arXiv:2603. 23016v2 Announce Type: replace-cross Abstract: Tabular data is more challenging to generate than text and images, due to its heterogeneous features and much lower sample sizes.
arXiv:2609.39124v1 Announce Type: new Abstract: Generative models for tabular data are typically trained separately for each dataset, limiting knowledge transfer and requiring the storage of many spe...
arXiv:2603. 10823v2 Announce Type: replace-cross Abstract: Deep generative models can help with data scarcity and privacy by producing synthetic training data, but they struggle in low-data, imbalanced tabular settings to fully learn the complex data distribution.
arXiv:2602. 07875v3 Announce Type: replace Abstract: Generating tabular data under conditions is critical to applications requiring precise control over the generative process.
arXiv:2606. 09257v1 Announce Type: cross Abstract: High-Dimensional Low-Sample Size (HDLSS) tabular domains (e.
arXiv:2609.16069v1 Announce Type: cross Abstract: Synthetic tabular data can match real data distributions while still violating the semantic constraints that govern valid tabular rows. This reveals...
arXiv:2603. 11946v2 Announce Type: replace-cross Abstract: Probabilistic circuits (PCs) enable exact and tractable inference but employ data independent mixture weights that limit their ability to capture local geometry of the data manifold.
arXiv:2608. 14496v1 Announce Type: cross Abstract: Cross-Tabular Data Generation (CTDG) seeks to learn a generative model from multiple heterogeneous tables and produce new synthetic tabular datasets.
arXiv:2606. 31268v1 Announce Type: cross Abstract: The growing demand for privacy-preserving data sharing has positioned synthetic data generation as a critical component of responsible AI workflows.
arXiv:2608. 12989v1 Announce Type: new Abstract: Pretrained tabular foundation models have demonstrated strong predictive capability; however, their application to large-scale datasets remains constrained by the limited inference context.
arXiv:2608. 01400v1 Announce Type: new Abstract: Tabular foundation models, driven by in-context learning, have rapidly grown in quality and popularity.
TabICLv2 is a new state‑of‑the‑art tabular foundation model that outperforms existing methods on regression and classification tasks. It relies on a synthetic data generation engine for diverse pretraining, architectural innovations such as a scalable softmax attention, and optimized training protocols that replace AdamW with the Muon optimizer. On the TabArena and TALENT benchmarks, TabICLv2 surpasses the current best model, RealTabPFN‑2.5, without any tuning, while also being faster and capable of handling million‑scale datasets with limited GPU memory.
arXiv:2607. 27372v1 Announce Type: new Abstract: The deep learning revolution, kicked off by AlexNet, taught us that end-to-end training beats decomposing a problem into hand-designed stages.