{"total":90,"rows":[{"id":"2212.09720","title":"The case for 4-bit precision: k-bit Inference Scaling Laws","created":"2022-12-19","cited_by_count":251,"area":null},{"id":"2306.00317","title":"FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization","created":"2023-06-01","cited_by_count":48,"area":null},{"id":"2104.09987","title":"Differentiable Model Compression via Pseudo Quantization Noise","created":"2021-04-20","cited_by_count":45,"area":null},{"id":"2201.07703","title":"Q-ViT: Fully Differentiable Quantization for Vision Transformer","created":"2022-01-19","cited_by_count":37,"area":null},{"id":"2105.07809","title":"Learned Smartphone ISP on Mobile NPUs with Deep Learning, Mobile AI 2021 Challenge: Report","created":"2021-05-17","cited_by_count":34,"area":null},{"id":"2105.07825","title":"Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: Report","created":"2021-05-17","cited_by_count":34,"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":"2202.05239","title":"F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization","created":"2022-02-10","cited_by_count":28,"area":null},{"id":"2206.04459","title":"SDQ: Stochastic Differentiable Quantization with Mixed Precision","created":"2022-06-09","cited_by_count":28,"area":null},{"id":"2105.03536","title":"Pareto-Optimal Quantized ResNet Is Mostly 4-bit","created":"2021-05-07","cited_by_count":26,"area":null},{"id":"2404.03605","title":"Mitigating the Impact of Outlier Channels for Language Model Quantization with Activation Regularization","created":"2024-04-04","cited_by_count":23,"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":"2105.08630","title":"Fast and Accurate Single-Image Depth Estimation on Mobile Devices, Mobile AI 2021 Challenge: Report","created":"2021-05-17","cited_by_count":19,"area":null},{"id":"2105.08826","title":"Real-Time Video Super-Resolution on Smartphones with Deep Learning, Mobile AI 2021 Challenge: Report","created":"2021-05-17","cited_by_count":19,"area":null},{"id":"2211.05910","title":"Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report","created":"2022-11-07","cited_by_count":16,"area":null},{"id":"2101.05938","title":"KDLSQ-BERT: A Quantized Bert Combining Knowledge Distillation with Learned Step Size Quantization","created":"2021-01-15","cited_by_count":15,"area":"distill"},{"id":"2105.08629","title":"Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Report","created":"2021-05-17","cited_by_count":15,"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":"2211.03885","title":"Learned Smartphone ISP on Mobile GPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Report","created":"2022-11-07","cited_by_count":13,"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":"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":"2308.13504","title":"A2Q: Accumulator-Aware Quantization with Guaranteed Overflow Avoidance","created":"2023-08-25","cited_by_count":12,"area":null},{"id":"2307.05999","title":"Flexible and Fully Quantized Ultra-Lightweight TinyissimoYOLO for Ultra-Low-Power Edge Systems","created":"2023-07-12","cited_by_count":11,"area":null},{"id":"2408.04413","title":"Deeploy: Enabling Energy-Efficient Deployment of Small Language Models On Heterogeneous Microcontrollers","created":"2024-08-08","cited_by_count":11,"area":null},{"id":"2105.08819","title":"Fast and Accurate Quantized Camera Scene Detection on Smartphones, Mobile AI 2021 Challenge: Report","created":"2021-05-17","cited_by_count":10,"area":null},{"id":"2109.09113","title":"HPTQ: Hardware-Friendly Post Training Quantization","created":"2021-09-19","cited_by_count":10,"area":null},{"id":"2112.15139","title":"Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks","created":"2021-12-30","cited_by_count":9,"area":null},{"id":"2404.02945","title":"Optimizing the Deployment of Tiny Transformers on Low-Power MCUs","created":"2024-04-03","cited_by_count":8,"area":null},{"id":"2105.12676","title":"Low-Precision Hardware Architectures Meet Recommendation Model Inference at Scale","created":"2021-05-26","cited_by_count":7,"area":null},{"id":"2111.06503","title":"AnalogNets: ML-HW Co-Design of Noise-robust TinyML Models and Always-On Analog Compute-in-Memory