{"total":204,"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":"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":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263,"area":null},{"id":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255,"area":null},{"id":"2312.04564","title":"EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingS","created":"2023-12-07","cited_by_count":196,"area":null},{"id":"2106.08962","title":"Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better","created":"2021-06-16","cited_by_count":154,"area":null},{"id":"2210.06707","title":"Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer","created":"2022-10-13","cited_by_count":108,"area":null},{"id":"2104.00903","title":"Network Quantization with Element-wise Gradient Scaling","created":"2021-04-02","cited_by_count":87,"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":"2103.05579","title":"hls4ml: An Open-Source Codesign Workflow to Empower Scientific Low-Power Machine Learning Devices","created":"2021-03-09","cited_by_count":62,"area":null},{"id":"2110.06554","title":"Towards Mixed-Precision Quantization of Neural Networks via Constrained Optimization","created":"2021-10-13","cited_by_count":61,"area":null},{"id":"2104.09987","title":"Differentiable Model Compression via Pseudo Quantization Noise","created":"2021-04-20","cited_by_count":45,"area":null},{"id":"2109.15082","title":"Towards Efficient Post-training Quantization of Pre-trained Language Models","created":"2021-09-30","cited_by_count":39,"area":null},{"id":"2208.08084","title":"AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets","created":"2022-08-17","cited_by_count":38,"area":null},{"id":"2406.04333","title":"BitsFusion: 1.99 bits Weight Quantization of Diffusion Model","created":"2024-06-06","cited_by_count":37,"area":"diffusion"},{"id":"2204.11786","title":"Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications","created":"2022-04-25","cited_by_count":32,"area":null},{"id":"2102.11289","title":"Ps and Qs: Quantization-aware pruning for efficient low latency neural network inference","created":"2021-02-22","cited_by_count":31,"area":null},{"id":"2102.04782","title":"Distribution Adaptive INT8 Quantization for Training CNNs","created":"2021-02-09","cited_by_count":28,"area":null},{"id":"2406.00800","title":"MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization","created":"2024-06-02","cited_by_count":28,"area":null},{"id":"2102.08329","title":"An Information-Theoretic Justification for Model Pruning","created":"2021-02-16","cited_by_count":25,"area":null},{"id":"2109.12338","title":"Distribution-sensitive Information Retention for Accurate Binary Neural Network","created":"2021-09-25","cited_by_count":25,"area":null},{"id":"2104.12456","title":"3D Scene Compression through Entropy Penalized Neural Representation Functions","created":"2021-04-26","cited_by_count":23,"area":null},{"id":"2203.11239","title":"DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization","created":"2022-03-21","cited_by_count":23,"area":null},{"id":"2210.16103","title":"Collaborative Multi-Teacher Knowledge Distillation for Learning Low Bit-width Deep Neural Networks","created":"2022-10-27","cited_by_count":23,"area":"distill"},{"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":"2408.08554","title":"ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language Models","created":"2024-08-16","cited_by_count":22,"area":"inference"},{"id":"2407.12327","title":"Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale","created":"2024-07-17","cited_by_count":21,"area":null},{"id":"2101.09868","title":"CPT: Efficient Deep Neural Network Training via Cyclic Precision","created":"2021-01-25","cited_by_count":19,"area":null},{"id":"2103.16701","title":"Charged particle tracking via edge-classifying interaction networks","created":"2021-03-30","cited_by_count":19,"area":null},{"id":"2108.06983","title":"Distance-aware Quantization","created":"2021-08-16","cited_by_count":19,"area":null},{"id":"2206.01859","title":"Extreme Compression for Pre-trained Transformers Made Simple and Efficient","created":"2022-06-04","cited_by_count":19,"area":"distill"},{"id":"2308.02350","title":"RobustMQ: Benchmarking Robustness of Quantized Models","created":"2023-08-04","cited_by_count":19,"area":null},{"id":"2406.07177","title":"TernaryLLM: Ternarized Large Language Model","created":"2024-06-11","cited_by_count":17,"area":null},{"id":"2101.08430","title":"Generative Zero-shot Network Quantization","created":"2021-01-21","cited_by_count":15,"area":null},{"id":"2310.08012","title":"AutoFHE: Automated Adaption of CNNs for Efficient Evaluation over FHE","created":"2023-10-12","cited_by_count":15,"area":null},{"id":"2109.14710","title":"Convolutional Neural Network Compression through Generalized Kronecker Product