{"total":230,"rows":[{"id":"2309.12284","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","created":"2023-09-21","cited_by_count":735,"area":"synth"},{"id":"2203.11932","title":"Dataset Distillation by Matching Training Trajectories","created":"2022-03-22","cited_by_count":442,"area":null},{"id":"2105.10056","title":"Data-Free Knowledge Distillation for Heterogeneous Federated Learning","created":"2021-05-20","cited_by_count":383,"area":"distill"},{"id":"2110.04181","title":"Dataset Condensation with Distribution Matching","created":"2021-10-08","cited_by_count":365,"area":null},{"id":"2102.08259","title":"Dataset Condensation with Differentiable Siamese Augmentation","created":"2021-02-16","cited_by_count":291,"area":null},{"id":"2105.15183","title":"Efficient and Modular Implicit Differentiation","created":"2021-05-31","cited_by_count":203,"area":null},{"id":"2206.00719","title":"Dataset Distillation using Neural Feature Regression","created":"2022-06-01","cited_by_count":177,"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":"2211.11004","title":"Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation","created":"2022-11-20","cited_by_count":142,"area":null},{"id":"2306.13092","title":"Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective","created":"2023-06-22","cited_by_count":138,"area":null},{"id":"2301.07014","title":"Dataset Distillation: A Comprehensive Review","created":"2023-01-17","cited_by_count":127,"area":null},{"id":"2305.01649","title":"Generalizing Dataset Distillation via Deep Generative Prior","created":"2023-05-02","cited_by_count":126,"area":null},{"id":"2306.04140","title":"Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventions","created":"2023-06-07","cited_by_count":125,"area":null},{"id":"2307.09742","title":"Improved Distribution Matching for Dataset Condensation","created":"2023-07-19","cited_by_count":124,"area":null},{"id":"2301.05603","title":"A Comprehensive Survey of Dataset Distillation","created":"2023-01-13","cited_by_count":115,"area":null},{"id":"2202.02916","title":"Dataset Condensation with Contrastive Signals","created":"2022-02-07","cited_by_count":105,"area":null},{"id":"2207.09639","title":"DC-BENCH: Dataset Condensation Benchmark","created":"2022-07-20","cited_by_count":67,"area":null},{"id":"2212.06152","title":"Accelerating Dataset Distillation via Model Augmentation","created":"2022-12-12","cited_by_count":62,"area":null},{"id":"2309.09455","title":"CaT: Balanced Continual Graph Learning with Graph Condensation","created":"2023-09-18","cited_by_count":52,"area":null},{"id":"2104.02857","title":"Soft-Label Anonymous Gastric X-ray Image Distillation","created":"2021-04-07","cited_by_count":51,"area":null},{"id":"2112.01528","title":"A Fast Knowledge Distillation Framework for Visual Recognition","created":"2021-12-02","cited_by_count":50,"area":"distill"},{"id":"2208.11311","title":"Federated Learning via Decentralized Dataset Distillation in Resource-Constrained Edge Environments","created":"2022-08-24","cited_by_count":49,"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":"2107.12603","title":"Federated Learning Meets Natural Language Processing: A Survey","created":"2021-07-27","cited_by_count":43,"area":null},{"id":"2308.00788","title":"An Introduction to Bi-level Optimization: Foundations and Applications in Signal Processing and Machine Learning","created":"2023-08-01","cited_by_count":41,"area":null},{"id":"2208.00311","title":"Delving into Effective Gradient Matching for Dataset Condensation","created":"2022-07-30","cited_by_count":40,"area":null},{"id":"2404.13733","title":"Elucidating the Design Space of Dataset Condensation","created":"2024-04-21","cited_by_count":40,"area":null},{"id":"2102.02515","title":"HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks","created":"2021-02-04","cited_by_count":38,"area":null},{"id":"2209.14635","title":"Compressed Gastric Image Generation Based on Soft-Label Dataset Distillation for Medical Data Sharing","created":"2022-09-29","cited_by_count":35,"area":null},{"id":"2211.04446","title":"Private Set Generation with Discriminative Information","created":"2022-11-07","cited_by_count":34,"area":null},{"id":"2204.04213","title":"Structure-aware Protein Self-supervised Learning","created":"2022-04-06","cited_by_count":33,"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":"2404.18962","title":"An Aggregation-Free Federated Learning for Tackling Data Heterogeneity","created":"2024-04-29","cited_by_count":33,"area":null},{"id":"2305.01975","title":"A Survey on Dataset Distillation: Approaches, Applications and Future Directions","created":"2023-05-03","cited_by_count":32,"area":null},{"id":"2204.01273","title":"FedSynth: