MulTaBench is a new benchmark comprising 40 datasets split evenly between image‑tabular and text‑tabular tasks, designed to evaluate multimodal tabular learning where modalities provide complementary predictive signals. The study shows that tuning embeddings to the specific task—target‑aware representation learning—improves performance across both modalities, various tabular learners, encoder sizes, and embedding dimensions. MulTaBench is the largest image‑tabular benchmark to date, covering high‑impact domains such as healthcare and e‑commerce, and aims to spur research into joint modeling and multimodal tabular foundation models.
arXiv:2606. 11682v1 Announce Type: cross Abstract: Tabular-image multimodal learning aims to improve predictive modeling by jointly using structured tabular attributes and visual data.
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...
The paper introduces TEmBed, a unified benchmark for evaluating tabular embeddings across four representation levels—cell, row, column, and table—using a diverse set of models. It demonstrates that the best model depends on the specific task and representation level, providing practical guidance for selecting embeddings in real-world applications. The study aims to facilitate the development of more general-purpose tabular representation models.
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.
arXiv:2607. 07756v1 Announce Type: new Abstract: Multimodal learning usually requires a dedicated encoder per modality.
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.
arXiv:2608. 10837v1 Announce Type: cross Abstract: The strong performance of foundation models for tabular tasks comes at substantial inference costs.
AdaKerNet is a task‑adaptive neural kernel decoder that operates on frozen multimodal representations from large foundation models, without requiring access to the models’ parameters. It learns Lipschitz‑controlled multimodal features, a reference kernel providing a soft structural prior, and a lightweight nonlinear predictor that deforms this structure. Experiments on four multimodal large language models and diverse input modalities show consistent improvements over baseline decoders, achieving up to 41% error reduction in scarce‑label settings.
arXiv:2607. 16305v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have achieved strong progress in multimodal understanding.
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...
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.
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.