Synthesis Without Training: An Inference-Only Pipeline for Tabular, Temporal, and Relational Synthetic Data
cs.LG
Submitted: 2026-09-29
Updated: 2026-09-29
Sources
- TabTreeFormer: Tabular Data Generation Using Hybrid Tree-Transformer
- LLM-TabLogic: Preserving Inter-Column Logical Relationships in Synthetic Tabular Data via Prompt-Guided Latent Diffusion
- REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformers
- TabularARGN: A Flexible and Efficient Auto-Regressive Framework for Generating High-Fidelity Synthetic Data
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