{"total":97,"rows":[{"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":"2310.11453","title":"BitNet: Scaling 1-bit Transformers for Large Language Models","created":"2023-10-17","cited_by_count":189,"area":null},{"id":"2111.14826","title":"Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation","created":"2021-11-29","cited_by_count":79,"area":null},{"id":"2201.00814","title":"Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space","created":"2022-01-03","cited_by_count":66,"area":null},{"id":"2103.09377","title":"Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted Network","created":"2021-03-17","cited_by_count":55,"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":"2112.00133","title":"PokeBNN: A Binary Pursuit of Lightweight Accuracy","created":"2021-11-30","cited_by_count":49,"area":null},{"id":"2110.06804","title":"A comprehensive review of Binary Neural Network","created":"2021-10-11","cited_by_count":45,"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":"2108.09187","title":"Quantization Backdoors to Deep Learning Commercial Frameworks","created":"2021-08-20","cited_by_count":29,"area":null},{"id":"2309.01885","title":"QuantEase: Optimization-based Quantization for Language Models","created":"2023-09-05","cited_by_count":29,"area":null},{"id":"2211.07091","title":"BiViT: Extremely Compressed Binary Vision Transformer","created":"2022-11-14","cited_by_count":28,"area":null},{"id":"2403.06213","title":"$V_kD:$ Improving Knowledge Distillation using Orthogonal Projections","created":"2024-03-10","cited_by_count":26,"area":"distill"},{"id":"2109.12338","title":"Distribution-sensitive Information Retention for Accurate Binary Neural Network","created":"2021-09-25","cited_by_count":25,"area":null},{"id":"2109.12872","title":"Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks","created":"2021-09-27","cited_by_count":25,"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":"2301.11233","title":"BiBench: Benchmarking and Analyzing Network Binarization","created":"2023-01-26","cited_by_count":22,"area":null},{"id":"2209.09004","title":"EcoFormer: Energy-Saving Attention with Linear Complexity","created":"2022-09-19","cited_by_count":21,"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":"2402.00422","title":"Lightweight Pixel Difference Networks for Efficient Visual Representation Learning","created":"2024-02-01","cited_by_count":17,"area":null},{"id":"2110.00337","title":"PhiNets: a scalable backbone for low-power AI at the edge","created":"2021-10-01","cited_by_count":16,"area":null},{"id":"2107.02751","title":"Quantum Annealing Formulation for Binary Neural Networks","created":"2021-07-05","cited_by_count":15,"area":null},{"id":"2207.06540","title":"Lipschitz Continuity Retained Binary Neural Network","created":"2022-07-13","cited_by_count":14,"area":null},{"id":"2211.12933","title":"Join the High Accuracy Club on ImageNet with A Binary Neural Network Ticket","created":"2022-11-23","cited_by_count":14,"area":null},{"id":"2103.08953","title":"Training Dynamical Binary Neural Networks with Equilibrium Propagation","created":"2021-03-16","cited_by_count":13,"area":null},{"id":"2110.05185","title":"Dynamic Binary Neural Network by learning channel-wise thresholds","created":"2021-10-08","cited_by_count":13,"area":null},{"id":"2407.03548","title":"HiDiff: Hybrid Diffusion Framework for Medical Image Segmentation","created":"2024-07-03","cited_by_count":13,"area":"diffusion"},{"id":"2207.02970","title":"Network Binarization via Contrastive Learning","created":"2022-07-06","cited_by_count":12,"area":null},{"id":"2103.13813","title":"RA-BNN: Constructing Robust & Accurate Binary Neural Network to Simultaneously Defend Adversarial Bit-Flip Attack and Improve Accuracy","created":"2021-03-22","cited_by_count":11,"area":null},{"id":"2412.05926","title":"BiDM: Pushing the Limit of Quantization for Diffusion Models","created":"2024-12-08","cited_by_count":11,"area":"diffusion"},{"id":"2112.03406","title":"Equal Bits: Enforcing Equally Distributed Binary Network Weights","created":"2021-12-02","cited_by_count":9,"area":null},{"id":"2204.07439","title":"INSTA-BNN: Binary Neural Network with INSTAnce-aware Threshold","created":"2022-04-15","cited_by_count":9,"area":null},{"id":"2205.06701","title":"Knowledge Distillation Meets Open-Set Semi-Supervised Learning","created":"2022-05-13","cited_by_count":9,"area":"distill"},{"id":"2404.01278","title":"BiPer: