{"total":122,"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":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255,"area":null},{"id":"2109.12948","title":"Understanding and Overcoming the Challenges of Efficient Transformer Quantization","created":"2021-09-27","cited_by_count":141,"area":null},{"id":"2302.14017","title":"Full Stack Optimization of Transformer Inference: a Survey","created":"2023-02-27","cited_by_count":80,"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":"2101.09336","title":"A Comprehensive Survey on Hardware-Aware Neural Architecture Search","created":"2021-01-22","cited_by_count":61,"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":"2203.08368","title":"Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance","created":"2022-03-16","cited_by_count":54,"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":"2108.10394","title":"Dynamic Network Quantization for Efficient Video Inference","created":"2021-08-23","cited_by_count":36,"area":null},{"id":"2110.13041","title":"Applications and Techniques for Fast Machine Learning in Science","created":"2021-10-25","cited_by_count":32,"area":null},{"id":"2108.13041","title":"Auto-Split: A General Framework of Collaborative Edge-Cloud AI","created":"2021-08-30","cited_by_count":30,"area":null},{"id":"2206.04459","title":"SDQ: Stochastic Differentiable Quantization with Mixed Precision","created":"2022-06-09","cited_by_count":28,"area":null},{"id":"2111.12273","title":"Sharpness-aware Quantization for Deep Neural Networks","created":"2021-11-24","cited_by_count":25,"area":null},{"id":"2302.05397","title":"A Practical Mixed Precision Algorithm for Post-Training Quantization","created":"2023-02-10","cited_by_count":24,"area":null},{"id":"2103.17267","title":"Bit-Mixer: Mixed-precision networks with runtime bit-width selection","created":"2021-03-31","cited_by_count":22,"area":null},{"id":"2212.01593","title":"Make RepVGG Greater Again: A Quantization-aware Approach","created":"2022-12-03","cited_by_count":22,"area":null},{"id":"2307.10554","title":"EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization","created":"2023-07-20","cited_by_count":22,"area":null},{"id":"2108.03428","title":"PSViT: Better Vision Transformer via Token Pooling and Attention Sharing","created":"2021-08-07","cited_by_count":21,"area":null},{"id":"2105.08952","title":"BatchQuant: Quantized-for-all Architecture Search with Robust Quantizer","created":"2021-05-19","cited_by_count":20,"area":null},{"id":"2302.04453","title":"Data Quality-aware Mixed-precision Quantization via Hybrid Reinforcement Learning","created":"2023-02-09","cited_by_count":17,"area":null},{"id":"2104.12766","title":"HAO: Hardware-aware neural Architecture Optimization for Efficient Inference","created":"2021-04-26","cited_by_count":16,"area":null},{"id":"2305.06559","title":"Patch-wise Mixed-Precision Quantization of Vision Transformer","created":"2023-05-11","cited_by_count":15,"area":null},{"id":"2112.09245","title":"Automated Deep Learning: Neural Architecture Search Is Not the End","created":"2021-12-16","cited_by_count":13,"area":null},{"id":"2401.01543","title":"Retraining-free Model Quantization via One-Shot Weight-Coupling Learning","created":"2024-01-03","cited_by_count":13,"area":null},{"id":"2102.06365","title":"Dynamic Precision Analog Computing for Neural Networks","created":"2021-02-12","cited_by_count":12,"area":null},{"id":"2106.06575","title":"Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators","created":"2021-06-11","cited_by_count":12,"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":"2210.08502","title":"FIT: A Metric for Model Sensitivity","created":"2022-10-16","cited_by_count":11,"area":null},{"id":"2311.18129","title":"Mixed-Precision Quantization for Federated Learning on Resource-Constrained Heterogeneous Devices","created":"2023-11-29","cited_by_count":11,"area":null},{"id":"2410.13056","title":"Channel-Wise Mixed-Precision Quantization for Large Language Models","created":"2024-10-16","cited_by_count":11,"area":null},{"id":"2507.06671","title":"FlexGaussian: Flexible and Cost-Effective Training-Free Compression for 3D Gaussian Splatting","created":"2025-07-09","cited_by_count":11,"area":null},{"id":"2102.06366","title":"Confounding Tradeoffs for Neural Network Quantization","created":"2021-02-12","cited_by_count":9,"area":null},{"id":"2205.11244","title":"A Silicon Photonic