{"total":41,"rows":[{"id":"2106.04533","title":"Chasing Sparsity in Vision Transformers: An End-to-End Exploration","created":"2021-06-08","cited_by_count":183,"area":null},{"id":"2301.05603","title":"A Comprehensive Survey of Dataset Distillation","created":"2023-01-13","cited_by_count":115,"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":"2107.07467","title":"Only Train Once: A One-Shot Neural Network Training And Pruning Framework","created":"2021-07-15","cited_by_count":70,"area":null},{"id":"2210.08277","title":"Deep Differentiable Logic Gate Networks","created":"2022-10-15","cited_by_count":67,"area":null},{"id":"2210.06659","title":"Structural Pruning via Latency-Saliency Knapsack","created":"2022-10-13","cited_by_count":41,"area":null},{"id":"2110.12007","title":"When to Prune? A Policy towards Early Structural Pruning","created":"2021-10-22","cited_by_count":38,"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":"2203.15794","title":"CHEX: CHannel EXploration for CNN Model Compression","created":"2022-03-29","cited_by_count":36,"area":null},{"id":"2303.06862","title":"OTOV2: Automatic, Generic, User-Friendly","created":"2023-03-13","cited_by_count":32,"area":null},{"id":"2111.05685","title":"Efficient Neural Network Training via Forward and Backward Propagation Sparsification","created":"2021-11-10","cited_by_count":30,"area":null},{"id":"2106.09857","title":"Effective Model Sparsification by Scheduled Grow-and-Prune Methods","created":"2021-06-18","cited_by_count":26,"area":null},{"id":"2304.03589","title":"On Efficient Training of Large-Scale Deep Learning Models: A Literature Review","created":"2023-04-07","cited_by_count":26,"area":null},{"id":"2302.02596","title":"Ten Lessons We Have Learned in the New \"Sparseland\": A Short Handbook for Sparse Neural Network Researchers","created":"2023-02-06","cited_by_count":25,"area":null},{"id":"2206.10451","title":"Winning the Lottery Ahead of Time: Efficient Early Network Pruning","created":"2022-06-21","cited_by_count":21,"area":null},{"id":"2312.14227","title":"ElasticTrainer: Speeding Up On-Device Training with Runtime Elastic Tensor Selection","created":"2023-12-21","cited_by_count":12,"area":null},{"id":"2209.11204","title":"Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training","created":"2022-09-22","cited_by_count":11,"area":null},{"id":"2401.10341","title":"ELRT: Efficient Low-Rank Training for Compact Convolutional Neural Networks","created":"2024-01-18","cited_by_count":11,"area":null},{"id":"2110.10811","title":"HALP: Hardware-Aware Latency Pruning","created":"2021-10-20","cited_by_count":8,"area":null},{"id":"2101.09650","title":"GST: Group-Sparse Training for Accelerating Deep Reinforcement Learning","created":"2021-01-24","cited_by_count":7,"area":null},{"id":"2107.06039","title":"AutoScore-Imbalance: An interpretable machine learning tool for development of clinical scores with rare events data","created":"2021-07-13","cited_by_count":7,"area":null},{"id":"2403.07688","title":"Maxwell's Demon at Work: Efficient Pruning by Leveraging Saturation of Neurons","created":"2024-03-12","cited_by_count":6,"area":null},{"id":"2102.01963","title":"Local Critic Training for Model-Parallel Learning of Deep Neural Networks","created":"2021-02-03","cited_by_count":5,"area":null},{"id":"2106.14126","title":"AdaptCL: Efficient Collaborative Learning with Dynamic and Adaptive Pruning","created":"2021-06-27","cited_by_count":4,"area":null},{"id":"2204.02360","title":"Scientometric Review of Artificial Intelligence for Operations & Maintenance of Wind Turbines: The Past, Present and Future","created":"2022-03-30","cited_by_count":4,"area":null},{"id":"2211.10948","title":"FedDCT: Federated Learning of Large Convolutional Neural Networks on Resource Constrained Devices using Divide and Collaborative Training","created":"2022-11-20","cited_by_count":3,"area":null},{"id":"2404.03687","title":"DRIVE: Dual Gradient-Based Rapid Iterative Pruning","created":"2024-04-01","cited_by_count":3,"area":null},{"id":"2104.09075","title":"An Oracle for Guiding Large-Scale Model/Hybrid Parallel Training of Convolutional Neural Networks","created":"2021-04-19","cited_by_count":2,"area":null},{"id":"2309.06805","title":"FedDIP: Federated Learning with Extreme Dynamic Pruning and Incremental Regularization","created":"2023-09-13","cited_by_count":2,"area":null},{"id":"2406.06564","title":"SwitchLoRA: Switched Low-Rank Adaptation Can Learn Full-Rank Information","created":"2024-06-03","cited_by_count":2,"area":null},{"id":"2304.07613","title":"STen: Productive and Efficient Sparsity in PyTorch","created":"2023-04-15","cited_by_count":1,"area":null},{"id":"2406.03879","title":"Decay Pruning Method: Smooth Pruning With a Self-Rectifying Procedure","created":"2024-06-06","cited_by_count":1,"area":null},{"id":"2502.03658","title":"Advancing Weight and Channel Sparsification with Enhanced Saliency","created":"2025-02-05","cited_by_count":1,"area":null},{"id":"2510.03101","title":"AdaBet: Gradient-free Layer Selection for Efficient Training of Deep Neural Networks","created":"2025-10-03","cited_by_count":1,"area":null},{"id":"2510.13405","title":"Optimizing Storage Overhead of User Behavior Log for ML-embedded Mobile Apps","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2512.06288","title":"Theoretical Compression Bounds for Wide Multilayer Perceptrons","created":"2025-12-06","cited_by_count":1,"area":null},{"id":"2107.07706","title":"DANCE: DAta-Network Co-optimization for Efficient Segmentation Model Training and Inference","created":"2021-07-16","cited_by_count":0,"area":null},{"id":"2506.20152","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","created":"2025-06-25","cited_by_count":0,"area":null},{"id":"2508.14140","title":"Neuro-inspired Ensemble-to-Ensemble Communication Primitives for Sparse and Efficient ANNs","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2603.21508","title":"Optimizing Feature Extraction for On-device Model Inference with User Behavior Sequences","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2606.14346","title":"Squeeze-Release: Iterative Pruning with Exact Structural Minimization","created":"2026-06-12","cited_by_count":0,"area":null}],"next_cursor":null}