{"total":39,"rows":[{"id":"2104.08758","title":"Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus","created":"2021-04-18","cited_by_count":492,"area":null},{"id":"2102.08921","title":"How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models","created":"2021-02-17","cited_by_count":196,"area":null},{"id":"2103.09396","title":"Pros and Cons of GAN Evaluation Measures: New Developments","created":"2021-03-17","cited_by_count":123,"area":null},{"id":"2302.04062","title":"Machine Learning for Synthetic Data Generation: A Review","created":"2023-02-08","cited_by_count":120,"area":null},{"id":"2302.02041","title":"REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformers","created":"2023-02-04","cited_by_count":94,"area":null},{"id":"2203.07618","title":"Do Language Models Plagiarize?","created":"2022-03-15","cited_by_count":73,"area":null},{"id":"2106.03216","title":"On Memorization in Probabilistic Deep Generative Models","created":"2021-06-06","cited_by_count":60,"area":null},{"id":"2411.00113","title":"A Geometric Framework for Understanding Memorization in Generative Models","created":"2024-10-31","cited_by_count":40,"area":null},{"id":"2303.01325","title":"A Pathway Towards Responsible AI Generated Content","created":"2023-03-02","cited_by_count":38,"area":null},{"id":"2302.04440","title":"Feature Likelihood Divergence: Evaluating the Generalization of Generative Models Using Samples","created":"2023-02-09","cited_by_count":25,"area":null},{"id":"2310.12952","title":"Cousins Of The Vendi Score: A Family Of Similarity-Based Diversity Metrics For Science And Machine Learning","created":"2023-10-19","cited_by_count":24,"area":null},{"id":"2105.14203","title":"Understanding Instance-based Interpretability of Variational Auto-Encoders","created":"2021-05-29","cited_by_count":21,"area":null},{"id":"2106.03062","title":"On Training Sample Memorization: Lessons from Benchmarking Generative Modeling with a Large-scale Competition","created":"2021-06-06","cited_by_count":18,"area":null},{"id":"2402.17287","title":"An Interpretable Evaluation of Entropy-based Novelty of Generative Models","created":"2024-02-27","cited_by_count":17,"area":null},{"id":"2405.02700","title":"Unveiling Differences in Generative Models: A Scalable Differential Clustering Approach","created":"2024-05-04","cited_by_count":16,"area":null},{"id":"2506.07998","title":"Generative Modeling of Weights: Generalization or Memorization?","created":"2025-06-09","cited_by_count":14,"area":null},{"id":"2505.07175","title":"Metrics that matter: Evaluating image quality metrics for medical image generation","created":"2025-05-12","cited_by_count":12,"area":null},{"id":"2410.01322","title":"Forte : Finding Outliers with Representation Typicality Estimation","created":"2024-10-02","cited_by_count":9,"area":null},{"id":"2201.08770","title":"Generalization Metrics for Practical Quantum Advantage in Generative Models","created":"2022-01-21","cited_by_count":8,"area":null},{"id":"2111.13617","title":"DP-SGD vs PATE: Which Has Less Disparate Impact on GANs?","created":"2021-11-26","cited_by_count":7,"area":null},{"id":"2502.10828","title":"The Vendiscope: An Algorithmic Microscope For Data Collections","created":"2025-02-15","cited_by_count":5,"area":null},{"id":"2210.12231","title":"Reducing Training Sample Memorization in GANs by Training with Memorization Rejection","created":"2022-10-21","cited_by_count":4,"area":null},{"id":"2503.15564","title":"GReaTER: Generate Realistic Tabular data after data Enhancement and Reduction","created":"2025-03-19","cited_by_count":3,"area":null},{"id":"2411.00879","title":"DEREC-SIMPRO: unlock Language Model benefits to advance Synthesis in Data Clean Room","created":"2024-10-31","cited_by_count":2,"area":null},{"id":"2403.19050","title":"Detecting Generative Parroting through Overfitting Masked Autoencoders","created":"2024-03-27","cited_by_count":1,"area":null},{"id":"2411.03098","title":"Local Lesion Generation is Effective for Capsule Endoscopy Image Data Augmentation in a Limited Data Setting","created":"2024-11-05","cited_by_count":1,"area":null},{"id":"2505.21160","title":"STEB: In Search of the Best Evaluation Approach for Synthetic Time Series","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2506.03522","title":"Path Generation and Evaluation in Video Games: A Nonparametric Statistical Approach","created":"2025-06-04","cited_by_count":1,"area":null},{"id":"2509.21925","title":"Generation Properties of Stochastic Interpolation under Finite Training Set","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2510.24233","title":"PRIVET: PRoximIty leakage detection Via Extreme value Theory","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2512.23628","title":"Memorization in 3D Shape Generation: An Empirical Study","created":"2025-12-29","cited_by_count":1,"area":null},{"id":"2305.15441","title":"Improving few-shot learning-based protein engineering with evolutionary sampling","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2310.03556","title":"Stable Training of Probabilistic Models Using the Leave-One-Out Maximum Log-Likelihood Objective","created":"2023-10-05","cited_by_count":0,"area":null},{"id":"2412.18460","title":"GeFL: Model-Agnostic Federated Learning with Generative Models","created":"2024-12-24","cited_by_count":0,"area":null},{"id":"2503.18462","title":"PALATE: Peculiar Application of the Law of Total Expectation to Enhance the Evaluation of Deep Generative Models","created":"2025-03-24","cited_by_count":0,"area":null},{"id":"2602.13066","title":"A Calibrated Memorization Index (MI) for Detecting Training Data Leakage in Generative MRI Models","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2602.18525","title":"Do Generative Metrics Predict YOLO Performance? An Evaluation Across Models, Augmentation Ratios, and Dataset Complexity","created":"2026-02-20","cited_by_count":0,"area":null},{"id":"2608.12088","title":"RA-ClipScore: Making Generative Model Evaluation More Interpretable","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2610.00251","title":"The Null Is the Hard Part: Exact Tests for Memorization in Generative Models","created":"2026-09-23","cited_by_count":0,"area":null}],"next_cursor":null}