{"total":310,"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":"2305.10429","title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining","created":"2023-05-17","cited_by_count":399,"area":null},{"id":"2302.03169","title":"Data Selection for Language Models via Importance Resampling","created":"2023-02-06","cited_by_count":329,"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":"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":"2202.00622","title":"Datamodels: Predicting Predictions from Training Data","created":"2022-02-01","cited_by_count":189,"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":"2402.00530","title":"Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning","created":"2024-02-01","cited_by_count":138,"area":null},{"id":"2404.07965","title":"Rho-1: Not All Tokens Are What You Need","created":"2024-04-11","cited_by_count":133,"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":"2210.15809","title":"Coverage-centric Coreset Selection for High Pruning Rates","created":"2022-10-28","cited_by_count":117,"area":null},{"id":"2301.05603","title":"A Comprehensive Survey of Dataset Distillation","created":"2023-01-13","cited_by_count":115,"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":"2401.12926","title":"DsDm: Model-Aware Dataset Selection with Datamodels","created":"2024-01-23","cited_by_count":105,"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":"2207.10062","title":"DataPerf: Benchmarks for Data-Centric AI Development","created":"2022-07-20","cited_by_count":90,"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":"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":"2101.11665","title":"On Statistical Bias In Active Learning: How and When To Fix It","created":"2021-01-27","cited_by_count":75,"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":"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":"2207.13887","title":"Adaptive Second Order Coresets for Data-efficient Machine Learning","created":"2022-07-28","cited_by_count":60,"area":null},{"id":"2209.14981","title":"Stop Wasting My Time! Saving Days of ImageNet and BERT Training with Latest Weight Averaging","created":"2022-09-29","cited_by_count":54,"area":null},{"id":"2203.09410","title":"A Framework and Benchmark for Deep Batch Active Learning for Regression","created":"2022-03-17","cited_by_count":49,"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":"2308.10524","title":"Dataset Quantization","created":"2023-08-21","cited_by_count":48,"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":"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":"2310.09748","title":"Large Language Model-Aware In-Context Learning for Code Generation","created":"2023-10-15","cited_by_count":43,"area":null},{"id":"2307.06440","title":"No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models","created":"2023-07-12","cited_by_count":41,"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":"2311.00913","title":"Self-Influence Guided Data Reweighting for Language Model Pre-training","created":"2023-11-02","cited_by_count":37,"area":null},{"id":"2111.12084","title":"Self-Supervised Pre-Training for Transformer-Based Person Re-Identification","created":"2021-11-23","cited_by_count":36,"area":null},{"id":"2205.12600","title":"ORCA: Interpreting Prompted Language Models via Locating Supporting Data Evidence in the Ocean of Pretraining Data","created":"2022-05-25","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":"2303.04449","title":"Loss-Curvature Matching for Dataset Selection and Condensation","created":"2023-03-08","cited_by_count":33,"area":null},{"id":"2406.17711","title":"Data curation via joint example selection further accelerates multimodal learning","created":"2024-06-25","cited_by_count":33,"area":null},{"id":"2405.02774","title":"Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs","created":"2024-05-05","cited_by_count":32,"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":"2402.07625","title":"Autonomous Data Selection with Zero-shot Generative Classifiers for Mathematical Texts","created":"2024-02-12","cited_by_count":27,"area":null},{"id":"2207.01725","title":"How Much More Data Do I Need? Estimating Requirements for Downstream Tasks","created":"2022-07-04","cited_by_count":23,"area":null},{"id":"2305.13865","title":"Selective Pre-training for Private Fine-tuning","created":"2023-05-23","cited_by_count":23,"area":null},{"id":"2401.06692","title":"An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models","created":"2024-01-12","cited_by_count":23,"area":null},{"id":"2302.09195","title":"Data-Efficient Contrastive Self-supervised Learning: Most Beneficial Examples for Supervised Learning Contribute the Least","created":"2023-02-18","cited_by_count":22,"area":null},{"id":"2502.06905","title":"Lightweight Dataset Pruning without Full Training via Example Difficulty and Prediction Uncertainty","created":"2025-02-10","cited_by_count":22,"area":null},{"id":"2306.03208","title":"NLU on Data Diets: Dynamic Data Subset Selection for NLP Classification Tasks","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2306.09910","title":"LabelBench: A Comprehensive Framework for Benchmarking Adaptive Label-Efficient Learning","created":"2023-06-16","cited_by_count":20,"area":null},{"id":"2310.14019","title":"You Only Condense Once: Two Rules for Pruning Condensed Datasets","created":"2023-10-21","cited_by_count":20,"area":null},{"id":"2311.01002","title":"Robust Data Pruning under Label Noise via Maximizing Re-labeling Accuracy","created":"2023-11-02","cited_by_count":20,"area":null},{"id":"2403.12267","title":"Data-Efficient Contrastive Language-Image Pretraining: Prioritizing Data Quality over Quantity","created":"2024-03-18","cited_by_count":19,"area":null},{"id":"2405.00705","title":"SHED: Shapley-Based Automated Dataset Refinement for