{"total":94,"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":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263,"area":null},{"id":"2209.05433","title":"FP8 Formats for Deep Learning","created":"2022-09-12","cited_by_count":196,"area":null},{"id":"2111.14826","title":"Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation","created":"2021-11-29","cited_by_count":79,"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":"2102.04503","title":"VS-Quant: Per-vector Scaled Quantization for Accurate Low-Precision Neural Network Inference","created":"2021-02-08","cited_by_count":64,"area":null},{"id":"2302.02210","title":"Oscillation-free Quantization for Low-bit Vision Transformers","created":"2023-02-04","cited_by_count":57,"area":null},{"id":"2205.13016","title":"BiT: Robustly Binarized Multi-distilled Transformer","created":"2022-05-25","cited_by_count":52,"area":null},{"id":"2208.14286","title":"ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization","created":"2022-08-30","cited_by_count":51,"area":null},{"id":"2103.07156","title":"Learnable Companding Quantization for Accurate Low-bit Neural Networks","created":"2021-03-12","cited_by_count":42,"area":null},{"id":"2111.03759","title":"MQBench: Towards Reproducible and Deployable Model Quantization Benchmark","created":"2021-11-05","cited_by_count":40,"area":null},{"id":"2405.03144","title":"PTQ4SAM: Post-Training Quantization for Segment Anything","created":"2024-05-06","cited_by_count":32,"area":null},{"id":"2407.10960","title":"Fast Matrix Multiplications for Lookup Table-Quantized LLMs","created":"2024-07-15","cited_by_count":29,"area":null},{"id":"2206.04459","title":"SDQ: Stochastic Differentiable Quantization with Mixed Precision","created":"2022-06-09","cited_by_count":28,"area":null},{"id":"2112.10769","title":"Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats","created":"2021-12-19","cited_by_count":26,"area":null},{"id":"2203.05025","title":"Power-of-Two Quantization for Low Bitwidth and Hardware Compliant Neural Networks","created":"2022-03-09","cited_by_count":26,"area":null},{"id":"2206.02915","title":"8-bit Numerical Formats for Deep Neural Networks","created":"2022-06-06","cited_by_count":25,"area":null},{"id":"2106.02295","title":"Differentiable Dynamic Quantization with Mixed Precision and Adaptive Resolution","created":"2021-06-04","cited_by_count":20,"area":null},{"id":"2301.09858","title":"PowerQuant: Automorphism Search for Non-Uniform Quantization","created":"2023-01-24","cited_by_count":20,"area":null},{"id":"2405.03103","title":"Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs","created":"2024-05-06","cited_by_count":18,"area":null},{"id":"2410.04960","title":"On Efficient Variants of Segment Anything Model: A Survey","created":"2024-10-07","cited_by_count":16,"area":null},{"id":"2502.18755","title":"M-ANT: Efficient Low-bit Group Quantization for LLMs via Mathematically Adaptive Numerical Type","created":"2025-02-26","cited_by_count":16,"area":null},{"id":"2204.12322","title":"RAPQ: Rescuing Accuracy for Power-of-Two Low-bit Post-training Quantization","created":"2022-04-26","cited_by_count":15,"area":null},{"id":"2104.11849","title":"Do All MobileNets Quantize Poorly? Gaining Insights into the Effect of Quantization on Depthwise Separable Convolutional Networks Through the Eyes of Multi-scale Distributional Dynamics","created":"2021-04-24","cited_by_count":12,"area":null},{"id":"2505.01043","title":"Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities","created":"2025-05-02","cited_by_count":11,"area":null},{"id":"2109.01262","title":"On the Accuracy of Analog Neural Network Inference Accelerators","created":"2021-09-03","cited_by_count":10,"area":null},{"id":"2102.06366","title":"Confounding Tradeoffs for Neural Network Quantization","created":"2021-02-12","cited_by_count":9,"area":null},{"id":"2303.13003","title":"Benchmarking the Reliability of Post-training Quantization: a Particular Focus on Worst-case Performance","created":"2023-03-23","cited_by_count":9,"area":null},{"id":"2311.11883","title":"Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review","created":"2023-11-20","cited_by_count":9,"area":null},{"id":"2308.05600","title":"NUPES : Non-Uniform Post-Training Quantization via Power Exponent Search","created":"2023-08-10","cited_by_count":8,"area":null},{"id":"2310.05079","title":"Revisiting Block-based Quantisation: What is Important for Sub-8-bit LLM Inference?","created":"2023-10-08","cited_by_count":8,"area":null},{"id":"2106.13914","title":"LNS-Madam: Low-Precision Training in Logarithmic Number System using Multiplicative Weight Update","created":"2021-06-26","cited_by_count":7,"area":null},{"id":"2208.12866","title":"Reducing Computational Complexity