{"total":111,"rows":[{"id":"2212.04612","title":"Training Data Influence Analysis and Estimation: A Survey","created":"2022-12-09","cited_by_count":135,"area":null},{"id":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","cited_by_count":122,"area":null},{"id":"2206.07746","title":"Condensing Graphs via One-Step Gradient Matching","created":"2022-06-15","cited_by_count":100,"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":"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":"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":"2405.00334","title":"A Survey on Deep Active Learning: Recent Advances and New Frontiers","created":"2024-05-01","cited_by_count":54,"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":"2310.09192","title":"Does Graph Distillation See Like Vision Dataset Counterpart?","created":"2023-10-13","cited_by_count":45,"area":null},{"id":"2409.18153","title":"Most Influential Subset Selection: Challenges, Promises, and Beyond","created":"2024-09-25","cited_by_count":32,"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":"2407.14245","title":"Dataset Distillation by Automatic Training Trajectories","created":"2024-07-19","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":"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":"2310.14019","title":"You Only Condense Once: Two Rules for Pruning Condensed Datasets","created":"2023-10-21","cited_by_count":20,"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":"2506.01701","title":"Data Pruning by Information Maximization","created":"2025-06-02","cited_by_count":15,"area":null},{"id":"2306.11670","title":"GIO: Gradient Information Optimization for Training Dataset Selection","created":"2023-06-20","cited_by_count":13,"area":null},{"id":"2311.08675","title":"Refined Coreset Selection: Towards Minimal Coreset Size under Model Performance Constraints","created":"2023-11-15","cited_by_count":13,"area":null},{"id":"2501.18578","title":"R.I.P.: Better Models by Survival of the Fittest Prompts","created":"2025-01-30","cited_by_count":13,"area":null},{"id":"2502.14709","title":"Group-Level Data Selection for Efficient Pretraining","created":"2025-02-20","cited_by_count":13,"area":null},{"id":"2310.08782","title":"Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning","created":"2023-10-13","cited_by_count":11,"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":"2405.03869","title":"Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Models","created":"2024-05-06","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":"2408.03560","title":"In2Core: Leveraging Influence Functions for Coreset Selection in Instruction Finetuning of Large Language Models","created":"2024-08-07","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":"2305.18381","title":"Distill Gold from Massive Ores: Bi-level Data Pruning towards Efficient Dataset Distillation","created":"2023-05-28","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":"2312.05586","title":"Deeper Understanding of Black-box Predictions via Generalized Influence Functions","created":"2023-12-09","cited_by_count":7,"area":null},{"id":"2406.05677","title":"Evolution-aware VAriance (EVA) Coreset Selection for Medical Image Classification","created":"2024-06-09","cited_by_count":7,"area":null},{"id":"2503.00828","title":"Training-Free Dataset Pruning for Instance Segmentation","created":"2025-03-02","cited_by_count":7,"area":null},{"id":"2503.13385","title":"Scale Efficient Training for Large Datasets","created":"2025-03-17","cited_by_count":7,"area":null},{"id":"2512.11668","title":"Bridging Streaming Continual Learning via In-Context Large Tabular Models","created":"2025-12-12","cited_by_count":7,"area":null},{"id":"2310.00840","title":"Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models","created":"2023-10-02","cited_by_count":6,"area":null},{"id":"2310.16776","title":"DEFT: Data Efficient Fine-Tuning for Pre-Trained Language Models via Unsupervised Core-Set Selection","created":"2023-10-25","cited_by_count":6,"area":null},{"id":"2408.03506","title":"1.5-Pints Technical Report: Pretraining in Days, Not Months -- Your Language Model Thrives on Quality Data","created":"2024-08-07","cited_by_count":6,"area":null},{"id":"2411.09126","title":"SCAN: Bootstrapping Contrastive Pre-training for Data Efficiency","created":"2024-11-14","cited_by_count":6,"area":null},{"id":"2502.06434","title":"Unifying Dataset Pruning and Distillation for Efficient Large-scale Compression","created":"2025-02-10","cited_by_count":6,"area":null},{"id":"2505.03809","title":"When