Binary Neural Networks using a Periodic Function","created":"2024-04-01","cited_by_count":9,"area":null},{"id":"2110.09195","title":"Sub-bit Neural Networks: Learning to Compress and Accelerate Binary Neural Networks","created":"2021-10-18","cited_by_count":8,"area":null},{"id":"2502.13179","title":"PTQ1.61: Push the Real Limit of Extremely Low-Bit Post-Training Quantization Methods for Large Language Models","created":"2025-02-18","cited_by_count":8,"area":null},{"id":"2305.14730","title":"BinaryViT: Towards Efficient and Accurate Binary Vision Transformers","created":"2023-05-24","cited_by_count":7,"area":null},{"id":"2303.11127","title":"MT-SNN: Enhance Spiking Neural Network with Multiple Thresholds","created":"2023-03-20","cited_by_count":6,"area":null},{"id":"2311.15816","title":"Scale-Dropout: Estimating Uncertainty in Deep Neural Networks Using Stochastic Scale","created":"2023-11-27","cited_by_count":6,"area":null},{"id":"2111.10854","title":"XnODR and XnIDR: Two Accurate and Fast Fully Connected Layers For Convolutional Neural Networks","created":"2021-11-21","cited_by_count":5,"area":null},{"id":"2202.06483","title":"BiFSMN: Binary Neural Network for Keyword Spotting","created":"2022-02-14","cited_by_count":5,"area":null},{"id":"2403.03739","title":"A&B BNN: Add&Bit-Operation-Only Hardware-Friendly Binary Neural Network","created":"2024-03-06","cited_by_count":5,"area":null},{"id":"2103.02394","title":"Self-Distribution Binary Neural Networks","created":"2021-03-03","cited_by_count":4,"area":null},{"id":"2205.09120","title":"Fast matrix multiplication for binary and ternary CNNs on ARM CPU","created":"2022-05-18","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":"2303.12270","title":"SCALES: Boost Binary Neural Network for Image Super-Resolution with Efficient Scalings","created":"2023-03-22","cited_by_count":4,"area":null},{"id":"2305.02522","title":"BitGNN: Unleashing the Performance Potential of Binary Graph Neural Networks on GPUs","created":"2023-05-04","cited_by_count":4,"area":null},{"id":"2105.03822","title":"RBNN: Memory-Efficient Reconfigurable Deep Binary Neural Network with IP Protection for Internet of Things","created":"2021-05-09","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":"2110.08562","title":"BNAS v2: Learning Architectures for Binary Networks with Empirical Improvements","created":"2021-10-16","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":"2310.15128","title":"Projected Stochastic Gradient Descent with Quantum Annealed Binary Gradients","created":"2023-10-23","cited_by_count":3,"area":null},{"id":"2408.14267","title":"1-Bit FQT: Pushing the Limit of Fully Quantized Training to 1-bit","created":"2024-08-26","cited_by_count":3,"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":"2112.05215","title":"Road Extraction from Overhead Images with Graph Neural Networks","created":"2021-12-09","cited_by_count":2,"area":null},{"id":"2205.07433","title":"Binarizing by Classification: Is soft function really necessary?","created":"2022-05-16","cited_by_count":2,"area":null},{"id":"2205.11179","title":"Online Hybrid Lightweight Representations Learning: Its Application to Visual Tracking","created":"2022-05-23","cited_by_count":2,"area":null},{"id":"2206.12794","title":"CTMQ: Cyclic Training of Convolutional Neural Networks with Multiple Quantization Steps","created":"2022-06-26","cited_by_count":2,"area":null},{"id":"2207.06893","title":"E2FIF: Push the limit of Binarized Deep Imagery Super-resolution using End-to-end Full-precision Information Flow","created":"2022-07-14","cited_by_count":2,"area":null},{"id":"2304.00952","title":"Optimizing data-flow in Binary Neural Networks","created":"2023-04-03","cited_by_count":2,"area":null},{"id":"2407.05257","title":"OvSW: Overcoming Silent Weights for Accurate Binary Neural Networks","created":"2024-07-07","cited_by_count":2,"area":null},{"id":"2506.03515","title":"BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2507.03504","title":"Information-Bottleneck Driven Binary Neural Network for Change Detection","created":"2025-07-04","cited_by_count":2,"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":"2206.12322","title":"How to train accurate BNNs for embedded systems?","created":"2022-06-24","cited_by_count":1,"area":null},{"id":"2211.11331","title":"BrainTTA: A 35 fJ/op Compiler Programmable Mixed-Precision Transport-Triggered NN