{"total":190,"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":"2110.02861","title":"8-bit Optimizers via Block-wise Quantization","created":"2021-10-06","cited_by_count":403,"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":"2103.01050","title":"Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical World","created":"2021-03-01","cited_by_count":127,"area":null},{"id":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","cited_by_count":122,"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":"2310.00034","title":"PB-LLM: Partially Binarized Large Language Models","created":"2023-09-29","cited_by_count":83,"area":null},{"id":"2304.13013","title":"Stable and low-precision training for large-scale vision-language models","created":"2023-04-25","cited_by_count":75,"area":"mllm"},{"id":"2210.08277","title":"Deep Differentiable Logic Gate Networks","created":"2022-10-15","cited_by_count":67,"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":"2103.01049","title":"Diversifying Sample Generation for Accurate Data-Free Quantization","created":"2021-03-01","cited_by_count":63,"area":null},{"id":"2301.11913","title":"SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient","created":"2023-01-27","cited_by_count":59,"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":"2110.06804","title":"A comprehensive review of Binary Neural Network","created":"2021-10-11","cited_by_count":45,"area":null},{"id":"2307.16867","title":"Revisiting the Parameter Efficiency of Adapters from the Perspective of Precision Redundancy","created":"2023-07-31","cited_by_count":44,"area":null},{"id":"2109.15103","title":"Scalable Rule-Based Representation Learning for Interpretable Classification","created":"2021-09-30","cited_by_count":40,"area":null},{"id":"2411.04732","title":"Convolutional Differentiable Logic Gate Networks","created":"2024-11-07","cited_by_count":37,"area":null},{"id":"2303.07700","title":"PATS: Patch Area Transportation with Subdivision for Local Feature Matching","created":"2023-03-14","cited_by_count":33,"area":null},{"id":"2107.13892","title":"QuPeD: Quantized Personalization via Distillation with Applications to Federated Learning","created":"2021-07-29","cited_by_count":32,"area":"distill"},{"id":"2108.09187","title":"Quantization Backdoors to Deep Learning Commercial Frameworks","created":"2021-08-20","cited_by_count":29,"area":null},{"id":"2303.08942","title":"Spherical Space Feature Decomposition for Guided Depth Map Super-Resolution","created":"2023-03-15","cited_by_count":28,"area":null},{"id":"2209.13362","title":"DELTAR: Depth Estimation from a Light-weight ToF Sensor and RGB Image","created":"2022-09-27","cited_by_count":26,"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":"2305.10299","title":"Binarized Spectral Compressive Imaging","created":"2023-05-17","cited_by_count":23,"area":null},{"id":"2306.15552","title":"A Survey on Deep Learning Hardware Accelerators for Heterogeneous HPC Platforms","created":"2023-06-27","cited_by_count":21,"area":null},{"id":"2209.01019","title":"On Quantizing Implicit Neural Representations","created":"2022-09-01","cited_by_count":20,"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":"2403.19944","title":"Binarized Low-light Raw Video Enhancement","created":"2024-03-29","cited_by_count":17,"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":"2310.14336","title":"Learning Interpretable Rules for Scalable Data Representation and Classification","created":"2023-10-22","cited_by_count":14,"area":null},{"id":"2406.12311","title":"Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language Models","created":"2024-06-18","cited_by_count":14,"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":"2501.13492","title":"Quantized Spike-driven Transformer","created":"2025-01-23","cited_by_count":13,"area":null},{"id":"2111.07392","title":"Edge-Native Intelligence for 6G Communications Driven by Federated Learning: A Survey of Trends and Challenges","created":"2021-11-14","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":"2406.13672","title":"Q-SNNs: Quantized Spiking Neural Networks","created":"2024-06-19","cited_by_count":12,"area":null},{"id":"2501.05867","title":"Neural Network Verification is a Programming Language