Dynamic Data Selection Meets Data Augmentation","created":"2025-05-02","cited_by_count":6,"area":null},{"id":"2407.06120","title":"Sketchy Moment Matching: Toward Fast and Provable Data Selection for Finetuning","created":"2024-07-08","cited_by_count":5,"area":null},{"id":"2411.15796","title":"Data Lineage Inference: Uncovering Privacy Vulnerabilities of Dataset Pruning","created":"2024-11-24","cited_by_count":5,"area":null},{"id":"2212.01452","title":"CLIP: Train Faster with Less Data","created":"2022-12-02","cited_by_count":4,"area":null},{"id":"2406.11730","title":"CHG Shapley: Efficient Data Valuation and Selection towards Trustworthy Machine Learning","created":"2024-06-17","cited_by_count":4,"area":null},{"id":"2501.02432","title":"Swift Cross-Dataset Pruning: Enhancing Fine-Tuning Efficiency in Natural Language Understanding","created":"2025-01-05","cited_by_count":4,"area":null},{"id":"2505.22342","title":"Progressive Data Dropout: An Embarrassingly Simple Approach to Faster Training","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2312.05599","title":"Not All Data Matters: An End-to-End Adaptive Dataset Pruning Framework for Enhancing Model Performance and Efficiency","created":"2023-12-09","cited_by_count":3,"area":null},{"id":"2411.00360","title":"A Simple Remedy for Dataset Bias via Self-Influence: A Mislabeled Sample Perspective","created":"2024-11-01","cited_by_count":3,"area":null},{"id":"2412.00111","title":"Video Set Distillation: Information Diversification and Temporal Densification","created":"2024-11-28","cited_by_count":3,"area":null},{"id":"2506.23674","title":"Partial Forward Blocking: A Novel Data Pruning Paradigm for Lossless Training Acceleration","created":"2025-06-30","cited_by_count":3,"area":null},{"id":"2508.14648","title":"Understanding Data Influence with Differential Approximation","created":"2025-08-20","cited_by_count":3,"area":null},{"id":"2510.03247","title":"Towards Multimodal Active Learning: Efficient Learning with Limited Paired Data","created":"2025-09-25","cited_by_count":3,"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":"2405.11465","title":"Effective In-Context Example Selection through Data Compression","created":"2024-05-19","cited_by_count":2,"area":null},{"id":"2406.13283","title":"Large-Scale Dataset Pruning in Adversarial Training through Data Importance Extrapolation","created":"2024-06-19","cited_by_count":2,"area":null},{"id":"2409.13915","title":"Data Pruning via Separability, Integrity, and Model Uncertainty-Aware Importance Sampling","created":"2024-09-20","cited_by_count":2,"area":null},{"id":"2410.07158","title":"Quanda: An Interpretability Toolkit for Training Data Attribution Evaluation and Beyond","created":"2024-10-09","cited_by_count":2,"area":null},{"id":"2412.10091","title":"Data Pruning Can Do More: A Comprehensive Data Pruning Approach for Object Re-identification","created":"2024-12-13","cited_by_count":2,"area":null},{"id":"2506.09010","title":"Effective Data Pruning through Score Extrapolation","created":"2025-06-10","cited_by_count":2,"area":null},{"id":"2507.06931","title":"DICE: Data Influence Cascade in Decentralized Learning","created":"2025-07-09","cited_by_count":2,"area":null},{"id":"2510.24262","title":"UtilGen: Utility-Centric Generative Data Augmentation with Dual-Level Task Adaptation","created":"2025-10-28","cited_by_count":2,"area":null},{"id":"2603.04981","title":"Rethinking Representativeness and Diversity in Dynamic Data Selection","created":"2026-03-05","cited_by_count":2,"area":null},{"id":"2603.07433","title":"Data Agent: Learning to Select Data via End-to-End Dynamic Optimization","created":"2026-03-08","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":"2311.14468","title":"Online Importance Sampling for Stochastic Gradient Optimization","created":"2023-11-24","cited_by_count":1,"area":null},{"id":"2405.03228","title":"TED: Accelerate Model Training by Internal Generalization","created":"2024-05-06","cited_by_count":1,"area":null},{"id":"2406.17188","title":"Geometric Median (GM) Matching for Robust Data Pruning","created":"2024-06-25","cited_by_count":1,"area":null},{"id":"2408.14763","title":"Channel Matters: Estimating Channel Influence for Multivariate Time Series","created":"2024-08-27","cited_by_count":1,"area":null},{"id":"2412.00684","title":"Paint Outside the Box: Synthesizing and Selecting Training Data for Visual Grounding","created":"2024-12-01","cited_by_count":1,"area":null},{"id":"2504.00564","title":"Geometric Median