{"total":117,"rows":[{"id":"2305.05176","title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","created":"2023-05-09","cited_by_count":853,"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":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263,"area":null},{"id":"2203.11086","title":"Overcoming Oscillations in Quantization-Aware Training","created":"2022-03-21","cited_by_count":119,"area":null},{"id":"2104.00903","title":"Network Quantization with Element-wise Gradient Scaling","created":"2021-04-02","cited_by_count":87,"area":null},{"id":"2104.08500","title":"Vision Transformer Pruning","created":"2021-04-17","cited_by_count":79,"area":null},{"id":"2212.07048","title":"PD-Quant: Post-Training Quantization based on Prediction Difference Metric","created":"2022-12-14","cited_by_count":73,"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":"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":"2103.12369","title":"ReCU: Reviving the Dead Weights in Binary Neural Networks","created":"2021-03-23","cited_by_count":52,"area":null},{"id":"2109.07865","title":"OMPQ: Orthogonal Mixed Precision Quantization","created":"2021-09-16","cited_by_count":39,"area":null},{"id":"2103.00841","title":"Learning Frequency Domain Approximation for Binary Neural Networks","created":"2021-03-01","cited_by_count":38,"area":null},{"id":"2208.08084","title":"AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets","created":"2022-08-17","cited_by_count":38,"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":"2209.02681","title":"How important are activation functions in regression and classification? A survey, performance comparison, and future directions","created":"2022-09-06","cited_by_count":29,"area":null},{"id":"2309.14592","title":"Efficient Post-training Quantization with FP8 Formats","created":"2023-09-26","cited_by_count":29,"area":"diffusion"},{"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":"2406.00800","title":"MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization","created":"2024-06-02","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":"2309.11932","title":"A Machine Learning-oriented Survey on Tiny Machine Learning","created":"2023-09-21","cited_by_count":27,"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":"2210.16103","title":"Collaborative Multi-Teacher Knowledge Distillation for Learning Low Bit-width Deep Neural Networks","created":"2022-10-27","cited_by_count":23,"area":"distill"},{"id":"2203.17008","title":"It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher","created":"2022-03-31","cited_by_count":20,"area":null},{"id":"2108.06983","title":"Distance-aware Quantization","created":"2021-08-16","cited_by_count":19,"area":null},{"id":"2308.06689","title":"Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training","created":"2023-08-13","cited_by_count":19,"area":null},{"id":"2102.07981","title":"SiMaN: Sign-to-Magnitude Network Binarization","created":"2021-02-16","cited_by_count":18,"area":null},{"id":"2104.08215","title":"\"BNN - BN = ?\": Training Binary Neural Networks without Batch Normalization","created":"2021-04-16","cited_by_count":17,"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":"2307.10638","title":"Quantized Feature Distillation for Network Quantization","created":"2023-07-20","cited_by_count":15,"area":"distill"},{"id":"2106.12169","title":"APNN-TC: Accelerating Arbitrary Precision Neural Networks on Ampere GPU Tensor Cores","created":"2021-06-23","cited_by_count":12,"area":null},{"id":"2207.02970","title":"Network Binarization via Contrastive Learning","created":"2022-07-06","cited_by_count":12,"area":null},{"id":"2205.14510","title":"Q-LIC: Quantizing Learned Image Compression with Channel Splitting","created":"2022-05-28","cited_by_count":10,"area":null},{"id":"2207.03920","title":"Towards Semantic Communication Protocols: A Probabilistic Logic Perspective","created":"2022-07-08","cited_by_count":10,"area":null},{"id":"2106.00050","title":"Continual 3D Convolutional Neural Networks for Real-time Processing of Videos","created":"2021-05-31","cited_by_count":9,"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":"2303.03382","title":"Globally Optimal Training of Neural Networks with Threshold Activation