{"total":67,"rows":[{"id":"2209.07162","title":"Brain Imaging Generation with Latent Diffusion Models","created":"2022-09-15","cited_by_count":268,"area":"diffusion"},{"id":"2405.01147","title":"Why Tabular Foundation Models Should Be a Research Priority","created":"2024-05-02","cited_by_count":106,"area":null},{"id":"2301.07573","title":"Synthcity: facilitating innovative use cases of synthetic data in different data modalities","created":"2023-01-18","cited_by_count":76,"area":null},{"id":"2307.02106","title":"SoK: Privacy-Preserving Data Synthesis","created":"2023-07-05","cited_by_count":38,"area":null},{"id":"2304.01429","title":"Learning from data with structured missingness","created":"2023-04-04","cited_by_count":24,"area":null},{"id":"2403.06459","title":"From Pixel to Cancer: Cellular Automata in Computed Tomography","created":"2024-03-11","cited_by_count":20,"area":null},{"id":"2402.06806","title":"Systematic Assessment of Tabular Data Synthesis","created":"2024-02-09","cited_by_count":18,"area":"synth"},{"id":"2302.12749","title":"SurvivalGAN: Generating Time-to-Event Data for Survival Analysis","created":"2023-02-24","cited_by_count":17,"area":null},{"id":"2304.05233","title":"Mask-conditioned latent diffusion for generating gastrointestinal polyp images","created":"2023-04-11","cited_by_count":16,"area":"diffusion"},{"id":"2209.03177","title":"Morphology-preserving Autoregressive 3D Generative Modelling of the Brain","created":"2022-09-07","cited_by_count":15,"area":null},{"id":"2311.00530","title":"Advances in Embodied Navigation Using Large Language Models: A Survey","created":"2023-11-01","cited_by_count":14,"area":null},{"id":"2407.00118","title":"From Efficient Multimodal Models to World Models: A Survey","created":"2024-06-27","cited_by_count":13,"area":"wm"},{"id":"2410.05506","title":"Privacy Vulnerabilities in Marginals-based Synthetic Data","created":"2024-10-07","cited_by_count":10,"area":null},{"id":"2209.09239","title":"Non-Imaging Medical Data Synthesis for Trustworthy AI: A Comprehensive Survey","created":"2022-09-17","cited_by_count":9,"area":null},{"id":"2305.15538","title":"Post-processing Private Synthetic Data for Improving Utility on Selected Measures","created":"2023-05-24","cited_by_count":9,"area":null},{"id":"2211.01202","title":"Human-in-the-Loop Mixup","created":"2022-11-02","cited_by_count":8,"area":null},{"id":"2211.15809","title":"On the Utility Recovery Incapability of Neural Net-based Differential Private Tabular Training Data Synthesizer under Privacy Deregulation","created":"2022-11-28","cited_by_count":8,"area":null},{"id":"2305.10015","title":"Utility Theory of Synthetic Data Generation","created":"2023-05-17","cited_by_count":8,"area":null},{"id":"2310.19250","title":"Assessment of Differentially Private Synthetic Data for Utility and Fairness in End-to-End Machine Learning Pipelines for Tabular Data","created":"2023-10-30","cited_by_count":8,"area":null},{"id":"2209.13696","title":"What Does DALL-E 2 Know About Radiology?","created":"2022-09-27","cited_by_count":7,"area":null},{"id":"2310.17848","title":"Boosting Data Analytics With Synthetic Volume Expansion","created":"2023-10-27","cited_by_count":7,"area":null},{"id":"2403.14790","title":"Latent Diffusion Models for Attribute-Preserving Image Anonymization","created":"2024-03-21","cited_by_count":7,"area":"diffusion"},{"id":"2407.07926","title":"Synthetic Data: Revisiting the Privacy-Utility Trade-off","created":"2024-07-09","cited_by_count":7,"area":null},{"id":"2304.05350","title":"Astroformer: More Data Might not be all you need for Classification","created":"2023-04-03","cited_by_count":6,"area":null},{"id":"2404.04314","title":"Faraday: Synthetic Smart Meter Generator for the smart grid","created":"2024-04-05","cited_by_count":6,"area":null},{"id":"2406.13130","title":"Advancing Retail Data Science: Comprehensive Evaluation of Synthetic Data","created":"2024-06-19","cited_by_count":6,"area":null},{"id":"2408.01690","title":"IDNet: A Novel Dataset for Identity Document Analysis and Fraud Detection","created":"2024-08-03","cited_by_count":6,"area":null},{"id":"2411.03351","title":"Tabular Data Synthesis with Differential Privacy: A Survey","created":"2024-11-04","cited_by_count":6,"area":null},{"id":"2507.00951","title":"Thinking Beyond Tokens: From Brain-Inspired Intelligence to Cognitive Foundations for Artificial General Intelligence and its Societal Impact","created":"2025-07-01","cited_by_count":6,"area":"lr"},{"id":"2312.14095","title":"RetailSynth: Synthetic Data Generation for Retail AI Systems Evaluation","created":"2023-12-21","cited_by_count":5,"area":null},{"id":"2211.06582","title":"Provable Membership Inference Privacy","created":"2022-11-12","cited_by_count":4,"area":"safety"},{"id":"2309.15696","title":"A Unified View of Differentially Private Deep Generative Modeling","created":"2023-09-27","cited_by_count":4,"area":null},{"id":"2310.00277","title":"A Unified Framework for Generative Data Augmentation: A Comprehensive Survey","created":"2023-09-30","cited_by_count":4,"area":null},{"id":"2311.17453","title":"Privacy Measurement in Tabular Synthetic Data: State of the Art and Future Research Directions","created":"2023-11-29","cited_by_count":4,"area":null},{"id":"2403.13612","title":"Does Differentially Private