of Neural Networks in Optical Channel Equalization: From Concepts to Implementation","created":"2022-08-26","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":"2103.02904","title":"Effective and Fast: A Novel Sequential Single Path Search for Mixed-Precision Quantization","created":"2021-03-04","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":"2203.14645","title":"REx: Data-Free Residual Quantization Error Expansion","created":"2022-03-28","cited_by_count":6,"area":null},{"id":"2412.15846","title":"Improving Quantization-aware Training of Low-Precision Network via Block Replacement on Full-Precision Counterpart","created":"2024-12-20","cited_by_count":6,"area":null},{"id":"2208.04494","title":"A Time-to-first-spike Coding and Conversion Aware Training for Energy-Efficient Deep Spiking Neural Network Processor Design","created":"2022-08-09","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":"2401.10139","title":"Model Compression Techniques in Biometrics Applications: A Survey","created":"2024-01-18","cited_by_count":5,"area":null},{"id":"2103.05363","title":"MWQ: Multiscale Wavelet Quantized Neural Networks","created":"2021-03-09","cited_by_count":4,"area":null},{"id":"2109.03513","title":"Elastic Significant Bit Quantization and Acceleration for Deep Neural Networks","created":"2021-09-08","cited_by_count":4,"area":null},{"id":"2201.03013","title":"ThreshNet: An Efficient DenseNet Using Threshold Mechanism to Reduce Connections","created":"2022-01-09","cited_by_count":4,"area":null},{"id":"2209.15257","title":"Energy Efficient Hardware Acceleration of Neural Networks with Power-of-Two Quantisation","created":"2022-09-30","cited_by_count":4,"area":null},{"id":"2307.05035","title":"Number Systems for Deep Neural Network Architectures: A Survey","created":"2023-07-11","cited_by_count":4,"area":null},{"id":"2312.05725","title":"FP8-BERT: Post-Training Quantization for Transformer","created":"2023-12-10","cited_by_count":4,"area":null},{"id":"2404.00103","title":"PikeLPN: Mitigating Overlooked Inefficiencies of Low-Precision Neural Networks","created":"2024-03-29","cited_by_count":4,"area":null},{"id":"2501.04517","title":"Histogram-Equalized Quantization for logic-gated Residual Neural Networks","created":"2025-01-08","cited_by_count":4,"area":null},{"id":"2105.01353","title":"One Model for All Quantization: A Quantized Network Supporting Hot-Swap Bit-Width Adjustment","created":"2021-05-04","cited_by_count":3,"area":null},{"id":"2110.12308","title":"A Layer-wise Adversarial-aware Quantization Optimization for Improving Robustness","created":"2021-10-23","cited_by_count":3,"area":null},{"id":"2111.07284","title":"Energy Efficient Learning with Low Resolution Stochastic Domain Wall Synapse Based Deep Neural Networks","created":"2021-11-14","cited_by_count":3,"area":null},{"id":"2112.08193","title":"N3H-Core: Neuron-designed Neural Network Accelerator via FPGA-based Heterogeneous Computing Cores","created":"2021-12-15","cited_by_count":3,"area":null},{"id":"2210.16556","title":"MinUn: Accurate ML Inference on Microcontrollers","created":"2022-10-29","cited_by_count":3,"area":null},{"id":"2401.17269","title":"Effect of Weight Quantization on Learning Models by Typical Case Analysis","created":"2024-01-30","cited_by_count":3,"area":null},{"id":"2505.24852","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2112.04291","title":"FastSGD: A Fast Compressed SGD Framework for Distributed Machine Learning","created":"2021-12-08","cited_by_count":2,"area":null},{"id":"2203.12091","title":"FxP-QNet: A Post-Training Quantizer for the Design of Mixed Low-Precision DNNs with Dynamic Fixed-Point Representation","created":"2022-03-22","cited_by_count":2,"area":null},{"id":"2306.07215","title":"Efficient and Robust Quantization-aware Training via Adaptive Coreset Selection","created":"2023-06-12","cited_by_count":2,"area":null},{"id":"2401.16760","title":"One-Step Forward and Backtrack: Overcoming Zig-Zagging in Loss-Aware Quantization Training","created":"2024-01-30","cited_by_count":2,"area":null},{"id":"2407.08272","title":"PowerYOLO: Mixed Precision Model for Hardware Efficient Object Detection with Event Data","created":"2024-07-11","cited_by_count":2,"area":null},{"id":"2408.00232","title":"CDFGNN: a Systematic Design of Cache-based Distributed Full-Batch Graph Neural Network Training with Communication Reduction","created":"2024-08-01","cited_by_count":2,"area":null},{"id":"2412.17966","title":"tuGEMM: Area-Power-Efficient Temporal Unary GEMM Architecture for Low-Precision Edge AI","created":"2024-12-23","cited_by_count":2,"area":null},{"id":"2506.17768","title":"Log-Normal Multiplicative Dynamics for Stable Low-Precision Training of Large