{"total":606,"rows":[{"id":"2107.07075","title":"Deep Learning on a Data Diet: Finding Important Examples Early in Training","created":"2021-07-15","cited_by_count":533,"area":null},{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532,"area":null},{"id":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528,"area":null},{"id":"2203.11932","title":"Dataset Distillation by Matching Training Trajectories","created":"2022-03-22","cited_by_count":442,"area":null},{"id":"2110.04181","title":"Dataset Condensation with Distribution Matching","created":"2021-10-08","cited_by_count":365,"area":null},{"id":"2308.12032","title":"From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning","created":"2023-08-23","cited_by_count":307,"area":null},{"id":"2303.09540","title":"SemDeDup: Data-efficient learning at web-scale through semantic deduplication","created":"2023-03-16","cited_by_count":303,"area":null},{"id":"2102.08259","title":"Dataset Condensation with Differentiable Siamese Augmentation","created":"2021-02-16","cited_by_count":291,"area":null},{"id":"2110.08420","title":"Understanding Dataset Difficulty with $\\mathcal{V}$-Usable Information","created":"2021-10-16","cited_by_count":291,"area":null},{"id":"2103.00123","title":"GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training","created":"2021-02-27","cited_by_count":274,"area":null},{"id":"2309.16671","title":"Demystifying CLIP Data","created":"2023-09-28","cited_by_count":270,"area":null},{"id":"2206.07137","title":"Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt","created":"2022-06-14","cited_by_count":236,"area":null},{"id":"2205.10770","title":"Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models","created":"2022-05-22","cited_by_count":220,"area":null},{"id":"2202.00622","title":"Datamodels: Predicting Predictions from Training Data","created":"2022-02-01","cited_by_count":189,"area":null},{"id":"2205.14959","title":"Dataset Condensation via Efficient Synthetic-Data Parameterization","created":"2022-05-30","cited_by_count":188,"area":null},{"id":"2308.12284","title":"D4: Improving LLM Pretraining via Document De-Duplication and Diversification","created":"2023-08-23","cited_by_count":150,"area":null},{"id":"2204.08499","title":"DeepCore: A Comprehensive Library for Coreset Selection in Deep Learning","created":"2022-04-18","cited_by_count":147,"area":null},{"id":"2106.09647","title":"Deep Learning Through the Lens of Example Difficulty","created":"2021-06-17","cited_by_count":141,"area":null},{"id":"2205.09329","title":"Dataset Pruning: Reducing Training Data by Examining Generalization Influence","created":"2022-05-19","cited_by_count":133,"area":null},{"id":"2206.12654","title":"BackdoorBench: A Comprehensive Benchmark of Backdoor Learning","created":"2022-06-25","cited_by_count":128,"area":null},{"id":"2307.09742","title":"Improved Distribution Matching for Dataset Condensation","created":"2023-07-19","cited_by_count":124,"area":null},{"id":"2307.14430","title":"Skill-it! A Data-Driven Skills Framework for Understanding and Training Language Models","created":"2023-07-26","cited_by_count":121,"area":null},{"id":"2103.10689","title":"Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond","created":"2021-03-19","cited_by_count":118,"area":null},{"id":"2310.05773","title":"Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching","created":"2023-10-09","cited_by_count":118,"area":null},{"id":"2210.15809","title":"Coverage-centric Coreset Selection for High Pruning Rates","created":"2022-10-28","cited_by_count":117,"area":null},{"id":"2210.16774","title":"Dataset Distillation via Factorization","created":"2022-10-30","cited_by_count":115,"area":null},{"id":"2210.12067","title":"Efficient Dataset Distillation Using Random Feature Approximation","created":"2022-10-21","cited_by_count":111,"area":null},{"id":"2312.03526","title":"On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm","created":"2023-12-06","cited_by_count":109,"area":null},{"id":"2104.08762","title":"Case-based Reasoning for Natural Language Queries over Knowledge Bases","created":"2021-04-18","cited_by_count":107,"area":null},{"id":"2302.13539","title":"Finding Support Examples for In-Context Learning","created":"2023-02-27","cited_by_count":104,"area":null},{"id":"2302.14416","title":"DREAM: Efficient Dataset Distillation by Representative Matching","created":"2023-02-28","cited_by_count":94,"area":null},{"id":"2402.09668","title":"How to Train Data-Efficient LLMs","created":"2024-02-15","cited_by_count":93,"area":null},{"id":"2303.04947","title":"InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning","created":"2023-03-08","cited_by_count":90,"area":null},{"id":"2301.04272","title":"Data Distillation: A Survey","created":"2023-01-11","cited_by_count":87,"area":null},{"id":"2310.00093","title":"DataDAM: Efficient Dataset Distillation with