Instruction Fine-Tuning","created":"2024-04-23","cited_by_count":19,"area":null},{"id":"2404.09161","title":"Coreset Selection for Object Detection","created":"2024-04-14","cited_by_count":18,"area":null},{"id":"2310.05674","title":"Making Scalable Meta Learning Practical","created":"2023-10-09","cited_by_count":17,"area":null},{"id":"2406.02378","title":"On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Concept","created":"2024-06-04","cited_by_count":16,"area":null},{"id":"2210.01234","title":"Optimizing Data Collection for Machine Learning","created":"2022-10-03","cited_by_count":15,"area":null},{"id":"2305.13016","title":"Iterative Forward Tuning Boosts In-Context Learning in Language Models","created":"2023-05-22","cited_by_count":15,"area":null},{"id":"2406.01063","title":"DANCE: Dual-View Distribution Alignment for Dataset Condensation","created":"2024-06-03","cited_by_count":15,"area":null},{"id":"2505.14826","title":"FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain","created":"2025-05-20","cited_by_count":15,"area":null},{"id":"2506.01701","title":"Data Pruning by Information Maximization","created":"2025-06-02","cited_by_count":15,"area":null},{"id":"2106.04784","title":"Accelerating Neural Architecture Search via Proxy Data","created":"2021-06-09","cited_by_count":14,"area":null},{"id":"2303.05151","title":"Provable Data Subset Selection For Efficient Neural Network Training","created":"2023-03-09","cited_by_count":14,"area":null},{"id":"2406.04872","title":"Diversified Batch Selection for Training Acceleration","created":"2024-06-07","cited_by_count":14,"area":null},{"id":"2408.12483","title":"Not All Samples Should Be Utilized Equally: Towards Understanding and Improving Dataset Distillation","created":"2024-08-22","cited_by_count":14,"area":null},{"id":"2302.12366","title":"Less is More: Data Pruning for Faster Adversarial Training","created":"2023-02-23","cited_by_count":13,"area":null},{"id":"2407.07268","title":"Dataset Quantization with Active Learning based Adaptive Sampling","created":"2024-07-09","cited_by_count":13,"area":null},{"id":"2409.12255","title":"Efficient Data Subset Selection to Generalize Training Across Models: Transductive and Inductive Networks","created":"2024-09-18","cited_by_count":13,"area":null},{"id":"2410.02536","title":"Intelligence at the Edge of Chaos","created":"2024-10-03","cited_by_count":13,"area":null},{"id":"2506.02281","title":"Angles Don't Lie: Unlocking Training-Efficient RL Through the Model's Own Signals","created":"2025-06-02","cited_by_count":13,"area":null},{"id":"2302.08981","title":"Black-Box Batch Active Learning for Regression","created":"2023-02-17","cited_by_count":12,"area":null},{"id":"2202.00390","title":"Minority Class Oriented Active Learning for Imbalanced Datasets","created":"2022-02-01","cited_by_count":11,"area":null},{"id":"2302.06960","title":"Data pruning and neural scaling laws: fundamental limitations of score-based algorithms","created":"2023-02-14","cited_by_count":11,"area":null},{"id":"2308.10544","title":"Towards Accelerated Model Training via Bayesian Data Selection","created":"2023-08-21","cited_by_count":11,"area":null},{"id":"2302.12018","title":"Gaussian Switch Sampling: A Second Order Approach to Active Learning","created":"2023-02-16","cited_by_count":10,"area":null},{"id":"2406.04273","title":"ELFS: Label-Free Coreset Selection with Proxy Training Dynamics","created":"2024-06-06","cited_by_count":10,"area":null},{"id":"2411.15349","title":"Zero-Shot Coreset Selection via Iterative Subspace Sampling","created":"2024-11-22","cited_by_count":10,"area":null},{"id":"2301.13287","title":"MILO: Model-Agnostic Subset Selection Framework for Efficient Model Training and Tuning","created":"2023-01-30","cited_by_count":9,"area":null},{"id":"2409.01081","title":"Beyond Efficiency: Molecular Data Pruning for Enhanced Generalization","created":"2024-09-02","cited_by_count":9,"area":null},{"id":"2410.10636","title":"Adapt-$\\infty$: Scalable Continual Multimodal Instruction Tuning via Dynamic Data Selection","created":"2024-10-14","cited_by_count":9,"area":null},{"id":"2412.16895","title":"Adaptive Dataset Quantization","created":"2024-12-22","cited_by_count":9,"area":null},{"id":"2506.02011","title":"OASIS: Online Sample Selection for Continual Visual Instruction Tuning","created":"2025-05-27","cited_by_count":9,"area":null},{"id":"2109.12534","title":"Data Summarization via Bilevel Optimization","created":"2021-09-26","cited_by_count":8,"area":null},{"id":"2201.04768","title":"On Sampling Collaborative Filtering Datasets","created":"2022-01-13","cited_by_count":8,"area":null},{"id":"2302.12948","title":"Agile Modeling: From Concept to Classifier in Minutes","created":"2023-02-25","cited_by_count":8,"area":null},{"id":"2303.11114","title":"SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage","created":"2023-03-20","cited_by_count":8,"area":null},{"id":"2305.06408","title":"Accelerating Batch Active Learning Using Continual Learning Techniques","created":"2023-05-10","cited_by_count":8,"area":null},{"id":"2311.05436","title":"Fair Wasserstein Coresets","created":"2023-11-09","cited_by_count":8,"area":null},{"id":"2406.03057","title":"BWS: Best Window Selection Based on Sample Scores for Data Pruning across Broad Ranges","created":"2024-06-05","cited_by_count":8,"area":null},{"id":"2410.13761","title":"GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning","created":"2024-10-17","cited_by_count":8,"area":null},{"id":"2107.02565","title":"Prioritized training on points that are learnable, worth learning, and not yet learned (workshop version)","created":"2021-07-06","cited_by_count":7,"area":null},{"id":"2112.02504","title":"A Novel Sequential Coreset Method for Gradient Descent Algorithms","created":"2021-12-05","cited_by_count":7,"area":null}],"next_cursor":"100"}