Gradient Compression via Synthetic Data in Federated Learning","created":"2022-04-04","cited_by_count":31,"area":null},{"id":"2206.11849","title":"Sample Condensation in Online Continual Learning","created":"2022-06-23","cited_by_count":31,"area":null},{"id":"2307.15967","title":"Graph Condensation for Inductive Node Representation Learning","created":"2023-07-29","cited_by_count":31,"area":null},{"id":"2311.18531","title":"Dataset Distillation via the Wasserstein Metric","created":"2023-11-30","cited_by_count":31,"area":null},{"id":"2406.10485","title":"A Label is Worth a Thousand Images in Dataset Distillation","created":"2024-06-15","cited_by_count":31,"area":null},{"id":"2206.12543","title":"A Fast, Well-Founded Approximation to the Empirical Neural Tangent Kernel","created":"2022-06-25","cited_by_count":30,"area":null},{"id":"2106.09613","title":"Meta-Calibration: Learning of Model Calibration Using Differentiable Expected Calibration Error","created":"2021-06-17","cited_by_count":29,"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":"2207.11719","title":"Gradient-based Bi-level Optimization for Deep Learning: A Survey","created":"2022-07-24","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":"2502.05673","title":"The Evolution of Dataset Distillation: Toward Scalable and Generalizable Solutions","created":"2025-02-08","cited_by_count":26,"area":null},{"id":"2209.14603","title":"Dataset Distillation for Medical Dataset Sharing","created":"2022-09-29","cited_by_count":25,"area":null},{"id":"2301.01197","title":"Backdoor Attacks Against Dataset Distillation","created":"2023-01-03","cited_by_count":21,"area":null},{"id":"2307.10655","title":"A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiency","created":"2023-07-20","cited_by_count":21,"area":null},{"id":"2102.09890","title":"Condensed Composite Memory Continual Learning","created":"2021-02-19","cited_by_count":20,"area":null},{"id":"2204.12493","title":"One-shot Federated Learning without Server-side Training","created":"2022-04-26","cited_by_count":20,"area":null},{"id":"2207.05409","title":"Knowledge Condensation Distillation","created":"2022-07-12","cited_by_count":20,"area":"distill"},{"id":"2305.16645","title":"Summarizing Stream Data for Memory-Constrained Online Continual Learning","created":"2023-05-26","cited_by_count":19,"area":null},{"id":"2402.06971","title":"In-Context Data Distillation with TabPFN","created":"2024-02-10","cited_by_count":19,"area":null},{"id":"2404.17732","title":"Generative Dataset Distillation: Balancing Global Structure and Local Details","created":"2024-04-26","cited_by_count":18,"area":null},{"id":"2403.10045","title":"Towards Adversarially Robust Dataset Distillation by Curvature Regularization","created":"2024-03-15","cited_by_count":17,"area":null},{"id":"2207.11727","title":"Can we achieve robustness from data alone?","created":"2022-07-24","cited_by_count":16,"area":null},{"id":"2303.01687","title":"Differentially Private Neural Tangent Kernels for Privacy-Preserving Data Generation","created":"2023-03-03","cited_by_count":15,"area":null},{"id":"2403.11395","title":"Automated data processing and feature engineering for deep learning and big data applications: a survey","created":"2024-03-18","cited_by_count":14,"area":null},{"id":"2408.16236","title":"Neural Spectral Decomposition for Dataset Distillation","created":"2024-08-29","cited_by_count":14,"area":null},{"id":"2302.00617","title":"Learning Large-scale Neural Fields via Context Pruned Meta-Learning","created":"2023-02-01","cited_by_count":13,"area":null},{"id":"2406.05704","title":"Hierarchical Features Matter: A Deep Exploration of Progressive Parameterization Method for Dataset Distillation","created":"2024-06-09","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":"2408.08610","title":"Generative Dataset Distillation Based on Diffusion Model","created":"2024-08-16","cited_by_count":13,"area":"diffusion"},{"id":"2410.07579","title":"Teddy: Efficient Large-Scale Dataset Distillation via Taylor-Approximated Matching","created":"2024-10-10","cited_by_count":13,"area":null},{"id":"2601.18778","title":"Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability","created":"2026-01-26","cited_by_count":13,"area":"lr"},{"id":"2205.01915","title":"Generalized Knowledge Distillation via Relationship Matching","created":"2022-05-04","cited_by_count":12,"area":"distill"},{"id":"2205.12449","title":"MAVIPER: Learning Decision Tree Policies for Interpretable Multi-Agent Reinforcement Learning","created":"2022-05-25","cited_by_count":12,"area":null},{"id":"2312.15520","title":"Graph Coarsening via Convolution Matching for Scalable Graph Neural Network