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 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
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
arXiv:2609.39628v1 Announce Type: new
Abstract: This paper proposes MIND, a marginal-invariant neural dependency diffusion model for mixed-type tabular data. MIND does not directly learn the joint di...
By Pengfei Li, Mohammad Khalil
arXiv:2605.09424v2 Announce Type: replace
Abstract: Generative modelling is a demanding test of foundation models, because it requires robust, holistic representation learning for a given data modali...
By Xiangjian Jiang, Mingxuan Liu, Nikola Simidjievski, Tassilo Klein, Mateja Jamnik
Support-Compiled Feature Folding (SCFF) is a training‑free inference framework that addresses the feature‑side scaling dilemma in tabular foundation models by routing support‑ranked features through bounded leaves of the native encoder, checking residual evidence, and merging encoded messages for a single contextual prediction. This approach transforms quadratic pairwise mixing into linear‑in‑width work with a bounded local working set, achieving dataset‑macro accuracy and NLL improvements across six backbones on an 18‑dataset wide‑table slice. SCFF delivers significant GPU‑memory savings (median 2.09×–2.36×) and, when constrained by a peak‑memory ceiling, further boosts accuracy by up to 4.06 points over the widest single‑leaf baseline.
whyItMatters":"SCFF demonstrates that memory‑efficient inference can simultaneously improve accuracy and reduce resource usage in tabular foundation models, offering a practical solution for deploying these models at scale."
By Tian Zhou, Beverly Jin, Xue Wang, Linxiao Yang, Wenwei Wang, Bingqing Peng, Mengni Ye, Jinjie Gu, Liang Sun
arXiv:2606. 04485v1 Announce Type: new Abstract: Tabular foundation models (TFMs) increasingly rival tree ensembles, but their performance is often compute-inefficient: with standard affine scalar tokenization, each feature injects value variation through an essentially one-dimensional channel, and feature IDs/positional signals cannot increase within-feature value degrees of freedom, yielding weak early-layer value sensitivity and redundant hidden states.
By Yuanrui Wang, Xingxuan Zhang, Han Yu, Mingchao Ming, Gang Ren, Hao Yuan, Li Mao, Yunjia Zhang, Chun Yuan, Peng Cui
The paper introduces the General Demographic Pre-trained (GDP) model, a lightweight foundation model that learns representations from the two most common clinical attributes—age and sex. By optimizing encoding and visit‑reordering strategies, GDP embeddings are shown to improve predictive performance when concatenated with raw features across various disease and geographic cohorts. The model outperforms several state‑of‑the‑art tabular foundation models and tree‑based algorithms, demonstrating that enriched demographic embeddings can enhance classification tasks while remaining fully compatible with standard classifiers.
By Li-Chin Chen, Ji-Tian Sheu, Yuh-Jue Chuang
arXiv:2606. 09323v1 Announce Type: new Abstract: Tabular encoders are usually evaluated inside task-specific end-to-end pipelines, so models from different training paradigms are difficult to compare directly even when they operate on similar tabular signals.
By Wei Pang, Xiangru Jian, Hehan Li, Zhixuan Yu, Alex Xue, Jinyang Li, Zhengyuan Dong, Xinjian Zhao, Hao Xu, Chao Zhang, Reynold Cheng, M. Tamer \"Ozsu, Tianshu Yu
arXiv:2606. 30410v1 Announce Type: cross Abstract: Foundation models for predictive machine learning on tabular data have recently gained significant traction in academia and industry.
By Lennart Purucker, Andrej Tschalzev, Nick Erickson, Gioia Blayer, David Holzm\"uller, Alan Arazi, Alexander Pfefferle, Mustafa Tajjar, Ga\"el Varoquaux, Frank Hutter
LoopICL is a transformer architecture that loops a single block to address tabular tasks. It separates parameter count from computational depth by using a cell stream for per‑cell features and a row stream for in‑context examples, refined via within‑column and cross‑column attention. During pre‑training, varying loop counts and a learned exit‑gate allow the model to adjust inference depth at test time, achieving competitive performance with TabICLv2 while using about 90% fewer parameters.
By Amir Rezaei Balef, Katharina Eggensperger
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