{"total":37,"rows":[{"id":"2206.01861","title":"ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers","created":"2022-06-04","cited_by_count":526,"area":null},{"id":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255,"area":null},{"id":"2101.08940","title":"Hessian-Aware Pruning and Optimal Neural Implant","created":"2021-01-22","cited_by_count":45,"area":null},{"id":"2202.04736","title":"Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets","created":"2022-02-09","cited_by_count":27,"area":null},{"id":"2301.12017","title":"Understanding INT4 Quantization for Transformer Models: Latency Speedup, Composability, and Failure Cases","created":"2023-01-27","cited_by_count":23,"area":null},{"id":"2207.12577","title":"Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution","created":"2022-07-25","cited_by_count":20,"area":null},{"id":"2209.04766","title":"Towards Sparsification of Graph Neural Networks","created":"2022-09-11","cited_by_count":18,"area":null},{"id":"2209.06979","title":"Efficient Quantized Sparse Matrix Operations on Tensor Cores","created":"2022-09-14","cited_by_count":16,"area":null},{"id":"2309.07438","title":"Towards Artificial General Intelligence (AGI) in the Internet of Things (IoT): Opportunities and Challenges","created":"2023-09-14","cited_by_count":14,"area":null},{"id":"2304.14082","title":"JaxPruner: A concise library for sparsity research","created":"2023-04-27","cited_by_count":13,"area":null},{"id":"2104.08700","title":"Lottery Jackpots Exist in Pre-trained Models","created":"2021-04-18","cited_by_count":10,"area":null},{"id":"2102.06336","title":"Dancing along Battery: Enabling Transformer with Run-time Reconfigurability on Mobile Devices","created":"2021-02-12","cited_by_count":9,"area":null},{"id":"2104.10461","title":"Improving the Accuracy of Early Exits in Multi-Exit Architectures via Curriculum Learning","created":"2021-04-21","cited_by_count":9,"area":null},{"id":"2309.03824","title":"Training Acceleration of Low-Rank Decomposed Networks using Sequential Freezing and Rank Quantization","created":"2023-09-07","cited_by_count":8,"area":null},{"id":"2309.12412","title":"Speeding up Resnet Architecture with Layers Targeted Low Rank Decomposition","created":"2023-09-21","cited_by_count":8,"area":null},{"id":"2402.01089","title":"No Free Prune: Information-Theoretic Barriers to Pruning at Initialization","created":"2024-02-02","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":"2208.06064","title":"Mixed-Precision Neural Networks: A Survey","created":"2022-08-11","cited_by_count":7,"area":null},{"id":"2112.11438","title":"Mixed Precision Low-bit Quantization of Neural Network Language Models for Speech Recognition","created":"2021-11-29","cited_by_count":5,"area":null},{"id":"2206.01627","title":"Pruning for Feature-Preserving Circuits in CNNs","created":"2022-06-03","cited_by_count":4,"area":null},{"id":"2104.09056","title":"RingCNN: Exploiting Algebraically-Sparse Ring Tensors for Energy-Efficient CNN-Based Computational Imaging","created":"2021-04-19","cited_by_count":3,"area":null},{"id":"2208.06660","title":"Entropy Induced Pruning Framework for Convolutional Neural Networks","created":"2022-08-13","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":"2106.07894","title":"S2Engine: A Novel Systolic Architecture for Sparse Convolutional Neural Networks","created":"2021-06-15","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":"2112.10898","title":"Load-balanced Gather-scatter Patterns for Sparse Deep Neural Networks","created":"2021-12-20","cited_by_count":1,"area":null},{"id":"2202.02310","title":"EcoFlow: Efficient Convolutional Dataflows for Low-Power Neural Network Accelerators","created":"2022-02-04","cited_by_count":1,"area":null},{"id":"2407.20266","title":"Accelerating the Low-Rank Decomposed Models","created":"2024-07-24","cited_by_count":1,"area":null},{"id":"2101.01163","title":"SmartDeal: Re-Modeling Deep Network Weights for Efficient Inference and Training","created":"2021-01-04","cited_by_count":0,"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":"2202.05137","title":"Quantization in Layer's Input is Matter","created":"2022-02-10","cited_by_count":0,"area":null},{"id":"2206.10088","title":"Renormalized Sparse Neural Network Pruning","created":"2022-06-21","cited_by_count":0,"area":null},{"id":"2206.10620","title":"CoCoPIE XGen: A Full-Stack AI-Oriented Optimizing Framework","created":"2022-06-21","cited_by_count":0,"area":null},{"id":"2207.10083","title":"Mixed-Precision Inference Quantization: Radically Towards Faster inference speed, Lower Storage requirement, and Lower Loss","created":"2022-07-20","cited_by_count":0,"area":null},{"id":"2309.05090","title":"Sculpting Efficiency: Pruning Medical Imaging Models for On-Device Inference","created":"2023-09-10","cited_by_count":0,"area":null},{"id":"2411.00288","title":"Inducing Semi-Structured Sparsity by Masking for Efficient Model Inference in Convolutional Networks","created":"2024-11-01","cited_by_count":0,"area":null}],"next_cursor":null}