Decomposition","created":"2021-09-29","cited_by_count":14,"area":null},{"id":"2110.02226","title":"Communication-Efficient Federated Learning with Binary Neural Networks","created":"2021-10-05","cited_by_count":14,"area":null},{"id":"2112.06126","title":"Neural Network Quantization for Efficient Inference: A Survey","created":"2021-12-08","cited_by_count":14,"area":null},{"id":"2104.12046","title":"Quantization of Deep Neural Networks for Accurate Edge Computing","created":"2021-04-25","cited_by_count":13,"area":null},{"id":"2109.02100","title":"Cluster-Promoting Quantization with Bit-Drop for Minimizing Network Quantization Loss","created":"2021-09-05","cited_by_count":12,"area":null},{"id":"2109.14960","title":"Prune Your Model Before Distill It","created":"2021-09-30","cited_by_count":12,"area":"distill"},{"id":"2204.06760","title":"HCFL: A High Compression Approach for Communication-Efficient Federated Learning in Very Large Scale IoT Networks","created":"2022-04-14","cited_by_count":12,"area":null},{"id":"2310.06756","title":"Going Beyond Neural Network Feature Similarity: The Network Feature Complexity and Its Interpretation Using Category Theory","created":"2023-10-10","cited_by_count":12,"area":null},{"id":"2110.13220","title":"Demystifying and Generalizing BinaryConnect","created":"2021-10-25","cited_by_count":11,"area":null},{"id":"2112.13843","title":"BMPQ: Bit-Gradient Sensitivity Driven Mixed-Precision Quantization of DNNs from Scratch","created":"2021-12-24","cited_by_count":11,"area":null},{"id":"2201.08050","title":"TerViT: An Efficient Ternary Vision Transformer","created":"2022-01-20","cited_by_count":11,"area":null},{"id":"2202.11453","title":"Bitwidth Heterogeneous Federated Learning with Progressive Weight Dequantization","created":"2022-02-23","cited_by_count":11,"area":null},{"id":"2403.03866","title":"KIWI: A Dataset of Knowledge-Intensive Writing Instructions for Answering Research Questions","created":"2024-03-06","cited_by_count":11,"area":null},{"id":"2112.11540","title":"Mixed Precision of Quantization of Transformer Language Models for Speech Recognition","created":"2021-11-29","cited_by_count":10,"area":null},{"id":"2203.06673","title":"FlexBlock: A Flexible DNN Training Accelerator with Multi-Mode Block Floating Point Support","created":"2022-03-13","cited_by_count":10,"area":null},{"id":"2112.15131","title":"Resource-Efficient Deep Learning: A Survey on Model-, Arithmetic-, and Implementation-Level Techniques","created":"2021-12-30","cited_by_count":9,"area":null},{"id":"2212.01076","title":"Are Straight-Through gradients and Soft-Thresholding all you need for Sparse Training?","created":"2022-12-02","cited_by_count":9,"area":null},{"id":"2307.00498","title":"Data-Free Quantization via Mixed-Precision Compensation without Fine-Tuning","created":"2023-07-02","cited_by_count":9,"area":null},{"id":"2505.02309","title":"Optimizing LLMs for Resource-Constrained Environments: A Survey of Model Compression Techniques","created":"2025-05-05","cited_by_count":9,"area":null},{"id":"2509.23809","title":"Tequila: Trapping-free Ternary Quantization for Large Language Models","created":"2025-09-28","cited_by_count":9,"area":null},{"id":"2107.13490","title":"Adaptive Precision Training (AdaPT): A dynamic fixed point quantized training approach for DNNs","created":"2021-07-28","cited_by_count":8,"area":null},{"id":"2208.05969","title":"Safety and Performance, Why not Both? Bi-Objective Optimized Model Compression toward AI Software Deployment","created":"2022-08-11","cited_by_count":8,"area":null},{"id":"2211.16726","title":"Boosted Dynamic Neural Networks","created":"2022-11-30","cited_by_count":8,"area":null},{"id":"2212.02770","title":"CSQ: Growing Mixed-Precision Quantization Scheme with Bi-level Continuous Sparsification","created":"2022-12-06","cited_by_count":8,"area":null},{"id":"2304.10618","title":"ULEEN: A Novel Architecture for Ultra Low-Energy Edge Neural Networks","created":"2023-04-20","cited_by_count":8,"area":null},{"id":"2310.00109","title":"FedAIoT: A Federated Learning Benchmark for Artificial Intelligence of Things","created":"2023-09-29","cited_by_count":8,"area":null},{"id":"2401.04339","title":"Memory-Efficient Fine-Tuning for Quantized Diffusion Model","created":"2024-01-09","cited_by_count":8,"area":"diffusion"},{"id":"2107.03453","title":"$S^3$: Sign-Sparse-Shift Reparametrization for Effective Training of Low-bit Shift Networks","created":"2021-07-07","cited_by_count":7,"area":null},{"id":"2201.13361","title":"Signing the Supermask: Keep, Hide, Invert","created":"2022-01-31","cited_by_count":7,"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":"2306.01841","title":"Binary and Ternary Natural Language Generation","created":"2023-06-02","cited_by_count":7,"area":null},{"id":"2411.07501","title":"LAuReL: Learned Augmented Residual Layer","created":"2024-11-12","cited_by_count":7,"area":null},{"id":"2502.10216","title":"Forget