{"list":"other","total":168,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1712.05877","title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference","created":"2017-12-15","cited_by_count":1593},{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"2404.00456","title":"QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs","created":"2024-03-30","cited_by_count":634},{"id":"1511.00363","title":"BinaryConnect: Training Deep Neural Networks with binary weights during propagations","created":"2015-11-02","cited_by_count":592},{"id":"1806.08342","title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","created":"2018-06-21","cited_by_count":521},{"id":"2106.08295","title":"A White Paper on Neural Network Quantization","created":"2021-06-15","cited_by_count":472},{"id":"1805.06085","title":"PACT: Parameterized Clipping Activation for Quantized Neural Networks","created":"2018-05-16","cited_by_count":467},{"id":"1811.08886","title":"HAQ: Hardware-Aware Automated Quantization with Mixed Precision","created":"2018-11-21","cited_by_count":443},{"id":"1703.09039","title":"Efficient Processing of Deep Neural Networks: A Tutorial and Survey","created":"2017-03-27","cited_by_count":434},{"id":"1609.07061","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","created":"2016-09-22","cited_by_count":426},{"id":"2308.13137","title":"OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models","created":"2023-08-25","cited_by_count":424},{"id":"1905.03696","title":"HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision","created":"2019-04-29","cited_by_count":402},{"id":"1906.05113","title":"A Survey of Autonomous Driving: Common Practices and Emerging Technologies","created":"2019-06-12","cited_by_count":379},{"id":"2402.04396","title":"QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks","created":"2024-02-06","cited_by_count":378},{"id":"1909.05840","title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","created":"2019-09-12","cited_by_count":359},{"id":"1906.04721","title":"Data-Free Quantization Through Weight Equalization and Bias Correction","created":"2019-06-11","cited_by_count":336},{"id":"1807.10029","title":"LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks","created":"2018-07-26","cited_by_count":274},{"id":"2007.10319","title":"MCUNet: Tiny Deep Learning on IoT Devices","created":"2020-07-20","cited_by_count":273},{"id":"2001.00281","title":"ZeroQ: A Novel Zero Shot Quantization Framework","created":"2020-01-01","cited_by_count":269},{"id":"1911.03852","title":"HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks","created":"2019-11-10","cited_by_count":261},{"id":"2006.02903","title":"A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions","created":"2020-06-01","cited_by_count":254},{"id":"1908.05033","title":"Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks","created":"2019-08-14","cited_by_count":238},{"id":"1702.03044","title":"Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights","created":"2017-02-10","cited_by_count":217},{"id":"1612.01064","title":"Trained Ternary Quantization","created":"2016-12-04","cited_by_count":208},{"id":"2405.04532","title":"QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving","created":"2024-05-07","cited_by_count":208},{"id":"1605.04711","title":"Ternary Weight Networks","created":"2016-05-16","cited_by_count":204},{"id":"1902.06822","title":"Low-bit Quantization of Neural Networks for Efficient Inference","created":"2019-02-18","cited_by_count":193},{"id":"2004.09602","title":"Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation","created":"2020-04-20","cited_by_count":188},{"id":"1909.10788","title":"Forward and Backward Information Retention for Accurate Binary Neural Networks","created":"2019-09-24","cited_by_count":169},{"id":"2406.01721","title":"DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs","created":"2024-06-03","cited_by_count":167},{"id":"2010.08678","title":"TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systems","created":"2020-10-17","cited_by_count":165},{"id":"1911.09464","title":"Quantization Networks","created":"2019-11-21","cited_by_count":153},{"id":"1901.09504","title":"Improving Neural Network Quantization without Retraining using Outlier Channel Splitting","created":"2019-01-28","cited_by_count":151},{"id":"2111.13824","title":"FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer","created":"2021-11-27","cited_by_count":151},{"id":"1511.06393","title":"Fixed Point Quantization of Deep Convolutional Networks","created":"2015-11-19","cited_by_count":143},{"id":"1801.06601","title":"CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUs","created":"2018-01-19","cited_by_count":121},{"id":"1702.00953","title":"Deep Learning with Low Precision by Half-wave Gaussian Quantization","created":"2017-02-03","cited_by_count":117},{"id":"2306.02272","title":"OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models","created":"2023-06-04","cited_by_count":114},{"id":"1603.01025","title":"Convolutional Neural Networks using Logarithmic Data Representation","created":"2016-03-03","cited_by_count":99},{"id":"2006.08509","title":"APQ: Joint Search for Network Architecture, Pruning and Quantization Policy","created":"2020-06-15","cited_by_count":99},{"id":"2104.11892","title":"A Survey of Modern Deep Learning based Object Detection Models","created":"2021-04-24","cited_by_count":98},{"id":"1912.12607","title":"Towards Unified INT8 Training for Convolutional Neural Network","created":"2019-12-29","cited_by_count":79},{"id":"2111.14826","title":"Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation","created":"2021-11-29","cited_by_count":79},{"id":"2008.05441","title":"Stable Low-rank Tensor Decomposition for Compression of Convolutional Neural Network","created":"2020-08-12","cited_by_count":74},{"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},{"id":"1912.09666","title":"AdaBits: Neural Network Quantization with Adaptive Bit-Widths","created":"2019-12-20","cited_by_count":64},{"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},{"id":"1902.05690","title":"AutoQ: Automated Kernel-Wise Neural Network Quantization","created":"2019-02-15","cited_by_count":63},{"id":"2002.07686","title":"Robust Quantization: One Model to Rule Them All","created":"2020-02-18","cited_by_count":63},{"id":"2211.16056","title":"NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers","created":"2022-11-29","cited_by_count":61},{"id":"2304.09145","title":"Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling","created":"2023-04-18","cited_by_count":61},{"id":"2306.11987","title":"Training Transformers with 4-bit Integers","created":"2023-06-21","cited_by_count":60},{"id":"2202.07471","title":"SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation","created":"2022-02-14","cited_by_count":55},{"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},{"id":"2112.00133","title":"PokeBNN: A Binary Pursuit of Lightweight Accuracy","created":"2021-11-30","cited_by_count":49},{"id":"1510.03009","title":"Neural Networks with Few Multiplications","created":"2015-10-11","cited_by_count":48},{"id":"1806.07550","title":"Binary Ensemble Neural Network: More Bits per Network or More Networks per Bit?","created":"2018-06-20","cited_by_count":39},{"id":"2010.04871","title":"Training Binary Neural Networks through Learning with Noisy Supervision","created":"2020-10-10","cited_by_count":39},{"id":"1608.06049","title":"Local Binary Convolutional Neural Networks","created":"2016-08-22","cited_by_count":38},{"id":"2404.07236","title":"Lightweight Deep Learning for Resource-Constrained Environments: A Survey","created":"2024-04-08","cited_by_count":38},{"id":"1811.10413","title":"Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation","created":"2018-11-22","cited_by_count":37},{"id":"1511.06488","title":"Resiliency of Deep Neural Networks under Quantization","created":"2015-11-20","cited_by_count":35},{"id":"1908.11263","title":"PULP-NN: Accelerating Quantized Neural Networks on Parallel Ultra-Low-Power RISC-V Processors","created":"2019-08-29","cited_by_count":35},{"id":"2206.00820","title":"NIPQ: Noise proxy-based Integrated Pseudo-Quantization","created":"2022-06-02","cited_by_count":35},{"id":"2010.03558","title":"High-Capacity Expert Binary Networks","created":"2020-10-07","cited_by_count":34},{"id":"2012.11233","title":"Hardware and Software Optimizations for Accelerating Deep Neural Networks: Survey of Current Trends, Challenges, and the Road Ahead","created":"2020-12-21","cited_by_count":34},{"id":"2010.05501","title":"BiPointNet: Binary Neural Network for Point Clouds","created":"2020-10-12","cited_by_count":30},{"id":"1601.06071","title":"Bitwise Neural Networks","created":"2016-01-22","cited_by_count":29},{"id":"1910.10853","title":"Circulant Binary Convolutional Networks: Enhancing the Performance of 1-bit DCNNs with Circulant Back Propagation","created":"2019-10-24","cited_by_count":28},{"id":"2202.05239","title":"F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization","created":"2022-02-10","cited_by_count":28},{"id":"2205.14550","title":"Machine Learning for Microcontroller-Class Hardware: A Review","created":"2022-05-29","cited_by_count":28},{"id":"2406.00800","title":"MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization","created":"2024-06-02","cited_by_count":28},{"id":"2207.10345","title":"CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution","created":"2022-07-21","cited_by_count":27},{"id":"2309.11932","title":"A Machine Learning-oriented Survey on Tiny Machine Learning","created":"2023-09-21","cited_by_count":27},{"id":"2105.03536","title":"Pareto-Optimal Quantized ResNet Is Mostly 4-bit","created":"2021-05-07","cited_by_count":26},{"id":"2103.10873","title":"Fully Onboard AI-powered Human-Drone Pose Estimation on Ultra-low Power Autonomous Flying Nano-UAVs","created":"2021-03-19","cited_by_count":24},{"id":"2203.15952","title":"4-bit Conformer with Native Quantization Aware Training for Speech Recognition","created":"2022-03-29","cited_by_count":24},{"id":"2212.03332","title":"Edge Impulse: An MLOps Platform for Tiny Machine Learning","created":"2022-11-02","cited_by_count":24},{"id":"2504.11651","title":"70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)","created":"2025-04-15","cited_by_count":24},{"id":"2308.07209","title":"Unified Data-Free Compression: Pruning and Quantization without Fine-Tuning","created":"2023-08-14","cited_by_count":23},{"id":"1706.02021","title":"Network Sketching: Exploiting Binary Structure in Deep CNNs","created":"2017-06-07","cited_by_count":22},{"id":"2105.13331","title":"Quantization and Deployment of Deep Neural Networks on Microcontrollers","created":"2021-05-27","cited_by_count":21},{"id":"1810.01018","title":"Simultaneously Optimizing Weight and Quantizer of Ternary Neural Network using Truncated Gaussian Approximation","created":"2018-10-02","cited_by_count":20},{"id":"2011.09398","title":"Larq Compute Engine: Design, Benchmark, and Deploy State-of-the-Art Binarized Neural Networks","created":"2020-11-18","cited_by_count":20},{"id":"2304.03986","title":"SwiftTron: An Efficient Hardware Accelerator for Quantized Transformers","created":"2023-04-08","cited_by_count":18},{"id":"2306.00001","title":"TinyissimoYOLO: A Quantized, Low-Memory Footprint, TinyML Object Detection Network for Low Power Microcontrollers","created":"2023-05-22","cited_by_count":18},{"id":"1905.10138","title":"Structured Compression by Weight Encryption for Unstructured Pruning and Quantization","created":"2019-05-24","cited_by_count":16},{"id":"1912.10615","title":"Neural Outlier Rejection for Self-Supervised Keypoint Learning","created":"2019-12-23","cited_by_count":16},{"id":"2304.06454","title":"CABM: Content-Aware Bit Mapping for Single Image Super-Resolution Network with Large Input","created":"2023-04-13","cited_by_count":16},{"id":"2311.01057","title":"Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLO","created":"2023-11-02","cited_by_count":15},{"id":"1812.01762","title":"Deep Positron: A Deep Neural Network Using the Posit Number System","created":"2018-12-05","cited_by_count":13}],"next_cursor":"100"}