Seq2Synth: Benchmarking Temporal Fidelity in Synthetic Sequential Tabular Data
cs.LG, stat.ML
Submitted: 2026-07-17
Updated: 2026-08-31
Comments: 25 pages, 10 figures, 24 tables
Code: https://github.com/KiwanKwon/Seq2Synth
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Diffusion Transformers for Tabular Data Time Series Generation
- RelDiff: Relational Data Generative Modeling with Graph-Based Diffusion Models
- Joint Relational Database Generation via Graph-Conditional Diffusion Models
- Synthetic Data Applications in Finance
- REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformers
- TabularARGN: A Flexible and Efficient Auto-Regressive Framework for Generating High-Fidelity Synthetic Data
- Sequential Models in the Synthetic Data Vault
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