{"total":345,"rows":[{"id":"2208.07339","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","created":"2022-08-15","cited_by_count":906,"area":null},{"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":"2206.01861","title":"ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers","created":"2022-06-04","cited_by_count":526,"area":null},{"id":"2102.05426","title":"BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction","created":"2021-02-10","cited_by_count":479,"area":null},{"id":"2106.08295","title":"A White Paper on Neural Network Quantization","created":"2021-06-15","cited_by_count":472,"area":null},{"id":"2307.13304","title":"QuIP: 2-Bit Quantization of Large Language Models With Guarantees","created":"2023-07-25","cited_by_count":414,"area":null},{"id":"2306.07629","title":"SqueezeLLM: Dense-and-Sparse Quantization","created":"2023-06-13","cited_by_count":294,"area":null},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269,"area":null},{"id":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255,"area":null},{"id":"2112.04267","title":"Implicit Neural Representations for Image Compression","created":"2021-12-08","cited_by_count":162,"area":null},{"id":"2402.04291","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","created":"2024-02-06","cited_by_count":144,"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":"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,"area":null},{"id":"2207.01405","title":"I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference","created":"2022-07-04","cited_by_count":95,"area":null},{"id":"2304.07493","title":"OliVe: Accelerating Large Language Models via Hardware-friendly Outlier-Victim Pair Quantization","created":"2023-04-15","cited_by_count":92,"area":null},{"id":"2208.09225","title":"FP8 Quantization: The Power of the Exponent","created":"2022-08-19","cited_by_count":88,"area":null},{"id":"2104.00903","title":"Network Quantization with Element-wise Gradient Scaling","created":"2021-04-02","cited_by_count":87,"area":null},{"id":"2310.00034","title":"PB-LLM: Partially Binarized Large Language Models","created":"2023-09-29","cited_by_count":83,"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":"2202.00661","title":"When Do Flat Minima Optimizers Work?","created":"2022-02-01","cited_by_count":78,"area":null},{"id":"2110.04869","title":"Global Vision Transformer Pruning with Hessian-Aware Saliency","created":"2021-10-10","cited_by_count":70,"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":"2405.14917","title":"SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models","created":"2024-05-23","cited_by_count":63,"area":null},{"id":"2103.05579","title":"hls4ml: An Open-Source Codesign Workflow to Empower Scientific Low-Power Machine Learning Devices","created":"2021-03-09","cited_by_count":62,"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":"2211.16056","title":"NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers","created":"2022-11-29","cited_by_count":61,"area":null},{"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,"area":null},{"id":"2306.11987","title":"Training Transformers with 4-bit Integers","created":"2023-06-21","cited_by_count":60,"area":null},{"id":"2202.07471","title":"SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation","created":"2022-02-14","cited_by_count":55,"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":"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":"2307.02973","title":"Pruning vs Quantization: Which is Better?","created":"2023-07-06","cited_by_count":46,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2101.08940","title":"Hessian-Aware Pruning and Optimal Neural Implant","created":"2021-01-22","cited_by_count":45,"area":null},{"id":"2104.09987","title":"Differentiable Model Compression via Pseudo Quantization Noise","created":"2021-04-20","cited_by_count":45,"area":null},{"id":"2202.07105","title":"A Survey on Model Compression and Acceleration for Pretrained Language Models","created":"2022-02-15","cited_by_count":45,"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":"2102.10462","title":"BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization","created":"2021-02-20","cited_by_count":39,"area":null},{"id":"2404.07236","title":"Lightweight Deep Learning for Resource-Constrained Environments: A Survey","created":"2024-04-08","cited_by_count":38,"area":null},{"id":"2410.10912","title":"AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models","created":"2024-10-14","cited_by_count":36,"area":null},{"id":"2206.00820","title":"NIPQ: Noise proxy-based Integrated Pseudo-Quantization","created":"2022-06-02","cited_by_count":35,"area":null},{"id":"2307.07982","title":"A Survey of Techniques for Optimizing Transformer Inference","created":"2023-07-16","cited_by_count":35,"area":null},{"id":"2107.11228","title":"Taxonomizing local versus global structure in neural network loss landscapes","created":"2021-07-23","cited_by_count":34,"area":null},{"id":"2304.10136","title":"Diversifying the High-level Features for better Adversarial Transferability","created":"2023-04-20","cited_by_count":34,"area":null},{"id":"2103.01519","title":"Hessian Eigenspectra of More Realistic Nonlinear Models","created":"2021-03-02","cited_by_count":33,"area":null},{"id":"2201.11113","title":"Post-training Quantization for Neural Networks with Provable