Challenge","created":"2025-01-10","cited_by_count":12,"area":null},{"id":"2102.04270","title":"Enabling Binary Neural Network Training on the Edge","created":"2021-02-08","cited_by_count":11,"area":null},{"id":"2109.00212","title":"Diverse Sample Generation: Pushing the Limit of Generative Data-free Quantization","created":"2021-09-01","cited_by_count":11,"area":null},{"id":"2110.13220","title":"Demystifying and Generalizing BinaryConnect","created":"2021-10-25","cited_by_count":11,"area":null},{"id":"2112.02880","title":"AdaSTE: An Adaptive Straight-Through Estimator to Train Binary Neural Networks","created":"2021-12-06","cited_by_count":11,"area":null},{"id":"2206.04864","title":"Binarizing Split Learning for Data Privacy Enhancement and Computation Reduction","created":"2022-06-10","cited_by_count":11,"area":null},{"id":"2404.05662","title":"BinaryDM: Accurate Weight Binarization for Efficient Diffusion Models","created":"2024-04-08","cited_by_count":11,"area":"diffusion"},{"id":"2506.13771","title":"LittleBit: Ultra Low-Bit Quantization via Latent Factorization","created":"2025-05-30","cited_by_count":11,"area":null},{"id":"2212.00325","title":"HashVFL: Defending Against Data Reconstruction Attacks in Vertical Federated Learning","created":"2022-12-01","cited_by_count":10,"area":null},{"id":"2307.16418","title":"DRAW: Defending Camera-shooted RAW against Image Manipulation","created":"2023-07-31","cited_by_count":10,"area":null},{"id":"2308.07650","title":"EQ-Net: Elastic Quantization Neural Networks","created":"2023-08-15","cited_by_count":10,"area":null},{"id":"2112.03406","title":"Equal Bits: Enforcing Equally Distributed Binary Network Weights","created":"2021-12-02","cited_by_count":9,"area":null},{"id":"2311.11883","title":"Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review","created":"2023-11-20","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":"2105.11013","title":"Distributed CNN Inference on Resource-Constrained UAVs for Surveillance Systems: Design and Optimization","created":"2021-05-23","cited_by_count":8,"area":null},{"id":"2307.15712","title":"Quantum-limited stochastic optical neural networks operating at a few quanta per activation","created":"2023-07-28","cited_by_count":8,"area":null},{"id":"2308.04637","title":"Sparse Binary Transformers for Multivariate Time Series Modeling","created":"2023-08-09","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":"2110.01899","title":"Random matrices in service of ML footprint: ternary random features with no performance loss","created":"2021-10-05","cited_by_count":7,"area":null},{"id":"2111.11165","title":"Graph-Based Similarity of Neural Network Representations","created":"2021-11-22","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":"2405.14136","title":"Efficient Multitask Dense Predictor via Binarization","created":"2024-05-23","cited_by_count":7,"area":null},{"id":"2110.02998","title":"Federated Learning via Plurality Vote","created":"2021-10-06","cited_by_count":6,"area":null},{"id":"2208.13363","title":"Survey: Exploiting Data Redundancy for Optimization of Deep Learning","created":"2022-08-29","cited_by_count":6,"area":null},{"id":"2211.08410","title":"Low Latency Conversion of Artificial Neural Network Models to Rate-encoded Spiking Neural Networks","created":"2022-10-27","cited_by_count":6,"area":null},{"id":"2304.00245","title":"Reusing Deep Neural Network Models through Model Re-engineering","created":"2023-04-01","cited_by_count":6,"area":null},{"id":"2305.08117","title":"MBQuant: A Novel Multi-Branch Topology Method for Arbitrary Bit-width Network Quantization","created":"2023-05-14","cited_by_count":6,"area":null},{"id":"2510.15655","title":"WARP-LUTs -- Walsh-Assisted Relaxation for Probabilistic Look Up Tables","created":"2025-10-17","cited_by_count":6,"area":null},{"id":"2106.10254","title":"An Empirical Investigation into Deep and Shallow Rule Learning","created":"2021-06-18","cited_by_count":5,"area":null},{"id":"2110.11290","title":"Physical Side-Channel Attacks on Embedded Neural Networks: A Survey","created":"2021-10-21","cited_by_count":5,"area":null},{"id":"2301.00912","title":"Distributed Machine Learning for UAV Swarms: Computing, Sensing, and