{"total":42,"rows":[{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815,"area":null},{"id":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","cited_by_count":122,"area":null},{"id":"2205.07877","title":"A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classification","created":"2022-05-14","cited_by_count":65,"area":null},{"id":"2310.08041","title":"QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models","created":"2023-10-12","cited_by_count":64,"area":null},{"id":"2101.08940","title":"Hessian-Aware Pruning and Optimal Neural Implant","created":"2021-01-22","cited_by_count":45,"area":null},{"id":"2104.09987","title":"Differentiable Model Compression via Pseudo Quantization Noise","created":"2021-04-20","cited_by_count":45,"area":null},{"id":"2206.00820","title":"NIPQ: Noise proxy-based Integrated Pseudo-Quantization","created":"2022-06-02","cited_by_count":35,"area":null},{"id":"2111.12273","title":"Sharpness-aware Quantization for Deep Neural Networks","created":"2021-11-24","cited_by_count":25,"area":null},{"id":"2205.12268","title":"Wavelet Feature Maps Compression for Image-to-Image CNNs","created":"2022-05-24","cited_by_count":16,"area":null},{"id":"2502.16638","title":"Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression","created":"2025-02-23","cited_by_count":14,"area":null},{"id":"2301.00131","title":"Guided Hybrid Quantization for Object detection in Multimodal Remote Sensing Imagery via One-to-one Self-teaching","created":"2022-12-31","cited_by_count":12,"area":null},{"id":"2305.11203","title":"PDP: Parameter-free Differentiable Pruning is All You Need","created":"2023-05-18","cited_by_count":12,"area":null},{"id":"2108.02720","title":"Generalizable Mixed-Precision Quantization via Attribution Rank Preservation","created":"2021-08-05","cited_by_count":11,"area":null},{"id":"2312.15322","title":"Hardware-Aware DNN Compression via Diverse Pruning and Mixed-Precision Quantization","created":"2023-12-23","cited_by_count":10,"area":null},{"id":"2203.10991","title":"Minimum Variance Unbiased N:M Sparsity for the Neural Gradients","created":"2022-03-21","cited_by_count":9,"area":null},{"id":"2311.06798","title":"MetaMix: Meta-state Precision Searcher for Mixed-precision Activation Quantization","created":"2023-11-12","cited_by_count":7,"area":null},{"id":"2101.04935","title":"Single-path Bit Sharing for Automatic Loss-aware Model Compression","created":"2021-01-13","cited_by_count":6,"area":null},{"id":"2102.07444","title":"FAT: Learning Low-Bitwidth Parametric Representation via Frequency-Aware Transformation","created":"2021-02-15","cited_by_count":6,"area":null},{"id":"2407.01054","title":"Joint Pruning and Channel-wise Mixed-Precision Quantization for Efficient Deep Neural Networks","created":"2024-07-01","cited_by_count":6,"area":null},{"id":"2509.11177","title":"Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs","created":"2025-09-14","cited_by_count":6,"area":null},{"id":"2212.07818","title":"Towards Hardware-Specific Automatic Compression of Neural Networks","created":"2022-12-15","cited_by_count":4,"area":null},{"id":"2302.07612","title":"Towards Optimal Compression: Joint Pruning and Quantization","created":"2023-02-15","cited_by_count":4,"area":null},{"id":"2504.13296","title":"Enhanced Pruning Strategy for Multi-Component Neural Architectures Using Component-Aware Graph Analysis","created":"2025-04-17","cited_by_count":3,"area":null},{"id":"2206.15014","title":"Compressing Pre-trained Transformers via Low-Bit NxM Sparsity for Natural Language Understanding","created":"2022-06-30","cited_by_count":2,"area":null},{"id":"2309.14157","title":"LAPP: Layer Adaptive Progressive Pruning for Compressing CNNs from Scratch","created":"2023-09-25","cited_by_count":2,"area":null},{"id":"2404.08010","title":"Differentiable Search for Finding Optimal Quantization Strategy","created":"2024-04-10","cited_by_count":2,"area":null},{"id":"2512.12981","title":"CoDeQ: End-to-End Joint Model Compression with Dead-Zone Quantizer for High-Sparsity and Low-Precision Networks","created":"2025-12-15","cited_by_count":2,"area":null},{"id":"2304.06393","title":"Learning Accurate Performance Predictors for Ultrafast Automated Model Compression","created":"2023-04-13","cited_by_count":1,"area":null},{"id":"2501.14495","title":"BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference","created":"2025-01-24","cited_by_count":1,"area":null},{"id":"2504.09064","title":"PQS (Prune, Quantize, and Sort): Low-Bitwidth Accumulation of Dot Products in Neural Network Computations","created":"2025-04-12","cited_by_count":1,"area":null},{"id":"2104.01303","title":"Tight Compression: Compressing CNN Through Fine-Grained Pruning and Weight Permutation for Efficient Implementation","created":"2021-04-03","cited_by_count":0,"area":null},{"id":"2408.05752","title":"RTF-Q: Efficient Unsupervised Domain Adaptation with Retraining-free Quantization","created":"2024-08-11","cited_by_count":0,"area":null},{"id":"2412.07391","title":"A Data-Free Analytical Quantization Scheme for Deep Learning Models","created":"2024-12-10","cited_by_count":0,"area":null},{"id":"2505.13462","title":"End-to-end fully-binarized network design: from Generic Learned Thermometer to Block Pruning","created":"2025-05-05","cited_by_count":0,"area":null},{"id":"2507.13742","title":"Search-Optimized Quantization in Biomedical Ontology Alignment","created":"2025-07-18","cited_by_count":0,"area":null},{"id":"2508.08144","title":"COMponent-Aware Pruning for Accelerated Control Tasks in Latent Space Models","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2509.04244","title":"Integrating Pruning with Quantization for Efficient Deep Neural Networks Compression","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2510.08999","title":"SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2602.23192","title":"FairQuant: Fairness-Aware Mixed-Precision Quantization for Medical Image Classification","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2605.02086","title":"GETA-3DGS: Automatic Joint Structured Pruning and Quantization for 3D Gaussian Splatting","created":"2026-05-03","cited_by_count":0,"area":null},{"id":"2608.00859","title":"SparseKAN: Compressing Kolmogorov--Arnold Networks Across Basis Functions, Neurons, and Bits","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2609.22238","title":"Task-Aware QUBO Allocation for Mixed-Precision Quantization","created":"2026-09-04","cited_by_count":0,"area":null}],"next_cursor":null}