Functions","created":"2023-03-06","cited_by_count":9,"area":null},{"id":"2404.01278","title":"BiPer: Binary Neural Networks using a Periodic Function","created":"2024-04-01","cited_by_count":9,"area":null},{"id":"2407.20021","title":"MimiQ: Low-Bit Data-Free Quantization of Vision Transformers with Encouraging Inter-Head Attention Similarity","created":"2024-07-29","cited_by_count":9,"area":null},{"id":"2304.09049","title":"DeepGEMM: Accelerated Ultra Low-Precision Inference on CPU Architectures using Lookup Tables","created":"2023-04-18","cited_by_count":8,"area":null},{"id":"2107.03453","title":"$S^3$: Sign-Sparse-Shift Reparametrization for Effective Training of Low-bit Shift Networks","created":"2021-07-07","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":"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":"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":"2103.11083","title":"Compacting Deep Neural Networks for Internet of Things: Methods and Applications","created":"2021-03-20","cited_by_count":6,"area":null},{"id":"2204.10933","title":"A Tale of Two Models: Constructing Evasive Attacks on Edge Models","created":"2022-04-22","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":"2208.09708","title":"DenseShift: Towards Accurate and Efficient Low-Bit Power-of-Two Quantization","created":"2022-08-20","cited_by_count":5,"area":null},{"id":"2302.10899","title":"Feature Affinity Assisted Knowledge Distillation and Quantization of Deep Neural Networks on Label-Free Data","created":"2023-02-10","cited_by_count":5,"area":"distill"},{"id":"2307.13337","title":"Overcoming Distribution Mismatch in Quantizing Image Super-Resolution Networks","created":"2023-07-25","cited_by_count":5,"area":null},{"id":"2105.13890","title":"Towards Efficient Full 8-bit Integer DNN Online Training on Resource-limited Devices without Batch Normalization","created":"2021-05-27","cited_by_count":4,"area":null},{"id":"2111.09348","title":"End-to-End Learned Image Compression with Quantized Weights and Activations","created":"2021-11-17","cited_by_count":4,"area":null},{"id":"2201.05020","title":"Automatic Sparse Connectivity Learning for Neural Networks","created":"2022-01-13","cited_by_count":4,"area":null},{"id":"2202.10728","title":"Distilled Neural Networks for Efficient Learning to Rank","created":"2022-02-22","cited_by_count":4,"area":null},{"id":"2208.14839","title":"QuantNAS for super resolution: searching for efficient quantization-friendly architectures against quantization noise","created":"2022-08-31","cited_by_count":4,"area":null},{"id":"2211.06987","title":"BiFSMNv2: Pushing Binary Neural Networks for Keyword Spotting to Real-Network Performance","created":"2022-11-13","cited_by_count":4,"area":null},{"id":"2212.05326","title":"Vertical Layering of Quantized Neural Networks for Heterogeneous Inference","created":"2022-12-10","cited_by_count":4,"area":null},{"id":"2302.03390","title":"Learning Discretized Neural Networks under Ricci Flow","created":"2023-02-07","cited_by_count":4,"area":null},{"id":"2305.07931","title":"GSB: Group Superposition Binarization for Vision Transformer with Limited Training Samples","created":"2023-05-13","cited_by_count":4,"area":null},{"id":"2310.04469","title":"Taming Binarized Neural Networks and Mixed-Integer Programs","created":"2023-10-05","cited_by_count":4,"area":null},{"id":"2510.10693","title":"High-Dimensional Learning Dynamics of Quantized Models with Straight-Through Estimator","created":"2025-10-12","cited_by_count":4,"area":null},{"id":"2104.14124","title":"Condensation-Net: Memory-Efficient Network Architecture with Cross-Channel Pooling Layers and Virtual Feature Maps","created":"2021-04-29","cited_by_count":3,"area":null},{"id":"2110.05850","title":"Improving Binary Neural Networks through Fully Utilizing Latent Weights","created":"2021-10-12","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":"2211.10948","title":"FedDCT: Federated Learning of Large Convolutional Neural Networks on Resource Constrained Devices using Divide and Collaborative Training","created":"2022-11-20","cited_by_count":3,"area":null},{"id":"2212.10200","title":"Redistribution of Weights and Activations for AdderNet Quantization","created":"2022-12-20","cited_by_count":3,"area":null},{"id":"2310.15128","title":"Projected