{"total":46,"rows":[{"id":"2310.11453","title":"BitNet: Scaling 1-bit Transformers for Large Language Models","created":"2023-10-17","cited_by_count":189,"area":null},{"id":"2306.11987","title":"Training Transformers with 4-bit Integers","created":"2023-06-21","cited_by_count":60,"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":"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":"2211.07091","title":"BiViT: Extremely Compressed Binary Vision Transformer","created":"2022-11-14","cited_by_count":28,"area":null},{"id":"2111.12273","title":"Sharpness-aware Quantization for Deep Neural Networks","created":"2021-11-24","cited_by_count":25,"area":null},{"id":"2203.09680","title":"LeHDC: Learning-Based Hyperdimensional Computing Classifier","created":"2022-03-18","cited_by_count":17,"area":null},{"id":"2307.00331","title":"Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precision","created":"2023-07-01","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":"2110.05185","title":"Dynamic Binary Neural Network by learning channel-wise thresholds","created":"2021-10-08","cited_by_count":13,"area":null},{"id":"2302.04907","title":"Binarized Neural Machine Translation","created":"2023-02-09","cited_by_count":13,"area":null},{"id":"2110.14583","title":"Deep learning via message passing algorithms based on belief propagation","created":"2021-10-27","cited_by_count":12,"area":null},{"id":"2407.07093","title":"FBI-LLM: Scaling Up Fully Binarized LLMs from Scratch via Autoregressive Distillation","created":"2024-07-09","cited_by_count":12,"area":null},{"id":"2201.08050","title":"TerViT: An Efficient Ternary Vision Transformer","created":"2022-01-20","cited_by_count":11,"area":null},{"id":"2203.04894","title":"A Brain-Inspired Low-Dimensional Computing Classifier for Inference on Tiny Devices","created":"2022-03-09","cited_by_count":11,"area":null},{"id":"2405.14136","title":"Efficient Multitask Dense Predictor via Binarization","created":"2024-05-23","cited_by_count":7,"area":null},{"id":"2209.01404","title":"Towards Accurate Binary Neural Networks via Modeling Contextual Dependencies","created":"2022-09-03","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":"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":"2407.16020","title":"Sparks of Quantum Advantage and Rapid Retraining in Machine Learning","created":"2024-07-22","cited_by_count":5,"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":"2404.00103","title":"PikeLPN: Mitigating Overlooked Inefficiencies of Low-Precision Neural Networks","created":"2024-03-29","cited_by_count":4,"area":null},{"id":"2409.09245","title":"Robust Training of Neural Networks at Arbitrary Precision and Sparsity","created":"2024-09-14","cited_by_count":3,"area":null},{"id":"2504.18911","title":"A Langevin sampling algorithm inspired by the Adam optimizer","created":"2025-04-26","cited_by_count":3,"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":"2207.09049","title":"RepBNN: towards a precise Binary Neural Network with Enhanced Feature Map via Repeating","created":"2022-07-19","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":"2206.12322","title":"How to train accurate BNNs for embedded systems?","created":"2022-06-24","cited_by_count":1,"area":null},{"id":"2306.13515","title":"Binary domain generalization for sparsifying binary neural networks","created":"2023-06-23","cited_by_count":1,"area":null},{"id":"2405.17932","title":"Towards Communication-efficient Federated Learning via Sparse and Aligned Adaptive Optimization","created":"2024-05-28","cited_by_count":1,"area":null},{"id":"2502.14075","title":"Towards Vector Optimization on Low-Dimensional Vector Symbolic Architecture","created":"2025-02-19","cited_by_count":1,"area":null},{"id":"2209.15317","title":"Convolutional Neural Networks Quantization with Attention","created":"2022-09-30","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":"2303.14693","title":"Robotic Packaging Optimization with Reinforcement Learning","created":"2023-03-26","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":"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":"2410.06974","title":"Diagnosis of Malignant Lymphoma Cancer Using Hybrid Optimized Techniques Based on Dense Neural Networks","created":"2024-10-09","cited_by_count":0,"area":null},{"id":"2410.07547","title":"Rethinking SNN Online Training and Deployment: Gradient-Coherent Learning via Hybrid-Driven LIF Model","created":"2024-10-10","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":"2508.12609","title":"A Self-Ensemble Inspired Approach for Effective Training of Binary-Weight Spiking Neural Networks","created":"2025-08-18","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}