{"total":35,"rows":[{"id":"2104.08378","title":"Accelerating Sparse Deep Neural Networks","created":"2021-04-16","cited_by_count":223,"area":null},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2202.07105","title":"A Survey on Model Compression and Acceleration for Pretrained Language Models","created":"2022-02-15","cited_by_count":45,"area":null},{"id":"2307.07982","title":"A Survey of Techniques for Optimizing Transformer Inference","created":"2023-07-16","cited_by_count":35,"area":null},{"id":"2110.10030","title":"Accelerating Framework of Transformer by Hardware Design and Model Compression Co-Optimization","created":"2021-10-19","cited_by_count":27,"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":"2105.14713","title":"1xN Pattern for Pruning Convolutional Neural Networks","created":"2021-05-31","cited_by_count":16,"area":null},{"id":"2304.14082","title":"JaxPruner: A concise library for sparsity research","created":"2023-04-27","cited_by_count":13,"area":null},{"id":"2108.06277","title":"Towards Structured Dynamic Sparse Pre-Training of BERT","created":"2021-08-13","cited_by_count":12,"area":null},{"id":"2110.08352","title":"Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernet","created":"2021-10-15","cited_by_count":12,"area":null},{"id":"2209.05735","title":"Learning ASR pathways: A sparse multilingual ASR model","created":"2022-09-13","cited_by_count":12,"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":"2111.02351","title":"Weight, Block or Unit? Exploring Sparsity Tradeoffs for Speech Enhancement on Tiny Neural Accelerators","created":"2021-11-03","cited_by_count":8,"area":null},{"id":"2403.07953","title":"Enabling Unstructured Sparse Acceleration on Structured Sparse Accelerators","created":"2024-03-12","cited_by_count":8,"area":null},{"id":"2204.02965","title":"LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification","created":"2022-04-06","cited_by_count":7,"area":null},{"id":"2407.14106","title":"TorchGT: A Holistic System for Large-scale Graph Transformer Training","created":"2024-07-19","cited_by_count":5,"area":null},{"id":"2307.08771","title":"UPSCALE: Unconstrained Channel Pruning","created":"2023-07-17","cited_by_count":4,"area":null},{"id":"2105.10832","title":"Spectral Pruning for Recurrent Neural Networks","created":"2021-05-23","cited_by_count":3,"area":null},{"id":"2105.12920","title":"Search Spaces for Neural Model Training","created":"2021-05-27","cited_by_count":3,"area":null},{"id":"2305.14706","title":"PruMUX: Augmenting Data Multiplexing with Model Compression","created":"2023-05-24","cited_by_count":3,"area":null},{"id":"2404.00880","title":"Rethinking the Relationship between Recurrent and Non-Recurrent Neural Networks: A Study in Sparsity","created":"2024-04-01","cited_by_count":3,"area":null},{"id":"2412.11810","title":"Optimal Gradient Checkpointing for Sparse and Recurrent Architectures using Off-Chip Memory","created":"2024-12-16","cited_by_count":3,"area":null},{"id":"2503.21928","title":"An Efficient Training Algorithm for Models with Block-wise Sparsity","created":"2025-03-27","cited_by_count":2,"area":null},{"id":"2101.02667","title":"BRDS: An FPGA-based LSTM Accelerator with Row-Balanced Dual-Ratio Sparsification","created":"2021-01-07","cited_by_count":1,"area":null},{"id":"2210.16624","title":"LearningGroup: A Real-Time Sparse Training on FPGA via Learnable Weight Grouping for Multi-Agent Reinforcement Learning","created":"2022-10-29","cited_by_count":1,"area":null},{"id":"2310.00496","title":"The Sparsity Roofline: Understanding the Hardware Limits of Sparse Neural Networks","created":"2023-09-30","cited_by_count":1,"area":null},{"id":"2501.18953","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","created":"2025-01-31","cited_by_count":1,"area":null},{"id":"2103.10629","title":"Cascade Weight Shedding in Deep Neural Networks: Benefits and Pitfalls for Network Pruning","created":"2021-03-19","cited_by_count":0,"area":null},{"id":"2106.12089","title":"Structured in Space, Randomized in Time: Leveraging Dropout in RNNs for Efficient Training","created":"2021-06-22","cited_by_count":0,"area":null},{"id":"2207.14545","title":"A One-Shot Reparameterization Method for Reducing the Loss of Tile Pruning on DNNs","created":"2022-07-29","cited_by_count":0,"area":null},{"id":"2306.15656","title":"SparseOptimizer: Sparsify Language Models through Moreau-Yosida Regularization and Accelerate via Compiler Co-design","created":"2023-06-27","cited_by_count":0,"area":null},{"id":"2307.03930","title":"Rosko: Row Skipping Outer Products for Sparse Matrix Multiplication Kernels","created":"2023-07-08","cited_by_count":0,"area":null},{"id":"2307.07405","title":"Performance of $\\ell_1$ Regularization for Sparse Convex Optimization","created":"2023-07-14","cited_by_count":0,"area":null},{"id":"2509.15057","title":"Balancing Sparse RNNs with Hyperparameterization Benefiting Meta-Learning","created":"2025-09-18","cited_by_count":0,"area":null}],"next_cursor":null}