Accelerator for Convolutional Neural Networks with Heterogeneous Quantization","created":"2022-05-17","cited_by_count":9,"area":null},{"id":"2207.10188","title":"Bitwidth-Adaptive Quantization-Aware Neural Network Training: A Meta-Learning Approach","created":"2022-07-20","cited_by_count":9,"area":null},{"id":"2504.14152","title":"FGMP: Fine-Grained Mixed-Precision Weight and Activation Quantization for Hardware-Accelerated LLM Inference","created":"2025-04-19","cited_by_count":9,"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":"2509.20214","title":"Q-Palette: Fractional-Bit Quantizers Toward Optimal Bit Allocation for Efficient LLM Deployment","created":"2025-09-24","cited_by_count":8,"area":null},{"id":"2108.09413","title":"Integer-arithmetic-only Certified Robustness for Quantized Neural Networks","created":"2021-08-21","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":"2307.05657","title":"Mixed-Precision Quantization for Deep Vision Models with Integer Quadratic Programming","created":"2023-07-11","cited_by_count":7,"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":"2410.19483","title":"Content-Aware Radiance Fields: Aligning Model Complexity with Scene Intricacy Through Learned Bitwidth Quantization","created":"2024-10-25","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":"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":"2106.07611","title":"Neuroevolution-Enhanced Multi-Objective Optimization for Mixed-Precision Quantization","created":"2021-06-14","cited_by_count":6,"area":null},{"id":"2110.14812","title":"Differentiable NAS Framework and Application to Ads CTR Prediction","created":"2021-10-25","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":"2302.06845","title":"SEAM: Searching Transferable Mixed-Precision Quantization Policy through Large Margin Regularization","created":"2023-02-14","cited_by_count":6,"area":null},{"id":"2308.03290","title":"FLIQS: One-Shot Mixed-Precision Floating-Point and Integer Quantization Search","created":"2023-08-07","cited_by_count":6,"area":null},{"id":"2406.06593","title":"Differentiable Combinatorial Scheduling at Scale","created":"2024-06-06","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":"2103.01435","title":"Improved Techniques for Quantizing Deep Networks with Adaptive Bit-Widths","created":"2021-03-02","cited_by_count":5,"area":null},{"id":"2209.14252","title":"Physics-aware Differentiable Discrete Codesign for Diffractive Optical Neural Networks","created":"2022-09-28","cited_by_count":5,"area":null},{"id":"2101.11748","title":"Rethinking Floating Point Overheads for Mixed Precision DNN Accelerators","created":"2021-01-27","cited_by_count":4,"area":null},{"id":"2103.05363","title":"MWQ: Multiscale Wavelet Quantized Neural Networks","created":"2021-03-09","cited_by_count":4,"area":null},{"id":"2210.15623","title":"Neural Networks with Quantization Constraints","created":"2022-10-27","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":"2301.11810","title":"BOMP-NAS: Bayesian Optimization Mixed Precision NAS","created":"2023-01-27","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":"2309.17341","title":"MixQuant: Mixed Precision Quantization with a Bit-width Optimization Search","created":"2023-09-29","cited_by_count":4,"area":null},{"id":"2310.12182","title":"Block-Wise Mixed-Precision Quantization: Enabling High Efficiency for Practical ReRAM-based DNN Accelerators","created":"2023-10-17","cited_by_count":4,"area":null},{"id":"2407.18175","title":"Quasar-ViT: Hardware-Oriented Quantization-Aware Architecture Search for Vision Transformers","created":"2024-07-25","cited_by_count":4,"area":null},{"id":"2508.04753","title":"InfoQ: Mixed-Precision Quantization via Global Information Flow","created":"2025-08-06","cited_by_count":4,"area":null},{"id":"2103.10051","title":"Data-free mixed-precision quantization using novel sensitivity metric","created":"2021-03-18","cited_by_count":3,"area":null},{"id":"2109.09310","title":"Learning Versatile Convolution Filters for Efficient Visual Recognition","created":"2021-09-20","cited_by_count":3,"area":null},{"id":"2110.08562","title":"BNAS v2: Learning Architectures for Binary Networks with Empirical Improvements","created":"2021-10-16","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":"2208.04854","title":"Design of High-Throughput Mixed-Precision CNN Accelerators on