{"total":21,"rows":[{"id":"2104.08378","title":"Accelerating Sparse Deep Neural Networks","created":"2021-04-16","cited_by_count":223,"area":null},{"id":"2107.07983","title":"S2TA: Exploiting Structured Sparsity for Energy-Efficient Mobile CNN Acceleration","created":"2021-07-16","cited_by_count":19,"area":null},{"id":"2405.20935","title":"Effective Interplay between Sparsity and Quantization: From Theory to Practice","created":"2024-05-31","cited_by_count":19,"area":null},{"id":"2402.04744","title":"Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers","created":"2024-02-07","cited_by_count":18,"area":null},{"id":"2405.15743","title":"Sparse maximal update parameterization: A holistic approach to sparse training dynamics","created":"2024-05-24","cited_by_count":16,"area":null},{"id":"2209.14624","title":"Is Complexity Required for Neural Network Pruning? A Case Study on Global Magnitude Pruning","created":"2022-09-29","cited_by_count":13,"area":null},{"id":"2209.07617","title":"Training Recipe for N:M Structured Sparsity with Decaying Pruning Mask","created":"2022-09-15","cited_by_count":11,"area":null},{"id":"2308.05170","title":"FPGA Resource-aware Structured Pruning for Real-Time Neural Networks","created":"2023-08-09","cited_by_count":7,"area":null},{"id":"2602.18116","title":"Cut Less, Fold More: Model Compression through the Lens of Projection Geometry","created":"2026-02-20","cited_by_count":4,"area":null},{"id":"2306.07030","title":"Resource Efficient Neural Networks Using Hessian Based Pruning","created":"2023-06-12","cited_by_count":3,"area":null},{"id":"2512.00055","title":"KAN-SAs: Efficient Acceleration of Kolmogorov-Arnold Networks on Systolic Arrays","created":"2025-11-20","cited_by_count":3,"area":null},{"id":"2205.07433","title":"Binarizing by Classification: Is soft function really necessary?","created":"2022-05-16","cited_by_count":2,"area":null},{"id":"2405.06038","title":"From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks","created":"2024-05-09","cited_by_count":2,"area":null},{"id":"2507.05286","title":"Compressing Deep Neural Networks Using Explainable AI","created":"2025-07-04","cited_by_count":2,"area":null},{"id":"2411.10285","title":"Systolic Arrays and Structured Pruning Co-design for Efficient Transformers in Edge Systems","created":"2024-11-15","cited_by_count":1,"area":null},{"id":"2106.05825","title":"HASI: Hardware-Accelerated Stochastic Inference, A Defense Against Adversarial Machine Learning Attacks","created":"2021-06-09","cited_by_count":0,"area":null},{"id":"2208.00498","title":"DNNShield: Dynamic Randomized Model Sparsification, A Defense Against Adversarial Machine Learning","created":"2022-07-31","cited_by_count":0,"area":null},{"id":"2305.07778","title":"Accelerator-Aware Training for Transducer-Based Speech Recognition","created":"2023-05-12","cited_by_count":0,"area":null},{"id":"2408.16233","title":"PSE-Net: Channel Pruning for Convolutional Neural Networks with Parallel-subnets Estimator","created":"2024-08-29","cited_by_count":0,"area":null},{"id":"2507.01429","title":"Hardware-software co-exploration with racetrack memory based in-memory computing for CNN inference in embedded systems","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2608.24973","title":"Resource-Efficient Pruning for Transformer via Low-Rank Importance Estimation","created":"2026-08-25","cited_by_count":0,"area":null}],"next_cursor":null}