{"total":69,"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":"2104.01136","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","created":"2021-04-02","cited_by_count":475,"area":null},{"id":"2106.08295","title":"A White Paper on Neural Network Quantization","created":"2021-06-15","cited_by_count":472,"area":null},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319,"area":null},{"id":"2402.15319","title":"GPTVQ: The Blessing of Dimensionality for LLM Quantization","created":"2024-02-23","cited_by_count":82,"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":"2104.14129","title":"ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training","created":"2021-04-29","cited_by_count":61,"area":null},{"id":"2409.17066","title":"VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models","created":"2024-09-25","cited_by_count":57,"area":null},{"id":"2112.11312","title":"Implicit Neural Video Compression","created":"2021-12-21","cited_by_count":52,"area":null},{"id":"2212.14593","title":"NIRVANA: Neural Implicit Representations of Videos with Adaptive Networks and Autoregressive Patch-wise Modeling","created":"2022-12-30","cited_by_count":51,"area":null},{"id":"2104.09987","title":"Differentiable Model Compression via Pseudo Quantization Noise","created":"2021-04-20","cited_by_count":45,"area":null},{"id":"2104.14235","title":"Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety","created":"2021-04-29","cited_by_count":35,"area":null},{"id":"2108.12659","title":"DKM: Differentiable K-Means Clustering Layer for Neural Network Compression","created":"2021-08-28","cited_by_count":31,"area":null},{"id":"2201.08442","title":"Neural Network Quantization with AI Model Efficiency Toolkit (AIMET)","created":"2022-01-20","cited_by_count":24,"area":null},{"id":"2112.09852","title":"LegoDNN: Block-grained Scaling of Deep Neural Networks for Mobile Vision","created":"2021-12-18","cited_by_count":20,"area":null},{"id":"2302.03213","title":"LUT-NN: Empower Efficient Neural Network Inference with Centroid Learning and Table Lookup","created":"2023-02-07","cited_by_count":20,"area":null},{"id":"2105.14797","title":"RED : Looking for Redundancies for Data-Free Structured Compression of Deep Neural Networks","created":"2021-05-31","cited_by_count":19,"area":null},{"id":"2110.01397","title":"RED++ : Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Merging","created":"2021-09-30","cited_by_count":19,"area":null},{"id":"2111.08988","title":"LVAC: Learned Volumetric Attribute Compression for Point Clouds using Coordinate Based Networks","created":"2021-11-17","cited_by_count":19,"area":null},{"id":"2303.07129","title":"AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environments","created":"2023-03-13","cited_by_count":19,"area":null},{"id":"2410.13780","title":"Optimal Quantization for Matrix Multiplication","created":"2024-10-17","cited_by_count":14,"area":null},{"id":"2311.11420","title":"LifeLearner: Hardware-Aware Meta Continual Learning System for Embedded Computing Platforms","created":"2023-11-19","cited_by_count":11,"area":null},{"id":"2203.13483","title":"MKQ-BERT: Quantized BERT with 4-bits Weights and Activations","created":"2022-03-25","cited_by_count":10,"area":null},{"id":"2102.02147","title":"Fixed-point Quantization of Convolutional Neural Networks for Quantized Inference on Embedded Platforms","created":"2021-02-03","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":"2102.07444","title":"FAT: Learning Low-Bitwidth Parametric Representation via Frequency-Aware Transformation","created":"2021-02-15","cited_by_count":6,"area":null},{"id":"2208.08562","title":"Restructurable Activation Networks","created":"2022-08-17","cited_by_count":6,"area":null},{"id":"2305.18334","title":"PQA: Exploring the Potential of Product Quantization in DNN Hardware Acceleration","created":"2023-05-25","cited_by_count":6,"area":null},{"id":"2311.15782","title":"Relationship between Model Compression and Adversarial Robustness: A Review of Current Evidence","created":"2023-11-27","cited_by_count":6,"area":null},{"id":"2507.04610","title":"any4: Learned 4-bit Numeric Representation for LLMs","created":"2025-07-07","cited_by_count":5,"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":"2207.05808","title":"Look-ups are not (yet) all you need for deep learning inference","created":"2022-07-12","cited_by_count":4,"area":null},{"id":"2207.12779","title":"Reconciling Security and Communication Efficiency in Federated Learning","created":"2022-07-26","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":"2309.00964","title":"eDKM: An Efficient and Accurate Train-time Weight Clustering for Large Language Models","created":"2023-09-02","cited_by_count":4,"area":null},{"id":"2207.11048","title":"Quantized Sparse Weight Decomposition for Neural Network Compression","created":"2022-07-22","cited_by_count":3,"area":null},{"id":"2303.14470","title":"Compacting