Attention Matching","created":"2023-09-29","cited_by_count":84,"area":null},{"id":"2405.20541","title":"Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models","created":"2024-05-30","cited_by_count":84,"area":null},{"id":"2110.14032","title":"MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge","created":"2021-10-26","cited_by_count":79,"area":null},{"id":"2106.15831","title":"The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning","created":"2021-06-30","cited_by_count":75,"area":null},{"id":"2109.03216","title":"Learning Fast Sample Re-weighting Without Reward Data","created":"2021-09-07","cited_by_count":69,"area":null},{"id":"2307.09542","title":"Can Neural Network Memorization Be Localized?","created":"2023-07-18","cited_by_count":69,"area":null},{"id":"2310.07931","title":"D2 Pruning: Message Passing for Balancing Diversity and Difficulty in Data Pruning","created":"2023-10-11","cited_by_count":69,"area":null},{"id":"2207.09639","title":"DC-BENCH: Dataset Condensation Benchmark","created":"2022-07-20","cited_by_count":67,"area":null},{"id":"2310.14664","title":"Data Pruning via Moving-one-Sample-out","created":"2023-10-23","cited_by_count":67,"area":null},{"id":"2110.11526","title":"Wide Neural Networks Forget Less Catastrophically","created":"2021-10-21","cited_by_count":64,"area":null},{"id":"2306.05175","title":"Large-scale Dataset Pruning with Dynamic Uncertainty","created":"2023-06-08","cited_by_count":63,"area":null},{"id":"2107.02331","title":"Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering","created":"2021-07-06","cited_by_count":62,"area":null},{"id":"2303.11165","title":"Computationally Budgeted Continual Learning: What Does Matter?","created":"2023-03-20","cited_by_count":61,"area":null},{"id":"2207.13887","title":"Adaptive Second Order Coresets for Data-efficient Machine Learning","created":"2022-07-28","cited_by_count":60,"area":null},{"id":"2403.11435","title":"InsCL: A Data-efficient Continual Learning Paradigm for Fine-tuning Large Language Models with Instructions","created":"2024-03-18","cited_by_count":58,"area":null},{"id":"2209.09476","title":"SparCL: Sparse Continual Learning on the Edge","created":"2022-09-20","cited_by_count":55,"area":null},{"id":"2211.08422","title":"Mechanistic Mode Connectivity","created":"2022-11-15","cited_by_count":50,"area":null},{"id":"2405.15613","title":"Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach","created":"2024-05-24","cited_by_count":50,"area":null},{"id":"2312.15927","title":"M3D: Dataset Condensation by Minimizing Maximum Mean Discrepancy","created":"2023-12-26","cited_by_count":49,"area":null},{"id":"2112.03694","title":"Hard Sample Aware Noise Robust Learning for Histopathology Image Classification","created":"2021-12-05","cited_by_count":48,"area":null},{"id":"2308.10524","title":"Dataset Quantization","created":"2023-08-21","cited_by_count":48,"area":null},{"id":"2201.00454","title":"Memory-Guided Semantic Learning Network for Temporal Sentence Grounding","created":"2022-01-03","cited_by_count":46,"area":null},{"id":"2502.20653","title":"Dataset Distillation with Neural Characteristic Function: A Minmax Perspective","created":"2025-02-28","cited_by_count":45,"area":null},{"id":"2106.03225","title":"Efficient Lottery Ticket Finding: Less Data is More","created":"2021-06-06","cited_by_count":44,"area":null},{"id":"2109.00574","title":"Active label cleaning for improved dataset quality under resource constraints","created":"2021-09-01","cited_by_count":44,"area":null},{"id":"2306.01244","title":"Towards Sustainable Learning: Coresets for Data-efficient Deep Learning","created":"2023-06-02","cited_by_count":44,"area":null},{"id":"2403.07384","title":"SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models","created":"2024-03-12","cited_by_count":44,"area":null},{"id":"2111.12621","title":"Accelerating Deep Learning with Dynamic Data Pruning","created":"2021-11-24","cited_by_count":43,"area":null},{"id":"2103.04173","title":"LongReMix: Robust Learning with High Confidence Samples in a Noisy Label Environment","created":"2021-03-06","cited_by_count":40,"area":null},{"id":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2311.13613","title":"Spanning Training Progress: Temporal Dual-Depth Scoring (TDDS) for Enhanced Dataset Pruning","created":"2023-11-22","cited_by_count":38,"area":null},{"id":"2210.15031","title":"Characterizing Datapoints via Second-Split Forgetting","created":"2022-10-26","cited_by_count":37,"area":null},{"id":"2103.15851","title":"Distilled Replay: Overcoming Forgetting through Synthetic Samples","created":"2021-03-29","cited_by_count":36,"area":null},{"id":"2109.06096","title":"The Grammar-Learning Trajectories of Neural Language Models","created":"2021-09-13","cited_by_count":36,"area":null},{"id":"2110.05922","title":"Trivial or impossible -- dichotomous data difficulty