FPGA","created":"2022-08-09","cited_by_count":3,"area":null},{"id":"2301.13330","title":"Efficient and Effective Methods for Mixed Precision Neural Network Quantization for Faster, Energy-efficient Inference","created":"2023-01-30","cited_by_count":3,"area":null},{"id":"2502.15802","title":"A General Error-Theoretical Analysis Framework for Constructing Compression Strategies","created":"2025-02-19","cited_by_count":3,"area":null},{"id":"2505.04877","title":"Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning","created":"2025-05-08","cited_by_count":3,"area":null},{"id":"2606.04115","title":"dMX: Differentiable Mixed-Precision Assignment for Low-Precision Floating-Point Formats","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2102.09298","title":"GradFreeBits: Gradient Free Bit Allocation for Dynamic Low Precision Neural Networks","created":"2021-02-18","cited_by_count":2,"area":null},{"id":"2104.10853","title":"InstantNet: Automated Generation and Deployment of Instantaneously Switchable-Precision Networks","created":"2021-04-22","cited_by_count":2,"area":null},{"id":"2106.09686","title":"How Low Can We Go: Trading Memory for Error in Low-Precision Training","created":"2021-06-17","cited_by_count":2,"area":null},{"id":"2202.04303","title":"TinyM$^2$Net: A Flexible System Algorithm Co-designed Multimodal Learning Framework for Tiny Devices","created":"2022-02-09","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":"2304.06745","title":"End-to-end codesign of Hessian-aware quantized neural networks for FPGAs and ASICs","created":"2023-04-13","cited_by_count":2,"area":null},{"id":"2312.13301","title":"SimQ-NAS: Simultaneous Quantization Policy and Neural Architecture Search","created":"2023-12-19","cited_by_count":2,"area":null},{"id":"2402.17706","title":"Adaptive quantization with mixed-precision based on low-cost proxy","created":"2024-02-27","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":"2407.18267","title":"MCU-MixQ: A HW/SW Co-optimized Mixed-precision Neural Network Design Framework for MCUs","created":"2024-07-17","cited_by_count":2,"area":null},{"id":"2506.23717","title":"Towards Efficient and Accurate Spiking Neural Networks via Adaptive Bit Allocation","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2509.07222","title":"Explaining How Quantization Disparately Skews a Model","created":"2025-09-08","cited_by_count":2,"area":null},{"id":"2511.18474","title":"Adaptive Mesh-Quantization for Neural PDE Solvers","created":"2025-11-23","cited_by_count":2,"area":null},{"id":"2103.14493","title":"RCT: Resource Constrained Training for Edge AI","created":"2021-03-26","cited_by_count":1,"area":null},{"id":"2204.13666","title":"Schr\\\"odinger's FP: Dynamic Adaptation of Floating-Point Containers for Deep Learning Training","created":"2022-04-28","cited_by_count":1,"area":null},{"id":"2208.10498","title":"Design Automation for Fast, Lightweight, and Effective Deep Learning Models: A Survey","created":"2022-08-22","cited_by_count":1,"area":null},{"id":"2303.08308","title":"SpaceEvo: Hardware-Friendly Search Space Design for Efficient INT8 Inference","created":"2023-03-15","cited_by_count":1,"area":null},{"id":"2309.01945","title":"On-Chip Hardware-Aware Quantization for Mixed Precision Neural Networks","created":"2023-09-05","cited_by_count":1,"area":null},{"id":"2310.18656","title":"Med-DANet V2: A Flexible Dynamic Architecture for Efficient Medical Volumetric Segmentation","created":"2023-10-28","cited_by_count":1,"area":null},{"id":"2401.00379","title":"DREAM: Debugging and Repairing AutoML Pipelines","created":"2023-12-31","cited_by_count":1,"area":null},{"id":"2403.20080","title":"Mixed-precision Supernet Training from Vision Foundation Models using Low Rank Adapter","created":"2024-03-29","cited_by_count":1,"area":null},{"id":"2404.16876","title":"AdaQAT: Adaptive Bit-Width Quantization-Aware Training","created":"2024-04-22","cited_by_count":1,"area":null},{"id":"2409.20138","title":"Constraint Guided Model Quantization of Neural Networks","created":"2024-09-30","cited_by_count":1,"area":null},{"id":"2410.09531","title":"PrivQuant: Communication-Efficient Private Inference with Quantized Network/Protocol Co-Optimization","created":"2024-10-12","cited_by_count":1,"area":null},{"id":"2410.24214","title":"ARQ: A Mixed-Precision Quantization Framework for Accurate and Certifiably Robust DNNs","created":"2024-10-31","cited_by_count":1,"area":null}],"next_cursor":"100"}