Synthetic Data Lead to Synthetic Discoveries?","created":"2024-03-20","cited_by_count":4,"area":null},{"id":"2503.12999","title":"Concept-as-Tree: A Controllable Synthetic Data Framework Makes Stronger Personalized VLMs","created":"2025-03-17","cited_by_count":4,"area":"mllm"},{"id":"2304.09826","title":"Fairness in AI and Its Long-Term Implications on Society","created":"2023-04-16","cited_by_count":3,"area":null},{"id":"2506.19082","title":"FairCauseSyn: Towards Causally Fair LLM-Augmented Synthetic Data Generation","created":"2025-06-23","cited_by_count":3,"area":"synth"},{"id":"2509.21479","title":"Filtering with Confidence: When Data Augmentation Meets Conformal Prediction","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2405.04554","title":"Differentially Private Synthetic Data with Private Density Estimation","created":"2024-05-06","cited_by_count":2,"area":null},{"id":"2407.09789","title":"Convex space learning for tabular synthetic data generation","created":"2024-07-13","cited_by_count":2,"area":null},{"id":"2407.11785","title":"Defining 'Good': Evaluation Framework for Synthetic Smart Meter Data","created":"2024-07-16","cited_by_count":2,"area":null},{"id":"2306.13211","title":"Differentially Private Synthetic Data Using KD-Trees","created":"2023-06-19","cited_by_count":1,"area":null},{"id":"2309.05079","title":"A supervised generative optimization approach for tabular data","created":"2023-09-10","cited_by_count":1,"area":null},{"id":"2310.09729","title":"Private Synthetic Data Meets Ensemble Learning","created":"2023-10-15","cited_by_count":1,"area":null},{"id":"2502.09566","title":"Zero-shot generation of synthetic neurosurgical data with large language models","created":"2025-02-13","cited_by_count":1,"area":null},{"id":"2506.11753","title":"Exploring the Effectiveness of Deep Features from Domain-Specific Foundation Models in Retinal Image Synthesis","created":"2025-06-13","cited_by_count":1,"area":null},{"id":"2506.13443","title":"PRO: Projection Domain Synthesis for CT Imaging","created":"2025-06-16","cited_by_count":1,"area":null},{"id":"2508.00718","title":"Democratizing Tabular Data Access with an Open$\\unicode{x2013}$Source Synthetic$\\unicode{x2013}$Data SDK","created":"2025-08-01","cited_by_count":1,"area":null},{"id":"2605.17528","title":"CasualSynth: Generating Structurally Sound Synthetic Data","created":"2026-05-17","cited_by_count":1,"area":"synth"},{"id":"2605.24703","title":"TS-Skill: A Benchmark for Evaluating Analytical Skills in Time-Series Question Answering","created":"2026-05-23","cited_by_count":1,"area":null},{"id":"2309.03033","title":"Deep Learning for Polycystic Kidney Disease: Utilizing Neural Networks for Accurate and Early Detection through Gene Expression Analysis","created":"2023-09-06","cited_by_count":0,"area":null},{"id":"2408.16291","title":"Flexible framework for generating synthetic electrocardiograms and photoplethysmograms","created":"2024-08-29","cited_by_count":0,"area":null},{"id":"2411.19689","title":"MIMDE: Exploring the Use of Synthetic vs Human Data for Evaluating Multi-Insight Multi-Document Extraction Tasks","created":"2024-11-29","cited_by_count":0,"area":null},{"id":"2508.06647","title":"Privacy-Preserving Tabular Synthetic Data Generation Using TabularARGN","created":"2025-08-08","cited_by_count":0,"area":null},{"id":"2509.05325","title":"SynDelay: A Synthetic Dataset for Delivery Delay Prediction","created":"2025-08-30","cited_by_count":0,"area":null},{"id":"2510.13582","title":"ArtNet: Hierarchical Clustering-Based Artificial Netlist Generator for ML and DTCO Application","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2601.11897","title":"Task-tailored Pre-processing: Fair Downstream Supervised Learning","created":"2026-01-17","cited_by_count":0,"area":null},{"id":"2603.22954","title":"Privacy-Preserving EHR Data Transformation via Geometric Operators: A Human-AI Co-Design Technical Report","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2605.00788","title":"Repurposing Image Diffusion Models for Adversarial Synthetic Structured Data: A Case Study of Ground Truth Drift","created":"2026-05-01","cited_by_count":0,"area":"diffusion"},{"id":"2605.26823","title":"Generating Logically Consistent Synthetic Supply Chain Data with LLM-Driven Knowledge Graph Reasoning","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2605.27113","title":"High-Quality Synthetic Financial Time-Series using a GAN-Diffusion Framework","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.08372","title":"SoK: Reconstruction Attacks on Synthetic Tabular Data (Insights from Winning the NIST CRC)","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2606.18518","title":"PSyGenTAB: A Privacy-Preserving Framework for Synthetic Clinical Tabular Data Generation via Constrained Optimization","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2607.10196","title":"Generative Augmentation of Raman Spectra for Glioma Classification","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2607.12165","title":"Data Safety: Synthetic Data Quality Analysis Using CIFAKE Dataset","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2610.11407","title":"Beyond Distributional Fidelity: Causal-Penalized Diffusion for Synthetic Tabular Data","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}