CDMD: A Cross-Dataset Mixed-Type Diffusion Model for Tabular Data
cs.LG
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/ketatam/cdmd
Terminology
Sources
- Language Models are Realistic Tabular Data Generators
- TabDLM: Free-Form Tabular Data Generation via Joint Numerical-Language Diffusion
- Breaking the Quality-Privacy Tradeoff in Tabular Data Generation via In-Context Learning
- TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second
- TabFORGE: A Tabular Foundation Model for Generative Modelling
- Towards General Text Embeddings with Multi-stage Contrastive Learning
- TabPFGen -- Tabular Data Generation with TabPFN
- Synthcity: facilitating innovative use cases of synthetic data in different data modalities
- TabICL: A Tabular Foundation Model for In-Context Learning on Large Data
- A Comprehensive Survey of Synthetic Tabular Data Generation
- Score-Based Generative Modeling through Stochastic Differential Equations
- A Survey on Deep Learning Approaches for Tabular Data Generation: Utility, Alignment, Fidelity, Privacy, Diversity, and Beyond
- Beyond Privacy: Navigating the Opportunities and Challenges of Synthetic Data
- Why Tabular Foundation Models Should Be a Research Priority
- LaTable: Towards Large Tabular Models
- LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks