{"total":83,"rows":[{"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":"2303.04947","title":"InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning","created":"2023-03-08","cited_by_count":90,"area":null},{"id":"2107.00717","title":"SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios","created":"2021-07-01","cited_by_count":84,"area":null},{"id":"2103.00128","title":"PRISM: A Rich Class of Parameterized Submodular Information Measures for Guided Subset Selection","created":"2021-02-27","cited_by_count":51,"area":null},{"id":"2308.10524","title":"Dataset Quantization","created":"2023-08-21","cited_by_count":48,"area":null},{"id":"2202.00132","title":"Submodularity In Machine Learning and Artificial Intelligence","created":"2022-01-31","cited_by_count":38,"area":null},{"id":"2106.15324","title":"Effective Evaluation of Deep Active Learning on Image Classification Tasks","created":"2021-06-16","cited_by_count":37,"area":null},{"id":"2208.00549","title":"Unifying Approaches in Active Learning and Active Sampling via Fisher Information and Information-Theoretic Quantities","created":"2022-08-01","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":"2112.00166","title":"TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices using Submodular Mutual Information","created":"2021-11-30","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":"2410.11215","title":"A CLIP-Powered Framework for Robust and Generalizable Data Selection","created":"2024-10-15","cited_by_count":21,"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":"2408.02193","title":"CodeACT: Code Adaptive Compute-efficient Tuning Framework for Code LLMs","created":"2024-08-05","cited_by_count":15,"area":null},{"id":"2105.14559","title":"Active Learning in Bayesian Neural Networks with Balanced Entropy Learning Principle","created":"2021-05-30","cited_by_count":14,"area":null},{"id":"2411.04425","title":"DELIFT: Data Efficient Language model Instruction Fine Tuning","created":"2024-11-07","cited_by_count":14,"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":"2210.01520","title":"CLINICAL: Targeted Active Learning for Imbalanced Medical Image Classification","created":"2022-10-04","cited_by_count":9,"area":null},{"id":"2408.14506","title":"Distilling Long-tailed Datasets","created":"2024-08-24","cited_by_count":9,"area":null},{"id":"2412.16895","title":"Adaptive Dataset Quantization","created":"2024-12-22","cited_by_count":9,"area":null},{"id":"2105.00043","title":"Submodular Mutual Information for Targeted Data Subset Selection","created":"2021-04-30","cited_by_count":8,"area":null},{"id":"2202.10680","title":"Submodlib: A Submodular Optimization Library","created":"2022-02-22","cited_by_count":8,"area":null},{"id":"2311.15547","title":"Dataset Distillation in Latent Space","created":"2023-11-27","cited_by_count":8,"area":null},{"id":"2206.08566","title":"Active Data Discovery: Mining Unknown Data using Submodular Information Measures","created":"2022-06-17","cited_by_count":6,"area":null},{"id":"2210.11033","title":"Neural Estimation of Submodular Functions with Applications to Differentiable Subset Selection","created":"2022-10-20","cited_by_count":6,"area":null},{"id":"2411.11329","title":"Color-Oriented Redundancy Reduction in Dataset Distillation","created":"2024-11-18","cited_by_count":6,"area":null},{"id":"2401.16193","title":"Contributing Dimension Structure of Deep Feature for Coreset Selection","created":"2024-01-29","cited_by_count":5,"area":null},{"id":"2402.03038","title":"Automatic Combination of Sample Selection Strategies for Few-Shot Learning","created":"2024-02-05","cited_by_count":5,"area":null},{"id":"2405.17535","title":"Calibrated Dataset Condensation for Faster Hyperparameter Search","created":"2024-05-27","cited_by_count":5,"area":null},{"id":"2504.12687","title":"Data-efficient LLM Fine-tuning for Code Generation","created":"2025-04-17","cited_by_count":5,"area":null},{"id":"2306.01277","title":"Beyond Active Learning: Leveraging the Full Potential of Human Interaction via Auto-Labeling, Human Correction, and