Networks","created":"2025-06-21","cited_by_count":2,"area":null},{"id":"2105.03176","title":"ANNETTE: Accurate Neural Network Execution Time Estimation with Stacked Models","created":"2021-05-07","cited_by_count":1,"area":null},{"id":"2208.00087","title":"Low-complexity Approximate Convolutional Neural Networks","created":"2022-07-29","cited_by_count":1,"area":null},{"id":"2303.02347","title":"MetaGrad: Adaptive Gradient Quantization with Hypernetworks","created":"2023-03-04","cited_by_count":1,"area":null},{"id":"2304.01483","title":"Blockwise Compression of Transformer-based Models without Retraining","created":"2023-04-04","cited_by_count":1,"area":null},{"id":"2312.07602","title":"Sense, Predict, Adapt, Repeat: A Blueprint for Design of New Adaptive AI-Centric Sensing Systems","created":"2023-12-11","cited_by_count":1,"area":null},{"id":"2409.20403","title":"Accelerating PoT Quantization on Edge Devices","created":"2024-09-30","cited_by_count":1,"area":null},{"id":"2410.20345","title":"Logarithmically Quantized Distributed Optimization over Dynamic Multi-Agent Networks","created":"2024-10-27","cited_by_count":1,"area":null},{"id":"2504.17263","title":"Precision Neural Network Quantization via Learnable Adaptive Modules","created":"2025-04-24","cited_by_count":1,"area":null},{"id":"2506.10463","title":"Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization","created":"2025-06-12","cited_by_count":1,"area":null},{"id":"2605.06082","title":"PoTAcc: A Pipeline for End-to-End Acceleration of Power-of-Two Quantized DNNs","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2103.11704","title":"n-hot: Efficient bit-level sparsity for powers-of-two neural network quantization","created":"2021-03-22","cited_by_count":0,"area":null},{"id":"2104.13818","title":"NUQSGD: Provably Communication-efficient Data-parallel SGD via Nonuniform Quantization","created":"2021-04-28","cited_by_count":0,"area":null},{"id":"2106.08301","title":"Efficient Micro-Structured Weight Unification and Pruning for Neural Network Compression","created":"2021-06-15","cited_by_count":0,"area":null},{"id":"2106.09886","title":"Quantized Neural Networks via {-1, +1} Encoding Decomposition and Acceleration","created":"2021-06-18","cited_by_count":0,"area":null},{"id":"2111.00155","title":"ILMPQ : An Intra-Layer Multi-Precision Deep Neural Network Quantization framework for FPGA","created":"2021-10-30","cited_by_count":0,"area":null},{"id":"2111.05002","title":"Phantom: A High-Performance Computational Core for Sparse Convolutional Neural Networks","created":"2021-11-09","cited_by_count":0,"area":null},{"id":"2202.12422","title":"Standard Deviation-Based Quantization for Deep Neural Networks","created":"2022-02-24","cited_by_count":0,"area":null},{"id":"2206.07649","title":"Atrial Fibrillation Detection Using Weight-Pruned, Log-Quantised Convolutional Neural Networks","created":"2022-06-14","cited_by_count":0,"area":null},{"id":"2207.07832","title":"Approximation Capabilities of Neural Networks using Morphological Perceptrons and Generalizations","created":"2022-07-16","cited_by_count":0,"area":null},{"id":"2303.09184","title":"Block-wise Bit-Compression of Transformer-based Models","created":"2023-03-16","cited_by_count":0,"area":null},{"id":"2304.03782","title":"AutoQNN: An End-to-End Framework for Automatically Quantizing Neural Networks","created":"2023-04-07","cited_by_count":0,"area":null},{"id":"2306.16430","title":"DNA-TEQ: An Adaptive Exponential Quantization of Tensors for DNN Inference","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2311.15806","title":"PIPE : Parallelized Inference Through Post-Training Quantization Ensembling of Residual Expansions","created":"2023-11-27","cited_by_count":0,"area":null},{"id":"2402.18595","title":"EncodingNet: A Novel Encoding-based MAC Design for Efficient Neural Network Acceleration","created":"2024-02-25","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":"2510.04044","title":"Quantization Range Estimation for Convolutional Neural Networks","created":"2025-10-05","cited_by_count":0,"area":null},{"id":"2510.16088","title":"Differentiable, Bit-shifting, and Scalable Quantization without training neural network from scratch","created":"2025-10-18","cited_by_count":0,"area":null},{"id":"2510.18650","title":"Binary Quadratic Quantization: Beyond First-Order Quantization for Real-Valued Matrix Compression","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2602.00165","title":"Benford's Law as a Distributional Prior for Post-Training Quantization of Large Language Models","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2608.10010","title":"CurveFP: Co-Designing Numerical Representation and Product Arithmetic for Language Models","created":"2026-08-08","cited_by_count":0,"area":null}],"next_cursor":null}