Matching for Robust k-Subset Selection from Noisy Data","created":"2025-04-01","cited_by_count":1,"area":null},{"id":"2504.17132","title":"Latent Video Dataset Distillation","created":"2025-04-23","cited_by_count":1,"area":null},{"id":"2507.12750","title":"Multimodal-Guided Dynamic Dataset Pruning for Robust and Efficient Data-Centric Learning","created":"2025-07-17","cited_by_count":1,"area":null},{"id":"2510.26185","title":"Accumulative SGD Influence Estimation for Data Attribution","created":"2025-10-30","cited_by_count":1,"area":null},{"id":"2512.06950","title":"PARIS: Pruning Algorithm via the Representer theorem for Imbalanced Scenarios","created":"2025-12-07","cited_by_count":1,"area":null},{"id":"2512.13083","title":"DiRe: Diversity-promoting Regularization for Dataset Condensation","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2602.05393","title":"Late-to-Early Training: LET LLMs Learn Earlier, So Faster and Better","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2603.17684","title":"Does YOLO Really Need to See Every Training Image in Every Epoch?","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2604.12945","title":"Adaptive Data Dropout: Towards Self-Regulated Learning in Deep Neural Networks","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2306.04663","title":"U-PASS: an Uncertainty-guided deep learning Pipeline for Automated Sleep Staging","created":"2023-06-07","cited_by_count":0,"area":null},{"id":"2308.07662","title":"Gradient-Based Post-Training Quantization: Challenging the Status Quo","created":"2023-08-15","cited_by_count":0,"area":null},{"id":"2403.16557","title":"Accelerating Federated Learning by Selecting Beneficial Herd of Local Gradients","created":"2024-03-25","cited_by_count":0,"area":null},{"id":"2406.01086","title":"Diverse Subset Selection via Norm-Based Sampling and Orthogonality","created":"2024-06-03","cited_by_count":0,"area":null},{"id":"2406.14207","title":"LayerMatch: Do Pseudo-labels Benefit All Layers?","created":"2024-06-20","cited_by_count":0,"area":null},{"id":"2408.16031","title":"EMP: Enhance Memory in Data Pruning","created":"2024-08-28","cited_by_count":0,"area":null},{"id":"2409.12076","title":"Unsupervised Domain Adaptation Via Data Pruning","created":"2024-09-18","cited_by_count":0,"area":null},{"id":"2410.03790","title":"Accelerating Deep Learning with Fixed Time Budget","created":"2024-10-03","cited_by_count":0,"area":null},{"id":"2410.14254","title":"RAZOR: Refining Accuracy by Zeroing Out Redundancies","created":"2024-10-18","cited_by_count":0,"area":null},{"id":"2504.07742","title":"Gradient-based Sample Selection for Faster Bayesian Optimization","created":"2025-04-10","cited_by_count":0,"area":null},{"id":"2505.15272","title":"DiffProb: Data Pruning for Face Recognition","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2507.04269","title":"Efficient Training of Deep Networks using Guided Spectral Data Selection: A Step Toward Learning What You Need","created":"2025-07-06","cited_by_count":0,"area":null},{"id":"2507.09001","title":"Surprisingly High Redundancy in Electronic Structure Data Across Materials Explained by Low Intrinsic Dimensionality","created":"2025-07-11","cited_by_count":0,"area":null},{"id":"2509.07319","title":"MEGG: Replay via Maximally Extreme GGscore in Incremental Learning for Neural Recommendation Models","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2509.07909","title":"Uncovering Scaling Laws for Large Language Models via Inverse Problems","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2510.03950","title":"What Is The Performance Ceiling of My Classifier? Utilizing Category-Wise Influence Functions for Pareto Frontier Analysis","created":"2025-10-04","cited_by_count":0,"area":null},{"id":"2510.26776","title":"Faithful and Fast Influence Function via Advanced Sampling","created":"2025-10-30","cited_by_count":0,"area":null},{"id":"2511.15276","title":"SNAP: Low-Latency Test-Time Adaptation with Sparse Updates","created":"2025-11-19","cited_by_count":0,"area":null},{"id":"2512.05987","title":"Adaptive Dataset Quantization: A New Direction for Dataset Pruning","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2602.19756","title":"Multimodal Dataset Distillation Made Simple by Prototype-Guided Data Synthesis","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2602.20650","title":"Dataset Color Quantization: A Training-Oriented Framework for Dataset-Level Compression","created":"2026-02-24","cited_by_count":0,"area":null}],"next_cursor":"100"}