{"total":54,"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":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263,"area":null},{"id":"2212.09720","title":"The case for 4-bit precision: k-bit Inference Scaling Laws","created":"2022-12-19","cited_by_count":251,"area":null},{"id":"2406.01721","title":"DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs","created":"2024-06-03","cited_by_count":167,"area":null},{"id":"2203.10705","title":"Compression of Generative Pre-trained Language Models via Quantization","created":"2022-03-21","cited_by_count":79,"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":"2106.11309","title":"How Do Adam and Training Strategies Help BNNs Optimization?","created":"2021-06-21","cited_by_count":46,"area":null},{"id":"2110.06804","title":"A comprehensive review of Binary Neural Network","created":"2021-10-11","cited_by_count":45,"area":null},{"id":"2109.15082","title":"Towards Efficient Post-training Quantization of Pre-trained Language Models","created":"2021-09-30","cited_by_count":39,"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":"2211.07091","title":"BiViT: Extremely Compressed Binary Vision Transformer","created":"2022-11-14","cited_by_count":28,"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":"2301.11233","title":"BiBench: Benchmarking and Analyzing Network Binarization","created":"2023-01-26","cited_by_count":22,"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":"2305.16044","title":"Exploiting Noise as a Resource for Computation and Learning in Spiking Neural Networks","created":"2023-05-25","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":"2206.12372","title":"QReg: On Regularization Effects of Quantization","created":"2022-06-24","cited_by_count":11,"area":null},{"id":"2212.05735","title":"Adaptive Low-Precision Training for Embeddings in Click-Through Rate Prediction","created":"2022-12-12","cited_by_count":11,"area":null},{"id":"2408.03215","title":"FedBAT: Communication-Efficient Federated Learning via Learnable Binarization","created":"2024-08-06","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":"2112.02612","title":"Training Structured Neural Networks Through Manifold Identification and Variance Reduction","created":"2021-12-05","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":"2306.10185","title":"Spatial-SpinDrop: Spatial Dropout-based Binary Bayesian Neural Network with Spintronics Implementation","created":"2023-06-16","cited_by_count":7,"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":"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":"2302.03390","title":"Learning Discretized Neural Networks under Ricci Flow","created":"2023-02-07","cited_by_count":4,"area":null},{"id":"2104.10044","title":"BCNN: Binary Complex Neural Network","created":"2021-03-28","cited_by_count":3,"area":null},{"id":"2303.14470","title":"Compacting Binary Neural Networks by Sparse Kernel Selection","created":"2023-03-25","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":"2405.16339","title":"BOLD: Boolean Logic Deep Learning","created":"2024-05-25","cited_by_count":3,"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":"2208.01944","title":"PalQuant: Accelerating High-precision Networks on Low-precision Accelerators","created":"2022-08-03","cited_by_count":2,"area":null},{"id":"2210.03069","title":"PathProx: A Proximal Gradient Algorithm for Weight Decay Regularized Deep Neural Networks","created":"2022-10-06","cited_by_count":2,"area":null},{"id":"2401.16760","title":"One-Step Forward and Backtrack: Overcoming Zig-Zagging in Loss-Aware Quantization Training","created":"2024-01-30","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":"2107.03375","title":"Differentiable Architecture Pruning for Transfer Learning","created":"2021-07-07","cited_by_count":1,"area":null},{"id":"2206.03291","title":"GAAF: Searching Activation Functions for Binary Neural Networks through Genetic Algorithm","created":"2022-06-05","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":"2402.04012","title":"Quantized Approximately Orthogonal Recurrent Neural Networks","created":"2024-02-05","cited_by_count":1,"area":null},{"id":"2108.12704","title":"Compact representations of convolutional neural networks via weight pruning and quantization","created":"2021-08-28","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":"2210.03671","title":"A Closer Look at Hardware-Friendly Weight Quantization","created":"2022-10-07","cited_by_count":0,"area":null},{"id":"2210.13858","title":"LAB: Learnable Activation Binarizer for Binary Neural Networks","created":"2022-10-25","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":"2410.00050","title":"CycleBNN: Cyclic Precision Training in Binary Neural Networks","created":"2024-09-28","cited_by_count":0,"area":null},{"id":"2502.00047","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","created":"2025-01-28","cited_by_count":0,"area":null},{"id":"2503.01639","title":"Cauchy-Schwarz Regularizers","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2503.07107","title":"Towards Experience Replay for Class-Incremental Learning in Fully-Binary Networks","created":"2025-03-10","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}],"next_cursor":null}