Semantics","created":"2023-01-03","cited_by_count":5,"area":null},{"id":"2110.11382","title":"Efficient and Robust Mixed-Integer Optimization Methods for Training Binarized Deep Neural Networks","created":"2021-10-21","cited_by_count":4,"area":null},{"id":"2204.10687","title":"SNE: an Energy-Proportional Digital Accelerator for Sparse Event-Based Convolutions","created":"2022-04-22","cited_by_count":4,"area":null},{"id":"2205.08671","title":"K-textures, a self-supervised hard clustering deep learning algorithm for satellite image segmentation","created":"2022-05-18","cited_by_count":4,"area":null},{"id":"2307.05035","title":"Number Systems for Deep Neural Network Architectures: A Survey","created":"2023-07-11","cited_by_count":4,"area":null},{"id":"2309.06047","title":"Real-Time Semantic Segmentation: A Brief Survey & Comparative Study in Remote Sensing","created":"2023-09-12","cited_by_count":4,"area":null},{"id":"2401.09916","title":"Enabling On-device Continual Learning with Binary Neural Networks","created":"2024-01-18","cited_by_count":4,"area":null},{"id":"2409.08824","title":"Pathfinder for Low-altitude Aircraft with Binary Neural Network","created":"2024-09-13","cited_by_count":4,"area":null},{"id":"2505.19932","title":"Logic Gate Neural Networks are Good for Verification","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2603.08725","title":"Performance Analysis of Edge and In-Sensor AI Processors: A Comparative Review","created":"2026-02-18","cited_by_count":4,"area":null},{"id":"2102.11786","title":"QuPeL: Quantized Personalization with Applications to Federated Learning","created":"2021-02-23","cited_by_count":3,"area":null},{"id":"2104.05124","title":"A Bop and Beyond: A Second Order Optimizer for Binarized Neural Networks","created":"2021-04-11","cited_by_count":3,"area":null},{"id":"2104.10044","title":"BCNN: Binary Complex Neural Network","created":"2021-03-28","cited_by_count":3,"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":"2203.17089","title":"Quantum-Aided Meta-Learning for Bayesian Binary Neural Networks via Born Machines","created":"2022-03-31","cited_by_count":3,"area":null},{"id":"2209.03450","title":"Seeking Interpretability and Explainability in Binary Activated Neural Networks","created":"2022-09-07","cited_by_count":3,"area":null},{"id":"2303.06516","title":"Efficient Computation of Shap Explanation Scores for Neural Network Classifiers via Knowledge Compilation","created":"2023-03-11","cited_by_count":3,"area":null},{"id":"2305.19295","title":"Low Precision Quantization-aware Training in Spiking Neural Networks with Differentiable Quantization Function","created":"2023-05-30","cited_by_count":3,"area":null},{"id":"2308.15308","title":"On-Device Learning with Binary Neural Networks","created":"2023-08-29","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":"2311.03408","title":"Training Multi-layer Neural Networks on Ising Machine","created":"2023-11-06","cited_by_count":3,"area":null},{"id":"2312.06446","title":"Measurement-driven neural-network training for integrated magnetic tunnel junction arrays","created":"2023-12-11","cited_by_count":3,"area":null},{"id":"2405.16339","title":"BOLD: Boolean Logic Deep Learning","created":"2024-05-25","cited_by_count":3,"area":null},{"id":"2501.05904","title":"Binary Event-Driven Spiking Transformer","created":"2025-01-10","cited_by_count":3,"area":null},{"id":"2506.11431","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","created":"2025-06-13","cited_by_count":3,"area":null},{"id":"2103.05985","title":"Multi-Pretext Attention Network for Few-shot Learning with Self-supervision","created":"2021-03-10","cited_by_count":2,"area":null},{"id":"2103.14872","title":"Deep Learning Techniques for In-Crop Weed Identification: A Review","created":"2021-03-27","cited_by_count":2,"area":null},{"id":"2104.02306","title":"Binary Neural Network for Speaker Verification","created":"2021-04-06","cited_by_count":2,"area":null},{"id":"2112.00737","title":"Hardware-friendly Deep Learning by Network Quantization and Binarization","created":"2021-12-01","cited_by_count":2,"area":null},{"id":"2203.05704","title":"Deep Binary Reinforcement Learning for Scalable Verification","created":"2022-03-11","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}],"next_cursor":"100"}