Guarantees","created":"2022-01-26","cited_by_count":33,"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":"2204.11786","title":"Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications","created":"2022-04-25","cited_by_count":32,"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":"2403.12422","title":"Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization","created":"2024-03-19","cited_by_count":31,"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":"2208.05163","title":"Auto-ViT-Acc: An FPGA-Aware Automatic Acceleration Framework for Vision Transformer with Mixed-Scheme Quantization","created":"2022-08-10","cited_by_count":29,"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":"2411.05282","title":"MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization","created":"2024-11-08","cited_by_count":28,"area":null},{"id":"2207.10345","title":"CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution","created":"2022-07-21","cited_by_count":27,"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":"2207.07697","title":"POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Paging","created":"2022-07-15","cited_by_count":26,"area":null},{"id":"2109.12338","title":"Distribution-sensitive Information Retention for Accurate Binary Neural Network","created":"2021-09-25","cited_by_count":25,"area":null},{"id":"2111.12273","title":"Sharpness-aware Quantization for Deep Neural Networks","created":"2021-11-24","cited_by_count":25,"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":"2302.05397","title":"A Practical Mixed Precision Algorithm for Post-Training Quantization","created":"2023-02-10","cited_by_count":24,"area":null},{"id":"2301.12017","title":"Understanding INT4 Quantization for Transformer Models: Latency Speedup, Composability, and Failure Cases","created":"2023-01-27","cited_by_count":23,"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":"2307.10554","title":"EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization","created":"2023-07-20","cited_by_count":22,"area":null},{"id":"2502.12913","title":"GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning","created":"2025-02-18","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":"2312.00359","title":"Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training","created":"2023-12-01","cited_by_count":20,"area":null},{"id":"2202.02842","title":"Evaluating natural language processing models with generalization metrics that do not need access to any training or testing data","created":"2022-02-06","cited_by_count":19,"area":null},{"id":"2504.02508","title":"APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers","created":"2025-04-03","cited_by_count":19,"area":null},{"id":"2405.12725","title":"Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks","created":"2024-05-21","cited_by_count":18,"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":"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,"area":null},{"id":"2310.09499","title":"One-Shot Sensitivity-Aware Mixed Sparsity Pruning for Large Language Models","created":"2023-10-14","cited_by_count":16,"area":null},{"id":"2412.14590","title":"MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design","created":"2024-12-19","cited_by_count":16,"area":null},{"id":"2105.07320","title":"LocalNewton: Reducing Communication Bottleneck for Distributed Learning","created":"2021-05-16","cited_by_count":15,"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":"2403.06664","title":"Smart-Infinity: Fast Large Language Model Training using Near-Storage Processing on a Real System","created":"2024-03-11","cited_by_count":15,"area":null},{"id":"2112.06126","title":"Neural Network Quantization for Efficient Inference: A Survey","created":"2021-12-08","cited_by_count":14,"area":null},{"id":"2207.05022","title":"STI: Turbocharge NLP Inference at the Edge via Elastic Pipelining","created":"2022-07-11","cited_by_count":14,"area":null},{"id":"2312.08583","title":"ZeroQuant(4+2): Redefining LLMs Quantization with a New FP6-Centric Strategy for Diverse Generative Tasks","created":"2023-12-14","cited_by_count":14,"area":null},{"id":"2502.16638","title":"Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression","created":"2025-02-23","cited_by_count":14,"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":"2403.09344","title":"SketchINR: A First Look into Sketches as Implicit Neural Representations","created":"2024-03-14","cited_by_count":13,"area":null},{"id":"2410.06020","title":"QT-DoG: Quantization-aware Training for Domain Generalization","created":"2024-10-08","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":"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":"2105.00227","title":"On the Adversarial Robustness of Quantized Neural Networks","created":"2021-05-01","cited_by_count":11,"area":null},{"id":"2108.02720","title":"Generalizable Mixed-Precision Quantization via Attribution Rank Preservation","created":"2021-08-05","cited_by_count":11,"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":"2201.08050","title":"TerViT: An Efficient Ternary Vision Transformer","created":"2022-01-20","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":"2505.05530","title":"Low-bit Model Quantization for Deep Neural Networks: A Survey","created":"2025-05-08","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":"2112.11540","title":"Mixed Precision of Quantization of Transformer Language Models for Speech Recognition","created":"2021-11-29","cited_by_count":10,"area":null},{"id":"2206.07527","title":"QONNX: Representing Arbitrary-Precision Quantized Neural Networks","created":"2022-06-15","cited_by_count":10,"area":null}],"next_cursor":"100"}