Accelerator","created":"2021-11-10","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":"2210.07171","title":"SQuAT: Sharpness- and Quantization-Aware Training for BERT","created":"2022-10-13","cited_by_count":7,"area":null},{"id":"2201.10360","title":"Resource-efficient Deep Neural Networks for Automotive Radar Interference Mitigation","created":"2022-01-25","cited_by_count":6,"area":null},{"id":"2203.05492","title":"An Empirical Study of Low Precision Quantization for TinyML","created":"2022-03-10","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":"2308.07350","title":"Efficient Neural PDE-Solvers using Quantization Aware Training","created":"2023-08-14","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":"2401.10432","title":"A2Q+: Improving Accumulator-Aware Weight Quantization","created":"2024-01-19","cited_by_count":5,"area":null},{"id":"2403.01922","title":"FlowPrecision: Advancing FPGA-Based Real-Time Fluid Flow Estimation with Linear Quantization","created":"2024-03-04","cited_by_count":5,"area":null},{"id":"2108.13996","title":"Quantization of Generative Adversarial Networks for Efficient Inference: a Methodological Study","created":"2021-08-31","cited_by_count":4,"area":null},{"id":"2211.04470","title":"Efficient Single-Image Depth Estimation on Mobile Devices, Mobile AI & AIM 2022 Challenge: Report","created":"2022-11-07","cited_by_count":4,"area":null},{"id":"2311.09775","title":"MEGA: A Memory-Efficient GNN Accelerator Exploiting Degree-Aware Mixed-Precision Quantization","created":"2023-11-16","cited_by_count":4,"area":null},{"id":"2402.17710","title":"Understanding Neural Network Binarization with Forward and Backward Proximal Quantizers","created":"2024-02-27","cited_by_count":4,"area":null},{"id":"2405.19065","title":"xTern: Energy-Efficient Ternary Neural Network Inference on RISC-V-Based Edge Systems","created":"2024-05-29","cited_by_count":4,"area":null},{"id":"2405.19915","title":"P$^2$-ViT: Power-of-Two Post-Training Quantization and Acceleration for Fully Quantized Vision Transformer","created":"2024-05-30","cited_by_count":4,"area":null},{"id":"2107.11979","title":"HYPER-SNN: Towards Energy-efficient Quantized Deep Spiking Neural Networks for Hyperspectral Image Classification","created":"2021-07-26","cited_by_count":3,"area":null},{"id":"2112.10149","title":"Elastic-Link for Binarized Neural Network","created":"2021-12-19","cited_by_count":3,"area":null},{"id":"2203.11323","title":"Training Quantised Neural Networks with STE Variants: the Additive Noise Annealing Algorithm","created":"2022-03-21","cited_by_count":3,"area":null},{"id":"2211.05256","title":"Power Efficient Video Super-Resolution on Mobile NPUs with Deep Learning, Mobile AI & AIM 2022 challenge: Report","created":"2022-11-07","cited_by_count":3,"area":null},{"id":"2212.02634","title":"QFT: Post-training quantization via fast joint finetuning of all degrees of freedom","created":"2022-12-05","cited_by_count":3,"area":null},{"id":"2301.13376","title":"Quantized Neural Networks for Low-Precision Accumulation with Guaranteed Overflow Avoidance","created":"2023-01-31","cited_by_count":3,"area":null},{"id":"2302.00193","title":"$\\rm A^2Q$: Aggregation-Aware Quantization for Graph Neural Networks","created":"2023-02-01","cited_by_count":3,"area":null},{"id":"2307.02894","title":"Free Bits: Latency Optimization of Mixed-Precision Quantized Neural Networks on the Edge","created":"2023-07-06","cited_by_count":3,"area":null},{"id":"2310.03675","title":"Hadamard Domain Training with Integers for Class Incremental Quantized Learning","created":"2023-10-05","cited_by_count":3,"area":null},{"id":"2403.07851","title":"12 mJ per Class On-Device Online Few-Shot Class-Incremental Learning","created":"2024-03-12","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":"2104.00210","title":"Training Multi-bit Quantized and Binarized Networks with A Learnable Symmetric Quantizer","created":"2021-04-01","cited_by_count":2,"area":null},{"id":"2104.06666","title":"End-to-end Keyword Spotting using Neural Architecture Search and Quantization","created":"2021-04-14","cited_by_count":2,"area":null},{"id":"2211.06769","title":"Realistic Bokeh Effect Rendering on Mobile