Human Verification","created":"2023-06-02","cited_by_count":4,"area":null},{"id":"2405.18347","title":"Dataset Growth","created":"2024-05-28","cited_by_count":4,"area":null},{"id":"2407.05693","title":"Sub-SA: Strengthen In-context Learning via Submodular Selective Annotation","created":"2024-07-08","cited_by_count":4,"area":null},{"id":"2410.02268","title":"Structural-Entropy-Based Sample Selection for Efficient and Effective Learning","created":"2024-10-03","cited_by_count":4,"area":null},{"id":"2510.00303","title":"Looking Beyond the Known: Towards a Data Discovery Guided Open-World Object Detection","created":"2025-09-30","cited_by_count":4,"area":null},{"id":"2201.12928","title":"PLATINUM: Semi-Supervised Model Agnostic Meta-Learning using Submodular Mutual Information","created":"2022-01-30","cited_by_count":3,"area":null},{"id":"2207.01190","title":"Pareto Optimization for Active Learning under Out-of-Distribution Data Scenarios","created":"2022-07-04","cited_by_count":3,"area":null},{"id":"2405.17404","title":"Spectral Greedy Coresets for Graph Neural Networks","created":"2024-05-27","cited_by_count":3,"area":null},{"id":"2501.14991","title":"Advances in Set Function Learning: A Survey of Techniques and Applications","created":"2025-01-24","cited_by_count":3,"area":null},{"id":"2508.20230","title":"Coresets from Trajectories: Selecting Data via Correlation of Loss Differences","created":"2025-08-27","cited_by_count":3,"area":null},{"id":"2511.18858","title":"Rethinking Long-tailed Dataset Distillation: A Uni-Level Framework with Unbiased Recovery and Relabeling","created":"2025-11-24","cited_by_count":3,"area":null},{"id":"2605.23482","title":"Multimodal Distribution Matching for Vision-Language Dataset Distillation","created":"2026-05-22","cited_by_count":3,"area":null},{"id":"2305.06677","title":"INGENIOUS: Using Informative Data Subsets for Efficient Pre-Training of Language Models","created":"2023-05-11","cited_by_count":2,"area":null},{"id":"2305.10643","title":"STREAMLINE: Streaming Active Learning for Realistic Multi-Distributional Settings","created":"2023-05-18","cited_by_count":2,"area":null},{"id":"2306.07215","title":"Efficient and Robust Quantization-aware Training via Adaptive Coreset Selection","created":"2023-06-12","cited_by_count":2,"area":null},{"id":"2402.05356","title":"Exploring Learning Complexity for Efficient Downstream Dataset Pruning","created":"2024-02-08","cited_by_count":2,"area":null},{"id":"2505.24009","title":"Diversity of Transformer Layers: One Aspect of Parameter Scaling Laws","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2511.19476","title":"FAST: Topology-Aware Frequency-Domain Distribution Matching for Coreset Selection","created":"2025-11-22","cited_by_count":2,"area":null},{"id":"2606.08574","title":"OrderDP: A Theoretically Guaranteed Lossless Dynamic Data Pruning Framework","created":"2026-06-07","cited_by_count":2,"area":null},{"id":"2607.09739","title":"Coresets Before Score Sets: Evaluation-Unsupervised Prompt Subset Selection for LLM Benchmarks","created":"2026-07-02","cited_by_count":2,"area":null},{"id":"2210.01526","title":"DIAGNOSE: Avoiding Out-of-distribution Data using Submodular Information Measures","created":"2022-10-04","cited_by_count":1,"area":null},{"id":"2312.05751","title":"Benchmarking of Query Strategies: Towards Future Deep Active Learning","created":"2023-12-10","cited_by_count":1,"area":null},{"id":"2312.10366","title":"Fusing Conditional Submodular GAN and Programmatic Weak Supervision","created":"2023-12-16","cited_by_count":1,"area":null},{"id":"2402.05675","title":"Is Adversarial Training with Compressed Datasets Effective?","created":"2024-02-08","cited_by_count":1,"area":null},{"id":"2402.13454","title":"Theoretical Analysis of Submodular Information Measures for Targeted Data Subset Selection","created":"2024-02-21","cited_by_count":1,"area":null},{"id":"2402.16442","title":"On Distributed Larger-Than-Memory Subset Selection With Pairwise Submodular Functions","created":"2024-02-26","cited_by_count":1,"area":null},{"id":"2405.18754","title":"GIST: Greedy Independent Set Thresholding for Max-Min Diversification with Submodular Utility","created":"2024-05-29","cited_by_count":1,"area":null},{"id":"2501.14253","title":"Distributionally Robust Coreset Selection under Covariate Shift","created":"2025-01-24","cited_by_count":1,"area":null},{"id":"2507.02378","title":"Efficient Code LLM Training via Distribution-Consistent and Diversity-Aware Data Selection","created":"2025-07-03","cited_by_count":1,"area":null},{"id":"2508.21003","title":"InSQuAD: In-Context Learning for Efficient Retrieval via Submodular Mutual Information to Enforce Quality and Diversity","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2509.01221","title":"DaMoC: Efficiently Selecting the Optimal Large Language Model for Fine-tuning Domain Tasks Based on Data and Model Compression","created":"2025-09-01","cited_by_count":1,"area":null},{"id":"2602.05162","title":"SHaSaM: Submodular Hard Sample Mining for Fair Facial Attribute Recognition","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2604.18811","title":"Rethinking Dataset Distillation: Hard Truths about Soft Labels","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2605.12872","title":"SMA: Submodular Modality Aligner For Data Efficient Multimodal Learning","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2201.10547","title":"Optimal Data Selection: An Online Distributed View","created":"2022-01-25","cited_by_count":0,"area":null},{"id":"2203.05651","title":"BASIL: Balanced Active Semi-supervised Learning for Class Imbalanced Datasets","created":"2022-03-10","cited_by_count":0,"area":null},{"id":"2402.13468","title":"STENCIL: Submodular Mutual Information Based Weak Supervision for Cold-Start Active Learning","created":"2024-02-21","cited_by_count":0,"area":null},{"id":"2410.17715","title":"Continual Learning on a Data Diet","created":"2024-10-23","cited_by_count":0,"area":null},{"id":"2410.17945","title":"Theoretically Grounded Pruning of Large Ground Sets for Constrained, Discrete Optimization","created":"2024-10-23","cited_by_count":0,"area":null},{"id":"2502.15834","title":"Challenges of Multi-Modal Coreset Selection for Depth Prediction","created":"2025-02-20","cited_by_count":0,"area":null},{"id":"2506.22190","title":"dreaMLearning: Data Compression Assisted Machine Learning","created":"2025-06-27","cited_by_count":0,"area":null},{"id":"2509.21748","title":"SubZeroCore: A Submodular Approach with Zero Training for Coreset Selection","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2602.19113","title":"Learning from Complexity: Exploring Dynamic Sample Pruning of Spatio-Temporal Training","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2603.01698","title":"Towards Principled Dataset Distillation: A Spectral Distribution Perspective","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2603.06810","title":"Multi-Agent Reinforcement Learning with Submodular Reward","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2604.04681","title":"Batch Loss Score for Dynamic Data Pruning","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2604.07306","title":"Beyond Loss Values: Robust Dynamic Pruning via Loss Trajectory Alignment","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2605.14773","title":"Beyond What to Select: A Plug-and-play Oscillatory Data-Volume Scheduling for Efficient Model Training","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.24779","title":"Complement Submodular Information Measures for Balanced and Robust Data Selection","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.11761","title":"RCAP: Robust, Class-Aware, Probabilistic Dynamic Dataset Pruning","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2608.02690","title":"GLOBE: Trajectory-Aligned Gradient Matching with Structured SparseOptimization for Coreset Selection","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2610.00221","title":"Useful to Whom? The Easy-versus-Coverage Boundary Moves with the Learner","created":"2026-09-22","cited_by_count":0,"area":null}],"next_cursor":null}