Stochastic Gradient Descent with Quantum Annealed Binary Gradients","created":"2023-10-23","cited_by_count":3,"area":null},{"id":"2405.17776","title":"The Binary Quantized Neural Network for Dense Prediction via Specially Designed Upsampling and Attention","created":"2024-05-28","cited_by_count":3,"area":null},{"id":"2510.20348","title":"AccuQuant: Simulating Multiple Denoising Steps for Quantizing Diffusion Models","created":"2025-10-23","cited_by_count":3,"area":"diffusion"},{"id":"2511.01077","title":"AI Progress Should Be Measured by Capability-Per-Resource, Not Scale Alone: A Framework for Gradient-Guided Resource Allocation in LLMs","created":"2025-11-02","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":"2201.00490","title":"Learning with Latent Structures in Natural Language Processing: A Survey","created":"2022-01-03","cited_by_count":2,"area":null},{"id":"2201.07634","title":"FAT: An In-Memory Accelerator with Fast Addition for Ternary Weight Neural Networks","created":"2022-01-19","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":"2204.01234","title":"Soft Threshold Ternary Networks","created":"2022-04-04","cited_by_count":2,"area":null},{"id":"2208.01944","title":"PalQuant: Accelerating High-precision Networks on Low-precision Accelerators","created":"2022-08-03","cited_by_count":2,"area":null},{"id":"2308.12438","title":"Deploying Deep Reinforcement Learning Systems: A Taxonomy of Challenges","created":"2023-08-23","cited_by_count":2,"area":null},{"id":"2404.19248","title":"Scheduling Weight Transitions for Quantization-Aware Training","created":"2024-04-30","cited_by_count":2,"area":null},{"id":"2505.18113","title":"Beyond Discreteness: Sample Complexity Analysis of Straight-Through Estimator for 1-bit Quantization","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2509.13662","title":"Deep Lookup Network","created":"2025-09-17","cited_by_count":2,"area":null},{"id":"2105.14202","title":"Universal Adder Neural Networks","created":"2021-05-29","cited_by_count":1,"area":null},{"id":"2107.01400","title":"Exact Backpropagation in Binary Weighted Networks with Group Weight Transformations","created":"2021-07-03","cited_by_count":1,"area":null},{"id":"2110.02456","title":"VC dimension of partially quantized neural networks in the overparametrized regime","created":"2021-10-06","cited_by_count":1,"area":null},{"id":"2111.01135","title":"Arch-Net: Model Distillation for Architecture Agnostic Model Deployment","created":"2021-11-01","cited_by_count":1,"area":null},{"id":"2202.04499","title":"Lightweight Jet Reconstruction and Identification as an Object Detection Task","created":"2022-02-09","cited_by_count":1,"area":null},{"id":"2210.08648","title":"AttTrack: Online Deep Attention Transfer for Multi-object Tracking","created":"2022-10-16","cited_by_count":1,"area":null},{"id":"2301.06193","title":"RedBit: An End-to-End Flexible Framework for Evaluating the Accuracy of Quantized CNNs","created":"2023-01-15","cited_by_count":1,"area":null},{"id":"2405.15778","title":"Investigation of Energy-efficient AI Model Architectures and Compression Techniques for \"Green\" Fetal Brain Segmentation","created":"2024-04-03","cited_by_count":1,"area":null},{"id":"2407.10016","title":"Characterizing Disparity Between Edge Models and High-Accuracy Base Models for Vision Tasks","created":"2024-07-13","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":"2501.09849","title":"Coded Deep Learning: Framework and Algorithm","created":"2025-01-16","cited_by_count":1,"area":null},{"id":"2506.09782","title":"Q-SAM2: Accurate Quantization for Segment Anything Model 2","created":"2025-06-11","cited_by_count":1,"area":null},{"id":"2507.04456","title":"BiVM: Accurate Binarized Neural Network for Efficient Video Matting","created":"2025-07-06","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":"2202.12422","title":"Standard Deviation-Based Quantization for Deep Neural Networks","created":"2022-02-24","cited_by_count":0,"area":null},{"id":"2206.02006","title":"Combinatorial optimization for low bit-width neural networks","created":"2022-06-04","cited_by_count":0,"area":null},{"id":"2206.08175","title":"Not All Lotteries Are Made Equal","created":"2022-06-16","cited_by_count":0,"area":null}],"next_cursor":"100"}