the Data and Fine-Tuning! Just Fold the Network to Compress","created":"2025-02-14","cited_by_count":7,"area":null},{"id":"2508.15008","title":"Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applications","created":"2025-08-20","cited_by_count":7,"area":null},{"id":"2103.11083","title":"Compacting Deep Neural Networks for Internet of Things: Methods and Applications","created":"2021-03-20","cited_by_count":6,"area":null},{"id":"2111.00153","title":"RMSMP: A Novel Deep Neural Network Quantization Framework with Row-wise Mixed Schemes and Multiple Precisions","created":"2021-10-30","cited_by_count":6,"area":null},{"id":"2205.12918","title":"A Low Memory Footprint Quantized Neural Network for Depth Completion of Very Sparse Time-of-Flight Depth Maps","created":"2022-05-25","cited_by_count":6,"area":null},{"id":"2405.14854","title":"TerDiT: Ternary Diffusion Models with Transformers","created":"2024-05-23","cited_by_count":6,"area":"diffusion"},{"id":"2502.16473","title":"TerEffic: Highly Efficient Ternary LLM Inference on FPGA","created":"2025-02-23","cited_by_count":6,"area":null},{"id":"2602.21233","title":"AngelSlim: A more accessible, comprehensive, and efficient toolkit for large model compression","created":"2026-02-07","cited_by_count":6,"area":"inference"},{"id":"2606.26650","title":"CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs","created":"2026-06-25","cited_by_count":6,"area":null},{"id":"2103.01435","title":"Improved Techniques for Quantizing Deep Networks with Adaptive Bit-Widths","created":"2021-03-02","cited_by_count":5,"area":null},{"id":"2106.10254","title":"An Empirical Investigation into Deep and Shallow Rule Learning","created":"2021-06-18","cited_by_count":5,"area":null},{"id":"2108.00893","title":"Static analysis of ReLU neural networks with tropical polyhedra","created":"2021-07-30","cited_by_count":5,"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":"2208.09708","title":"DenseShift: Towards Accurate and Efficient Low-Bit Power-of-Two Quantization","created":"2022-08-20","cited_by_count":5,"area":null},{"id":"2308.13570","title":"Stochastic Configuration Machines for Industrial Artificial Intelligence","created":"2023-08-25","cited_by_count":5,"area":null},{"id":"2311.02758","title":"M4BRAM: Mixed-Precision Matrix-Matrix Multiplication in FPGA Block RAMs","created":"2023-11-05","cited_by_count":5,"area":null},{"id":"2505.18724","title":"LoTA-QAF: Lossless Ternary Adaptation for Quantization-Aware Fine-Tuning","created":"2025-05-24","cited_by_count":5,"area":null},{"id":"2601.07892","title":"Sherry: Hardware-Efficient 1.25-Bit Ternary Quantization via Fine-grained Sparsification","created":"2026-01-12","cited_by_count":5,"area":null},{"id":"2608.01078","title":"Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization","created":"2026-08-02","cited_by_count":5,"area":"lr"},{"id":"2103.05363","title":"MWQ: Multiscale Wavelet Quantized Neural Networks","created":"2021-03-09","cited_by_count":4,"area":null},{"id":"2104.05421","title":"NullaNet Tiny: Ultra-low-latency DNN Inference Through Fixed-function Combinational Logic","created":"2021-04-07","cited_by_count":4,"area":null},{"id":"2111.09348","title":"End-to-End Learned Image Compression with Quantized Weights and Activations","created":"2021-11-17","cited_by_count":4,"area":null},{"id":"2202.10728","title":"Distilled Neural Networks for Efficient Learning to Rank","created":"2022-02-22","cited_by_count":4,"area":null},{"id":"2203.03794","title":"YONO: Modeling Multiple Heterogeneous Neural Networks on Microcontrollers","created":"2022-03-08","cited_by_count":4,"area":null},{"id":"2212.12653","title":"Hyperspherical Quantization: Toward Smaller and More Accurate Models","created":"2022-12-24","cited_by_count":4,"area":null},{"id":"2302.03390","title":"Learning Discretized Neural Networks under Ricci Flow","created":"2023-02-07","cited_by_count":4,"area":null},{"id":"2302.08571","title":"A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniques","created":"2023-02-16","cited_by_count":4,"area":null},{"id":"2308.10422","title":"Split Unlearning","created":"2023-08-21","cited_by_count":4,"area":"safety"},{"id":"2501.04517","title":"Histogram-Equalized Quantization for logic-gated Residual Neural Networks","created":"2025-01-08","cited_by_count":4,"area":null},{"id":"2502.11895","title":"Continual Quantization-Aware Pre-Training: When to transition from 16-bit to 1.58-bit pre-training for BitNet language models?","created":"2025-02-17","cited_by_count":4,"area":null},{"id":"2510.03267","title":"PT$^2$-LLM: Post-Training Ternarization for Large Language Models","created":"2025-09-27","cited_by_count":4,"area":null},{"id":"2510.21879","title":"TernaryCLIP: Efficiently Compressing Vision-Language Models with Ternary Weights and Distilled Knowledge","created":"2025-10-23","cited_by_count":4,"area":"mllm"}],"next_cursor":"100"}