{"total":60,"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":"2402.04291","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","created":"2024-02-06","cited_by_count":144,"area":null},{"id":"2203.11086","title":"Overcoming Oscillations in Quantization-Aware Training","created":"2022-03-21","cited_by_count":119,"area":null},{"id":"2107.04562","title":"The Bayesian Learning Rule","created":"2021-07-09","cited_by_count":99,"area":null},{"id":"2310.00034","title":"PB-LLM: Partially Binarized Large Language Models","created":"2023-09-29","cited_by_count":83,"area":null},{"id":"2405.14852","title":"PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression","created":"2024-05-23","cited_by_count":61,"area":null},{"id":"2302.02210","title":"Oscillation-free Quantization for Low-bit Vision Transformers","created":"2023-02-04","cited_by_count":57,"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":"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":"2103.00841","title":"Learning Frequency Domain Approximation for Binary Neural Networks","created":"2021-03-01","cited_by_count":38,"area":null},{"id":"2301.11233","title":"BiBench: Benchmarking and Analyzing Network Binarization","created":"2023-01-26","cited_by_count":22,"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":"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":"2102.04270","title":"Enabling Binary Neural Network Training on the Edge","created":"2021-02-08","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":"2201.08050","title":"TerViT: An Efficient Ternary Vision Transformer","created":"2022-01-20","cited_by_count":11,"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":"2303.03382","title":"Globally Optimal Training of Neural Networks with Threshold Activation Functions","created":"2023-03-06","cited_by_count":9,"area":null},{"id":"2106.06991","title":"BoolNet: Minimizing The Energy Consumption of Binary Neural Networks","created":"2021-06-13","cited_by_count":6,"area":null},{"id":"2206.04385","title":"HideNseek: Federated Lottery Ticket via Server-side Pruning and Sign Supermask","created":"2022-06-09","cited_by_count":6,"area":null},{"id":"2405.05171","title":"Custom Gradient Estimators are Straight-Through Estimators in Disguise","created":"2024-05-08","cited_by_count":6,"area":null},{"id":"2502.14344","title":"Towards Accurate Binary Spiking Neural Networks: Learning with Adaptive Gradient Modulation Mechanism","created":"2025-02-20","cited_by_count":5,"area":null},{"id":"2509.18763","title":"Bi-VLM: Pushing Ultra-Low Precision Post-Training Quantization Boundaries in Vision-Language Models","created":"2025-09-23","cited_by_count":5,"area":"mllm"},{"id":"2302.11286","title":"Neural-based classification rule learning for sequential data","created":"2023-02-22","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":"2402.17710","title":"Understanding Neural Network Binarization with Forward and Backward Proximal Quantizers","created":"2024-02-27","cited_by_count":4,"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":"2110.05850","title":"Improving Binary Neural Networks through Fully Utilizing Latent Weights","created":"2021-10-12","cited_by_count":3,"area":null},{"id":"2207.01916","title":"Hierarchical Symbolic Reasoning in Hyperbolic Space for Deep Discriminative Models","created":"2022-07-05","cited_by_count":3,"area":"lr"},{"id":"2405.16339","title":"BOLD: Boolean Logic Deep Learning","created":"2024-05-25","cited_by_count":3,"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":"2301.13584","title":"Straight-Through meets Sparse Recovery: the Support Exploration Algorithm","created":"2023-01-31","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":"2311.07427","title":"Boolean Variation and Boolean Logic BackPropagation","created":"2023-11-13","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":"2407.05257","title":"OvSW: Overcoming Silent Weights for Accurate Binary Neural Networks","created":"2024-07-07","cited_by_count":2,"area":null},{"id":"2203.09082","title":"Confidence Dimension for Deep Learning based on Hoeffding Inequality and Relative Evaluation","created":"2022-03-17","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":"2206.09029","title":"Binary Early-Exit Network for Adaptive Inference on Low-Resource Devices","created":"2022-06-17","cited_by_count":1,"area":"inference"},{"id":"2206.12322","title":"How to train accurate BNNs for embedded systems?","created":"2022-06-24","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":"2101.01163","title":"SmartDeal: Re-Modeling Deep Network Weights for Efficient Inference and Training","created":"2021-01-04","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":"2303.02452","title":"Understanding weight-magnitude hyperparameters in training binary networks","created":"2023-03-04","cited_by_count":0,"area":null},{"id":"2311.10296","title":"BiHRNet: A Binary high-resolution network for Human Pose Estimation","created":"2023-11-17","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":"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":"2605.09256","title":"Improving Generalization by Permutation Routing Across Model Copies","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2606.09112","title":"Hybridizing Equilibrium Propagation with Ising Machines for Efficient Energy-Based Learning","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.13454","title":"Optical Implementation of Equilibrium Propagation Using Spatial Photonic Ising Machines","created":"2026-06-11","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":"2610.07853","title":"Lost in the bf16 Cast: Exporting Ternary Language Models Can Revert Most Low-Learning-Rate Code Changes","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.10630","title":"Phase-HDC: Replacing Optimizer History with Gradient Thresholds in Discrete Phase Learning","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}