{"total":18,"rows":[{"id":"2310.13981","title":"Filling the Missing: Exploring Generative AI for Enhanced Federated Learning over Heterogeneous Mobile Edge Devices","created":"2023-10-21","cited_by_count":13,"area":null},{"id":"2502.06604","title":"Do we really have to filter out random noise in pre-training data for language models?","created":"2025-02-10","cited_by_count":11,"area":null},{"id":"2310.16499","title":"Data Optimization in Deep Learning: A Survey","created":"2023-10-25","cited_by_count":6,"area":null},{"id":"2405.16845","title":"On Mesa-Optimization in Autoregressively Trained Transformers: Emergence and Capability","created":"2024-05-27","cited_by_count":5,"area":null},{"id":"2406.09864","title":"LUMA: A Benchmark Dataset for Learning from Uncertain and Multimodal Data","created":"2024-06-14","cited_by_count":5,"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":"2606.24418","title":"Data Augmentation: A Fourier Analysis Perspective","created":"2026-06-23","cited_by_count":4,"area":null},{"id":"2505.24190","title":"Provably Improving Generalization of Few-Shot Models with Synthetic Data","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2405.19590","title":"Weights Augmentation: it has never ever ever ever let her model down","created":"2024-05-30","cited_by_count":1,"area":null},{"id":"2410.10160","title":"Will the Inclusion of Generated Data Amplify Bias Across Generations in Future Image Classification Models?","created":"2024-10-14","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":"2502.14583","title":"A Theory for Conditional Generative Modeling on Multiple Data Sources","created":"2025-02-20","cited_by_count":1,"area":null},{"id":"2502.21110","title":"Rare event modeling with self-regularized normalizing flows: what can we learn from a single failure?","created":"2025-02-28","cited_by_count":1,"area":null},{"id":"2505.11703","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2506.03467","title":"Differentially Private Distribution Release of Gaussian Mixture Models via KL-Divergence Minimization","created":"2025-06-04","cited_by_count":0,"area":null},{"id":"2510.15194","title":"Salient Concept-Aware Generative Data Augmentation","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2602.14423","title":"The geometry of invariant learning: an information-theoretic analysis of data augmentation and generalization","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2607.02637","title":"Post-Generation Curation of Synthetic Images via Homogeneous-Heterogeneous Splitting","created":"2026-07-02","cited_by_count":0,"area":null}],"next_cursor":null}