GPUs, Mobile AI & AIM 2022 challenge: Report","created":"2022-11-07","cited_by_count":2,"area":null},{"id":"2306.01076","title":"Quantization-Aware and Tensor-Compressed Training of Transformers for Natural Language Understanding","created":"2023-06-01","cited_by_count":2,"area":null},{"id":"2408.02561","title":"HQOD: Harmonious Quantization for Object Detection","created":"2024-08-05","cited_by_count":2,"area":null},{"id":"2102.02896","title":"Compressed Object Detection","created":"2021-02-04","cited_by_count":1,"area":null},{"id":"2105.07869","title":"Fast and Accurate Camera Scene Detection on Smartphones","created":"2021-05-17","cited_by_count":1,"area":null},{"id":"2209.12982","title":"Going Further With Winograd Convolutions: Tap-Wise Quantization for Efficient Inference on 4x4 Tile","created":"2022-09-26","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":"2405.06264","title":"Selective Focus: Investigating Semantics Sensitivity in Post-training Quantization for Lane Detection","created":"2024-05-10","cited_by_count":1,"area":null},{"id":"2405.16807","title":"Extreme Compression of Adaptive Neural Images","created":"2024-05-27","cited_by_count":1,"area":null},{"id":"2407.02913","title":"SFC: Achieve Accurate Fast Convolution under Low-precision Arithmetic","created":"2024-07-03","cited_by_count":1,"area":null},{"id":"2407.11698","title":"NITRO-D: Native Integer-only Training of Deep Convolutional Neural Networks","created":"2024-07-16","cited_by_count":1,"area":null},{"id":"2411.00907","title":"On the Impact of White-box Deployment Strategies for Edge AI on Latency and Model Performance","created":"2024-11-01","cited_by_count":1,"area":null},{"id":"2501.01841","title":"Dedicated Inference Engine and Binary-Weight Neural Networks for Lightweight Instance Segmentation","created":"2025-01-03","cited_by_count":1,"area":null},{"id":"2501.18953","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","created":"2025-01-31","cited_by_count":1,"area":null},{"id":"2505.13461","title":"FPGA-based Acceleration for Convolutional Neural Networks: A Comprehensive Review","created":"2025-05-04","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":"2510.11484","title":"Rescaling-Aware Training for Efficient Deployment of Deep Learning Models on Full-Integer Hardware","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2607.08779","title":"Signed Symmetric Quantization for Few-Bit Integers","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2210.03671","title":"A Closer Look at Hardware-Friendly Weight Quantization","created":"2022-10-07","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":"2305.15536","title":"RAND: Robustness Aware Norm Decay For Quantized Seq2seq Models","created":"2023-05-24","cited_by_count":0,"area":null},{"id":"2308.01867","title":"MRQ:Support Multiple Quantization Schemes through Model Re-Quantization","created":"2023-08-01","cited_by_count":0,"area":null},{"id":"2409.14515","title":"SPAQ-DL-SLAM: Towards Optimizing Deep Learning-based SLAM for Resource-Constrained Embedded Platforms","created":"2024-09-22","cited_by_count":0,"area":null},{"id":"2412.19002","title":"Tempus Core: Area-Power Efficient Temporal-Unary Convolution Core for Low-Precision Edge DLAs","created":"2024-12-25","cited_by_count":0,"area":null},{"id":"2507.04842","title":"Efficient SAR Vessel Detection for FPGA-Based On-Satellite Sensing","created":"2025-07-07","cited_by_count":0,"area":null},{"id":"2510.05468","title":"AMAQ: Adaptive Mixed-bit Activation Quantization for Collaborative Parameter Efficient Fine-tuning","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2608.29667","title":"A Target-Centric Survey of Quantization-Aware Training","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.01743","title":"SCULPT: Training Edge Vision Models for Post-Training Quantization Readiness","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.33591","title":"Pretraining Transformers with Quantized Softmax in Attention","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.35586","title":"IMC-CLINIC: Coupled Loss-Informed Newton Iterations for Clipping in Analog In-Memory Computing","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}