Training","created":"2023-12-24","cited_by_count":12,"area":null},{"id":"2203.08559","title":"Learning to Generate Synthetic Training Data using Gradient Matching and Implicit Differentiation","created":"2022-03-16","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":"2403.07854","title":"Distilling the Knowledge in Data Pruning","created":"2024-03-12","cited_by_count":11,"area":"distill"},{"id":"2102.03919","title":"Mitigating belief projection in explainable artificial intelligence via Bayesian Teaching","created":"2021-02-07","cited_by_count":10,"area":null},{"id":"2207.01566","title":"General Policy Evaluation and Improvement by Learning to Identify Few But Crucial States","created":"2022-07-04","cited_by_count":10,"area":null},{"id":"2210.06205","title":"On Divergence Measures for Bayesian Pseudocoresets","created":"2022-10-12","cited_by_count":10,"area":null},{"id":"2401.12231","title":"Disentangled Condensation for Large-scale Graphs","created":"2024-01-18","cited_by_count":10,"area":null},{"id":"2505.19469","title":"Diversity-Driven Generative Dataset Distillation Based on Diffusion Model with Self-Adaptive Memory","created":"2025-05-26","cited_by_count":10,"area":"diffusion"},{"id":"2106.10575","title":"EvoGrad: Efficient Gradient-Based Meta-Learning and Hyperparameter Optimization","created":"2021-06-19","cited_by_count":9,"area":null},{"id":"2203.06905","title":"Less is More: Proxy Datasets in NAS approaches","created":"2022-03-14","cited_by_count":9,"area":null},{"id":"2208.10531","title":"RAIN: RegulArization on Input and Network for Black-Box Domain Adaptation","created":"2022-08-22","cited_by_count":9,"area":null},{"id":"2311.15772","title":"Attend Who is Weak: Enhancing Graph Condensation via Cross-Free Adversarial Training","created":"2023-11-27","cited_by_count":9,"area":null},{"id":"2312.14439","title":"PUMA: Efficient Continual Graph Learning for Node Classification with Graph Condensation","created":"2023-12-22","cited_by_count":9,"area":null},{"id":"2406.10861","title":"Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions","created":"2024-06-16","cited_by_count":9,"area":"distill"},{"id":"2408.10210","title":"A Survey on Symbolic Knowledge Distillation of Large Language Models","created":"2024-07-12","cited_by_count":9,"area":"distill"},{"id":"2412.16895","title":"Adaptive Dataset Quantization","created":"2024-12-22","cited_by_count":9,"area":null},{"id":"2503.18267","title":"Enhancing Dataset Distillation via Non-Critical Region Refinement","created":"2025-03-24","cited_by_count":9,"area":null},{"id":"2210.17467","title":"Iterative Teaching by Data Hallucination","created":"2022-10-31","cited_by_count":8,"area":null},{"id":"2302.09726","title":"Nystrom Method for Accurate and Scalable Implicit Differentiation","created":"2023-02-20","cited_by_count":8,"area":null},{"id":"2402.04924","title":"Two Trades is not Baffled: Condensing Graph via Crafting Rational Gradient Matching","created":"2024-02-07","cited_by_count":8,"area":null},{"id":"2403.13322","title":"DD-RobustBench: An Adversarial Robustness Benchmark for Dataset Distillation","created":"2024-03-20","cited_by_count":8,"area":null},{"id":"2405.03911","title":"Federated Graph Condensation with Information Bottleneck Principles","created":"2024-05-07","cited_by_count":8,"area":null},{"id":"2502.17788","title":"On-device edge learning for IoT data streams: a survey","created":"2025-02-25","cited_by_count":8,"area":null},{"id":"2507.03331","title":"Task-Specific Generative Dataset Distillation with Difficulty-Guided Sampling","created":"2025-07-04","cited_by_count":8,"area":null},{"id":"2203.01012","title":"Continual Feature Selection: Spurious Features in Continual Learning","created":"2022-03-02","cited_by_count":7,"area":null},{"id":"2304.10036","title":"Visual DNA: Representing and Comparing Images using Distributions of Neuron Activations","created":"2023-04-20","cited_by_count":7,"area":null},{"id":"2305.12316","title":"One-Shot Federated Learning for LEO Constellations that Reduces Convergence Time from Days to 90 Minutes","created":"2023-05-21","cited_by_count":7,"area":null},{"id":"2305.17768","title":"AIMS: All-Inclusive Multi-Level Segmentation","created":"2023-05-28","cited_by_count":6,"area":null},{"id":"2310.07506","title":"Leveraging Hierarchical Feature Sharing for Efficient Dataset Condensation","created":"2023-10-11","cited_by_count":6,"area":null},{"id":"2310.15052","title":"DREAM+: Efficient Dataset Distillation by Bidirectional Representative Matching","created":"2023-10-23","cited_by_count":6,"area":null},{"id":"2403.17083","title":"A Study in Dataset Pruning for Image Super-Resolution","created":"2024-03-25","cited_by_count":6,"area":null}],"next_cursor":"100"}