Binary Neural Networks by Sparse Kernel Selection","created":"2023-03-25","cited_by_count":3,"area":null},{"id":"2211.11397","title":"Learning Low-Rank Representations for Model Compression","created":"2022-11-21","cited_by_count":2,"area":null},{"id":"2307.05972","title":"Self-Distilled Quantization: Achieving High Compression Rates in Transformer-Based Language Models","created":"2023-07-12","cited_by_count":2,"area":null},{"id":"2405.06038","title":"From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks","created":"2024-05-09","cited_by_count":2,"area":null},{"id":"2406.11307","title":"An Empirical Investigation of Matrix Factorization Methods for Pre-trained Transformers","created":"2024-06-17","cited_by_count":2,"area":null},{"id":"2412.10261","title":"MVQ:Towards Efficient DNN Compression and Acceleration with Masked Vector Quantization","created":"2024-12-13","cited_by_count":2,"area":null},{"id":"2503.12211","title":"Changing Base Without Losing Pace: A GPU-Efficient Alternative to MatMul in DNNs","created":"2025-03-15","cited_by_count":2,"area":null},{"id":"2104.04576","title":"Compiler Toolchains for Deep Learning Workloads on Embedded Platforms","created":"2021-03-08","cited_by_count":1,"area":null},{"id":"2107.09095","title":"A New Clustering-Based Technique for the Acceleration of Deep Convolutional Networks","created":"2021-07-19","cited_by_count":1,"area":null},{"id":"2110.07809","title":"PTQ-SL: Exploring the Sub-layerwise Post-training Quantization","created":"2021-10-15","cited_by_count":1,"area":null},{"id":"2210.13554","title":"Weight Fixing Networks","created":"2022-10-24","cited_by_count":1,"area":null},{"id":"2309.13575","title":"Probabilistic Weight Fixing: Large-scale training of neural network weight uncertainties for quantization","created":"2023-09-24","cited_by_count":1,"area":null},{"id":"2411.15438","title":"Efficient Ternary Weight Embedding Model: Bridging Scalability and Performance","created":"2024-11-23","cited_by_count":1,"area":null},{"id":"2502.16931","title":"Machine learning and high dimensional vector search","created":"2025-02-24","cited_by_count":1,"area":null},{"id":"2506.02077","title":"Assigning Distinct Roles to Quantized and Low-Rank Matrices Toward Optimal Weight Decomposition","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2603.06606","title":"LegoNet: Memory Footprint Reduction Through Block Weight Clustering","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2105.01868","title":"Q-Rater: Non-Convex Optimization for Post-Training Uniform Quantization","created":"2021-05-05","cited_by_count":0,"area":null},{"id":"2105.10059","title":"Model Compression","created":"2021-05-20","cited_by_count":0,"area":null},{"id":"2107.10998","title":"Pruning Ternary Quantization","created":"2021-07-23","cited_by_count":0,"area":null},{"id":"2111.10320","title":"Toward Compact Parameter Representations for Architecture-Agnostic Neural Network Compression","created":"2021-11-19","cited_by_count":0,"area":null},{"id":"2203.08080","title":"Implicit Feature Decoupling with Depthwise Quantization","created":"2022-03-15","cited_by_count":0,"area":null},{"id":"2210.05111","title":"Deep learning model compression using network sensitivity and gradients","created":"2022-10-11","cited_by_count":0,"area":null},{"id":"2212.05603","title":"Error-aware Quantization through Noise Tempering","created":"2022-12-11","cited_by_count":0,"area":null},{"id":"2212.12649","title":"Hyperspherical Loss-Aware Ternary Quantization","created":"2022-12-24","cited_by_count":0,"area":null},{"id":"2306.14031","title":"Partitioning-Guided K-Means: Extreme Empty Cluster Resolution for Extreme Model Compression","created":"2023-06-24","cited_by_count":0,"area":null},{"id":"2308.10704","title":"Sampling From Autoencoders' Latent Space via Quantization And Probability Mass Function Concepts","created":"2023-08-21","cited_by_count":0,"area":null},{"id":"2312.07759","title":"IDKM: Memory Efficient Neural Network Quantization via Implicit, Differentiable k-Means","created":"2023-12-12","cited_by_count":0,"area":null},{"id":"2406.06237","title":"Efficient Neural Compression with Inference-time Decoding","created":"2024-06-10","cited_by_count":0,"area":null},{"id":"2501.03095","title":"A Novel Structure-Agnostic Multi-Objective Approach for Weight-Sharing Compression in Deep Neural Networks","created":"2025-01-06","cited_by_count":0,"area":null},{"id":"2503.08668","title":"SSVQ: Unleashing the Potential of Vector Quantization with Sign-Splitting","created":"2025-03-11","cited_by_count":0,"area":null},{"id":"2512.15742","title":"SHARe-KAN: Post-Training Vector Quantization for Cache-Resident KAN Inference","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2608.08652","title":"LegoLM: Structured Weight Sharing for Large Language Models","created":"2026-08-09","cited_by_count":0,"area":null}],"next_cursor":null}