun
TabMF is a framework that repurposes pretrained tabular foundation models (TFMs) as encoders for supervised datasets, adding a dataset-level readout and fine‑tuning via contrastive post‑training on synthetic views. The authors instantiate TabMF on TabICLv2 and TabPFN‑2.5 and evaluate the resulting representations on six tasks involving unseen real datasets. The approach achieves the best aggregate performance among both learned and classical dataset representations, excelling in dataset retrieval, compact benchmark construction, and distribution‑shift severity assessment.
By Rafiq Kamel, Nicolas Atienza, Aziz Fouch\'e, Nicola Cancedda, Josif Grabocka
The study shows that tabular foundation models (TFMs) can be dramatically simplified without losing performance. By replacing up to 96% of transformer blocks with a label‑free affine translator, researchers found that half‑depth models still outperform full‑depth TFMs and tuned GBDTs across 171 classification datasets. The simplification reduces parameters by up to 1.5 B, speeds GPU inference up to 6×, and cuts memory usage by 6× with minimal impact on AUROC.