Imagen de Portada

Inference-Time Refinement Closes the Synthetic-Real Gap in Tabular Diffusion

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lomurno, Eugenio, Balzarini, Filippo, Benelle, Francesco, Panaccione, Francesca Pia, Matteucci, Matteo
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Synthetic Image Learning: Preserving Performance and Preventing Membership Inference Attacks
por: Lomurno, Eugenio, et al.
Publicado: (2024)

Federated Knowledge Recycling: Privacy-Preserving Synthetic Data Sharing
por: Lomurno, Eugenio, et al.
Publicado: (2024)

Stable Diffusion Dataset Generation for Downstream Classification Tasks
por: Lomurno, Eugenio, et al.
Publicado: (2024)

Deep Variational Contrastive Learning for Joint Risk Stratification and Time-to-Event Estimation
por: Erbil, Pinar, et al.
Publicado: (2026)

FPBoost: Fully Parametric Gradient Boosting for Survival Analysis
por: Archetti, Alberto, et al.
Publicado: (2024)

Neuro-Symbolic Scene Graph Conditioning for Synthetic Image Dataset Generation
por: Savazzi, Giacomo, et al.
Publicado: (2025)

PolyGen: Fully Synthetic Vision-Language Training via Multi-Generator Ensembles
por: Brusini, Leonardo, et al.
Publicado: (2026)

POMONAG: Pareto-Optimal Many-Objective Neural Architecture Generator
por: Lomurno, Eugenio, et al.
Publicado: (2024)

Your Image Generator Is Your New Private Dataset
por: Resmini, Nicolo, et al.
Publicado: (2025)

A Lightweight Neural Architecture Search Model for Medical Image Classification
por: Xie, Lunchen, et al.
Publicado: (2024)

GeMM-GAN: A Multimodal Generative Model Conditioned on Histopathology Images and Clinical Descriptions for Gene Expression Profile Generation
por: Panaccione, Francesca Pia, et al.
Publicado: (2026)

A Structured Benchmark for Text-Guided Anomaly Detection: When Language Stops Conditioning the Decision
por: Samele, Stefano, et al.
Publicado: (2026)

Membership Inference over Diffusion-models-based Synthetic Tabular Data
por: Cheng, Peini, et al.
Publicado: (2025)

Inference-Time Scaling in Diffusion Models through Iterative Partial Refinement
por: Kang, Taegu, et al.
Publicado: (2026)

MantisV2: Closing the Zero-Shot Gap in Time Series Classification with Synthetic Data and Test-Time Strategies
por: Feofanov, Vasilii, et al.
Publicado: (2026)

Closing the Sim2Real Performance Gap in RL
por: Anand, Akhil S, et al.
Publicado: (2025)

Diffusion Transformers for Tabular Data Time Series Generation
por: Garuti, Fabrizio, et al.
Publicado: (2025)

ZO-DARTS++: An Efficient and Size-Variable Zeroth-Order Neural Architecture Search Algorithm
por: Xie, Lunchen, et al.
Publicado: (2025)

DenoGrad: A Gradient-Based Framework for Data Refinement in Tabular and Time-Series Learning
por: Alonso-Ramos, J. Javier, et al.
Publicado: (2025)

SurvKAN: A Fully Parametric Survival Model Based on Kolmogorov-Arnold Networks
por: Mastroleo, Marina, et al.
Publicado: (2026)

ProRefine: Inference-Time Prompt Refinement with Textual Feedback
por: Pandita, Deepak, et al.
Publicado: (2025)

Extending Tabular Denoising Diffusion Probabilistic Models for Time-Series Data Generation
por: Dobhal, Umang, et al.
Publicado: (2026)

Diffusion-Driven Synthetic Tabular Data Generation for Enhanced DoS/DDoS Attack Classification
por: B, Aravind, et al.
Publicado: (2026)

MicroFlow: An Efficient Rust-Based Inference Engine for TinyML
por: Carnelos, Matteo, et al.
Publicado: (2024)

FASTGEN: Fast and Cost-Effective Synthetic Tabular Data Generation with LLMs
por: Nguyen, Anh, et al.
Publicado: (2025)

Benchmarking Synthetic Tabular Data: A Multi-Dimensional Evaluation Framework
por: Sidorenko, Andrey, et al.
Publicado: (2025)

Diffusion-based Time Series Forecasting for Sewerage Systems
por: Pearson, Nicholas A., et al.
Publicado: (2025)

Tabular Data Generation using Binary Diffusion
por: Kinakh, Vitaliy, et al.
Publicado: (2024)

Are Synthetic Time-series Data Really not as Good as Real Data?
por: Fu, Fanzhe, et al.
Publicado: (2024)

Effective Test-Time Scaling of Discrete Diffusion through Iterative Refinement
por: Lee, Sanghyun, et al.
Publicado: (2025)

Synthetic Tabular Data Generation for Class Imbalance and Fairness: A Comparative Study
por: Panagiotou, Emmanouil, et al.
Publicado: (2024)

QuAIL: Quality-Aware Inertial Learning for Robust Training under Data Corruption
por: Sabella, Mattia, et al.
Publicado: (2026)

Robust Detection of Synthetic Tabular Data under Schema Variability
por: Kindji, G. Charbel N., et al.
Publicado: (2025)

MediTab: Scaling Medical Tabular Data Predictors via Data Consolidation, Enrichment, and Refinement
por: Wang, Zifeng, et al.
Publicado: (2023)

Is One Layer Enough? Understanding Inference Dynamics in Tabular Foundation Models
por: Balef, Amir Rezaei, et al.
Publicado: (2026)

Shaping the Prior: How Synthetic Task Distributions Determine Tabular Foundation Model Quality
por: Bouadi, Mohamed, et al.
Publicado: (2026)

TabDPT: Scaling Tabular Foundation Models on Real Data
por: Ma, Junwei, et al.
Publicado: (2024)

Dynamic Search for Inference-Time Alignment in Diffusion Models
por: Li, Xiner, et al.
Publicado: (2025)

Winning the MIDST Challenge: New Membership Inference Attacks on Diffusion Models for Tabular Data Synthesis
por: Wu, Xiaoyu, et al.
Publicado: (2025)

Generalizing Behavior via Inverse Reinforcement Learning with Closed-Form Reward Centroids
por: Lazzati, Filippo, et al.
Publicado: (2025)