{"total":63,"rows":[{"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":"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":"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":"2201.07703","title":"Q-ViT: Fully Differentiable Quantization for Vision Transformer","created":"2022-01-19","cited_by_count":37,"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":"2307.10554","title":"EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization","created":"2023-07-20","cited_by_count":22,"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":"2307.00331","title":"Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precision","created":"2023-07-01","cited_by_count":17,"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":"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":"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":"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":"2405.00645","title":"HGQ: High Granularity Quantization for Real-time Neural Networks on FPGAs","created":"2024-05-01","cited_by_count":9,"area":null},{"id":"2501.06357","title":"Mix-QViT: Mixed-Precision Vision Transformer Quantization Driven by Layer Importance and Quantization Sensitivity","created":"2025-01-10","cited_by_count":9,"area":null},{"id":"2503.03103","title":"Fast Jet Tagging with MLP-Mixers on FPGAs","created":"2025-03-05","cited_by_count":9,"area":null},{"id":"2401.11243","title":"LRP-QViT: Mixed-Precision Vision Transformer Quantization via Layer-wise Relevance Propagation","created":"2024-01-20","cited_by_count":8,"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":"2402.07545","title":"TransAxx: Efficient Transformers with Approximate Computing","created":"2024-02-12","cited_by_count":7,"area":null},{"id":"2508.15008","title":"Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applications","created":"2025-08-20","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":"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":"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":"2510.24784","title":"Sub-microsecond Transformers for Jet Tagging on FPGAs","created":"2025-10-26","cited_by_count":6,"area":null},{"id":"2206.15408","title":"Sub-8-Bit Quantization Aware Training for 8-Bit Neural Network Accelerator with On-Device Speech Recognition","created":"2022-06-30","cited_by_count":5,"area":null},{"id":"2307.13337","title":"Overcoming Distribution Mismatch in Quantizing Image Super-Resolution Networks","created":"2023-07-25","cited_by_count":5,"area":null},{"id":"2311.02758","title":"M4BRAM: Mixed-Precision Matrix-Matrix Multiplication in FPGA Block RAMs","created":"2023-11-05","cited_by_count":5,"area":null},{"id":"2109.03513","title":"Elastic Significant Bit Quantization and Acceleration for Deep Neural Networks","created":"2021-09-08","cited_by_count":4,"area":null},{"id":"2210.09188","title":"Sub-8-bit quantization for on-device speech recognition: a regularization-free approach","created":"2022-10-17","cited_by_count":4,"area":null},{"id":"2212.07818","title":"Towards Hardware-Specific Automatic Compression of Neural Networks","created":"2022-12-15","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":"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":"2412.06868","title":"Compression for Better: A General and Stable Lossless Compression Framework","created":"2024-12-09","cited_by_count":4,"area":null},{"id":"2503.12217","title":"TFHE-Coder: Evaluating LLM-agentic Fully Homomorphic Encryption Code Generation","created":"2025-03-15","cited_by_count":4,"area":"agents"},{"id":"2505.04861","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","created":"2025-05-08","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":"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":"2302.00193","title":"$\\rm A^2Q$: Aggregation-Aware Quantization for Graph Neural Networks","created":"2023-02-01","cited_by_count":3,"area":null},{"id":"2308.06422","title":"Sensitivity-Aware Mixed-Precision Quantization and Width Optimization of Deep Neural Networks Through Cluster-Based Tree-Structured Parzen Estimation","created":"2023-08-12","cited_by_count":3,"area":null},{"id":"2411.01417","title":"BF-IMNA: A Bit Fluid In-Memory Neural Architecture for Neural Network Acceleration","created":"2024-11-03","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":"2508.09176","title":"DQT: Dynamic Quantization Training via Dequantization-Free Nested Integer Arithmetic","created":"2025-08-07","cited_by_count":3,"area":null},{"id":"2108.13055","title":"Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directions","created":"2021-08-30","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":"2511.10004","title":"LampQ: Towards Accurate Layer-wise Mixed Precision Quantization for Vision Transformers","created":"2025-11-13","cited_by_count":2,"area":null},{"id":"2303.02347","title":"MetaGrad: Adaptive Gradient Quantization with Hypernetworks","created":"2023-03-04","cited_by_count":1,"area":null},{"id":"2304.06393","title":"Learning Accurate Performance Predictors for Ultrafast Automated Model Compression","created":"2023-04-13","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":"2409.20138","title":"Constraint Guided Model Quantization of Neural Networks","created":"2024-09-30","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},{"id":"2508.03002","title":"Where and How to Enhance: Discovering Bit-Width Contribution for Mixed Precision Quantization","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2510.21086","title":"DictPFL: Efficient and Private Federated Learning on Encrypted Gradients","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2601.21626","title":"HeRo-Q: A General Framework for Stable Low Bit Quantization via Hessian Conditioning","created":"2026-01-29","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":"2208.05880","title":"Automatic Hybrid-Precision Quantization for MIMO Detectors","created":"2022-08-11","cited_by_count":0,"area":null},{"id":"2304.03782","title":"AutoQNN: An End-to-End Framework for Automatically Quantizing Neural Networks","created":"2023-04-07","cited_by_count":0,"area":null},{"id":"2512.04746","title":"SignRoundV2: Toward Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs","created":"2025-12-04","cited_by_count":0,"area":null},{"id":"2601.01299","title":"T3C: Test-Time Tensor Compression with Consistency Guarantees","created":"2026-01-03","cited_by_count":0,"area":null},{"id":"2603.17891","title":"RAMP: Reinforcement Adaptive Mixed Precision Quantization for Efficient On Device LLM Inference","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2609.28262","title":"RAMP: Robust Adaptive Mixed-Precision Quantization for Edge CPU Vision Models","created":"2026-09-23","cited_by_count":0,"area":null}],"next_cursor":null}