masks model differences (on ImageNet and beyond)","created":"2021-10-12","cited_by_count":35,"area":null},{"id":"2212.09744","title":"DSI++: Updating Transformer Memory with New Documents","created":"2022-12-19","cited_by_count":35,"area":null},{"id":"2301.00930","title":"Data Valuation Without Training of a Model","created":"2023-01-03","cited_by_count":35,"area":null},{"id":"2103.07492","title":"Continual Learning for Recurrent Neural Networks: an Empirical Evaluation","created":"2021-03-12","cited_by_count":34,"area":null},{"id":"2104.08656","title":"Learning from Noisy Labels for Entity-Centric Information Extraction","created":"2021-04-17","cited_by_count":34,"area":null},{"id":"2208.10494","title":"Dataset Condensation with Latent Space Knowledge Factorization and Sharing","created":"2022-08-21","cited_by_count":34,"area":null},{"id":"2209.08928","title":"UMIX: Improving Importance Weighting for Subpopulation Shift via Uncertainty-Aware Mixup","created":"2022-09-19","cited_by_count":34,"area":null},{"id":"2211.04446","title":"Private Set Generation with Discriminative Information","created":"2022-11-07","cited_by_count":34,"area":null},{"id":"2401.04578","title":"Effective pruning of web-scale datasets based on complexity of concept clusters","created":"2024-01-09","cited_by_count":34,"area":null},{"id":"2411.05735","title":"Aioli: A Unified Optimization Framework for Language Model Data Mixing","created":"2024-11-08","cited_by_count":34,"area":null},{"id":"2303.04449","title":"Loss-Curvature Matching for Dataset Selection and Condensation","created":"2023-03-08","cited_by_count":33,"area":null},{"id":"2403.05890","title":"Towards Efficient Replay in Federated Incremental Learning","created":"2024-03-09","cited_by_count":33,"area":null},{"id":"2409.17612","title":"Diversity-Driven Synthesis: Enhancing Dataset Distillation through Directed Weight Adjustment","created":"2024-09-26","cited_by_count":33,"area":null},{"id":"2105.00828","title":"Memorisation versus Generalisation in Pre-trained Language Models","created":"2021-04-16","cited_by_count":32,"area":null},{"id":"2210.13738","title":"Pruning's Effect on Generalization Through the Lens of Training and Regularization","created":"2022-10-25","cited_by_count":31,"area":null},{"id":"2404.00563","title":"Exploiting Inter-sample and Inter-feature Relations in Dataset Distillation","created":"2024-03-31","cited_by_count":31,"area":null},{"id":"2305.09253","title":"Online Continual Learning Without the Storage Constraint","created":"2023-05-16","cited_by_count":29,"area":null},{"id":"2402.02318","title":"Diversity Measurement and Subset Selection for Instruction Tuning Datasets","created":"2024-02-04","cited_by_count":29,"area":null},{"id":"2107.03860","title":"SSSE: Efficiently Erasing Samples from Trained Machine Learning Models","created":"2021-07-08","cited_by_count":28,"area":null},{"id":"2108.00219","title":"Grain: Improving Data Efficiency of Graph Neural Networks via Diversified Influence Maximization","created":"2021-07-31","cited_by_count":28,"area":null},{"id":"2312.05328","title":"Bad Students Make Great Teachers: Active Learning Accelerates Large-Scale Visual Understanding","created":"2023-12-08","cited_by_count":28,"area":null},{"id":"2505.17799","title":"A Coreset Selection of Coreset Selection Literature: Introduction and Recent Advances","created":"2025-05-23","cited_by_count":28,"area":null},{"id":"2209.14609","title":"Dataset Distillation Using Parameter Pruning","created":"2022-09-29","cited_by_count":27,"area":null},{"id":"2310.10873","title":"IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models","created":"2023-10-16","cited_by_count":27,"area":null},{"id":"2305.18424","title":"Repeated Random Sampling for Minimizing the Time-to-Accuracy of Learning","created":"2023-05-28","cited_by_count":26,"area":null},{"id":"2307.04138","title":"On The Impact of Machine Learning Randomness on Group Fairness","created":"2023-07-09","cited_by_count":26,"area":null},{"id":"2407.14245","title":"Dataset Distillation by Automatic Training Trajectories","created":"2024-07-19","cited_by_count":26,"area":null},{"id":"2410.05578","title":"Swift Sampler: Efficient Learning of Sampler by 10 Parameters","created":"2024-10-08","cited_by_count":25,"area":null},{"id":"2202.04108","title":"A Lagrangian Duality Approach to Active Learning","created":"2022-02-08","cited_by_count":24,"area":null},{"id":"2211.10801","title":"Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Training","created":"2022-11-19","cited_by_count":24,"area":null},{"id":"2312.12736","title":"Learning and Forgetting Unsafe Examples in Large Language Models","created":"2023-12-20","cited_by_count":24,"area":null},{"id":"2405.05012","title":"The Entropy Enigma: Success and Failure of Entropy Minimization","created":"2024-05-08","cited_by_count":24,"area":null}],"next_cursor":"100"}