SoC","created":"2022-11-21","cited_by_count":1,"area":null},{"id":"2211.13838","title":"Signed Binary Weight Networks","created":"2022-11-25","cited_by_count":1,"area":null},{"id":"2303.15493","title":"Binarizing Sparse Convolutional Networks for Efficient Point Cloud Analysis","created":"2023-03-27","cited_by_count":1,"area":null},{"id":"2403.01046","title":"A Library of Mirrors: Deep Neural Nets in Low Dimensions are Convex Lasso Models with Reflection Features","created":"2024-03-02","cited_by_count":1,"area":null},{"id":"2412.00119","title":"Training Multi-Layer Binary Neural Networks With Local Binary Error Signals","created":"2024-11-28","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":"2111.06457","title":"Variability-Aware Training and Self-Tuning of Highly Quantized DNNs for Analog PIM","created":"2021-11-11","cited_by_count":0,"area":null},{"id":"2205.09839","title":"HyBNN and FedHyBNN: (Federated) Hybrid Binary Neural Networks","created":"2022-05-19","cited_by_count":0,"area":null},{"id":"2206.03325","title":"Searching Similarity Measure for Binarized Neural Networks","created":"2022-06-05","cited_by_count":0,"area":null},{"id":"2206.12358","title":"Low- and Mixed-Precision Inference Accelerators","created":"2022-06-24","cited_by_count":0,"area":null},{"id":"2209.15317","title":"Convolutional Neural Networks Quantization with Attention","created":"2022-09-30","cited_by_count":0,"area":null},{"id":"2210.02637","title":"IR2Net: Information Restriction and Information Recovery for Accurate Binary Neural Networks","created":"2022-10-06","cited_by_count":0,"area":null},{"id":"2211.02292","title":"Boosting Binary Neural Networks via Dynamic Thresholds Learning","created":"2022-11-04","cited_by_count":0,"area":null},{"id":"2303.02452","title":"Understanding weight-magnitude hyperparameters in training binary networks","created":"2023-03-04","cited_by_count":0,"area":null},{"id":"2304.04985","title":"Efficient Feature Description for Small Body Relative Navigation using Binary Convolutional Neural Networks","created":"2023-04-11","cited_by_count":0,"area":null},{"id":"2304.11706","title":"Deep Convolutional Tables: Deep Learning without Convolutions","created":"2023-04-23","cited_by_count":0,"area":null},{"id":"2306.15390","title":"DCP-NAS: Discrepant Child-Parent Neural Architecture Search for 1-bit CNNs","created":"2023-06-27","cited_by_count":0,"area":null},{"id":"2308.13735","title":"MST-compression: Compressing and Accelerating Binary Neural Networks with Minimum Spanning Tree","created":"2023-08-26","cited_by_count":0,"area":null},{"id":"2310.10321","title":"Hamming Encoder: Mining Discriminative k-mers for Discrete Sequence Classification","created":"2023-10-16","cited_by_count":0,"area":null},{"id":"2312.01581","title":"PLUM: Improving Inference Efficiency By Leveraging Repetition-Sparsity Trade-Off","created":"2023-12-04","cited_by_count":0,"area":null},{"id":"2312.13575","title":"ARBiBench: Benchmarking Adversarial Robustness of Binarized Neural Networks","created":"2023-12-21","cited_by_count":0,"area":null},{"id":"2404.00285","title":"Long-Tailed Recognition on Binary Networks by Calibrating A Pre-trained Model","created":"2024-03-30","cited_by_count":0,"area":null},{"id":"2408.11918","title":"Interpretable Classification via a Rule Network with Selective Logical Operators","created":"2024-08-21","cited_by_count":0,"area":null},{"id":"2412.00054","title":"Less is More: Efficient Model Merging with Binary Task Switch","created":"2024-11-24","cited_by_count":0,"area":null},{"id":"2501.03471","title":"Hyperbolic Binary Neural Network","created":"2025-01-07","cited_by_count":0,"area":null},{"id":"2503.23709","title":"Expanding-and-Shrinking Binary Neural Networks","created":"2025-03-31","cited_by_count":0,"area":null},{"id":"2512.04189","title":"BEP: A Binary Error Propagation Algorithm for Binary Neural Networks Training","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2601.22660","title":"Layerwise Progressive Freezing Enables STE-Free Training of Deep Binary Neural Networks","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2606.27759","title":"Layerwise Progressive Freezing: A Training Scaffold for Depth-Scalable Binary Networks","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2608.16756","title":"Binarized High-Efficiency RAW Video Restoration and Beyond","created":"2026-08-17","cited_by_count":0,"area":null}],"next_cursor":null}