arXiv AI
TabMosaic: Unified In-Context Diffusion for Tabular Generative Tasks
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 3
AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking
arXiv:2606. 03347v1 Announce Type: cross Abstract: Score-based diffusion models have emerged as prominent deep generative models; however, their application to tabular data remains challenging because their backbones assume fully specified inputs, whereas real-world tabular data often contain missing values.
arXiv AI
4d ago
TabGift: A Context-Efficient Foundation Model for Tabular Data Generation
arXiv:2610.16990v1 Announce Type: cross Abstract: Tabular data generation aims to synthesize realistic samples from limited observations while faithfully capturing the underlying data distribution. T...
arXiv Machine Learning
Oct 2
CDMD: A Cross-Dataset Mixed-Type Diffusion Model for Tabular Data
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 Machine Learning
Oct 12
Transformer-based In-Context Score Operator Learning for Diffusion Models
The paper introduces a transformer-based framework that learns an in‑context score operator for diffusion models, allowing the model to perform reverse‑diffusion sampling on unseen target distributions specified by a small empirical context set. By representing the task‑dependent score as a Gaussian‑kernel conditional mean and approximating it with a transformer‑based query‑dependent attention architecture, the method can adapt to new tasks without retraining or parameter updates. The authors provide theoretical generalization‑error bounds and evaluate the approach on scientific and visual datasets, noting strong performance on simple task families and limitations as task complexity grows.
arXiv AI
Aug 11
A Sobering Look at Tabular Data Generation via Probabilistic Circuits
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.
Hugging Face Trending Papers
Jun 29
UniGP: Taming Diffusion Transformer for Prior-Preserved Unified Generation and Perception
Recent advances in diffusion models have shown impressive performance in controllable image generation and dense prediction tasks. However, existing approaches typically treat diffusion-based controllable generation and dense prediction as separate tasks, overlooking the potential benefits of jointly modeling the heterogeneous distributions.