{"total":37,"rows":[{"id":"2310.00034","title":"PB-LLM: Partially Binarized Large Language Models","created":"2023-09-29","cited_by_count":83,"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":"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":"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":"2109.12338","title":"Distribution-sensitive Information Retention for Accurate Binary Neural Network","created":"2021-09-25","cited_by_count":25,"area":null},{"id":"2304.00253","title":"Q-DETR: An Efficient Low-Bit Quantized Detection Transformer","created":"2023-04-01","cited_by_count":24,"area":null},{"id":"2104.11883","title":"Carrying out CNN Channel Pruning in a White Box","created":"2021-04-24","cited_by_count":22,"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":"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":"2501.13492","title":"Quantized Spike-driven Transformer","created":"2025-01-23","cited_by_count":13,"area":null},{"id":"2207.02970","title":"Network Binarization via Contrastive Learning","created":"2022-07-06","cited_by_count":12,"area":null},{"id":"2104.08700","title":"Lottery Jackpots Exist in Pre-trained Models","created":"2021-04-18","cited_by_count":10,"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":"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":"2306.01841","title":"Binary and Ternary Natural Language Generation","created":"2023-06-02","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":"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":"2103.02394","title":"Self-Distribution Binary Neural Networks","created":"2021-03-03","cited_by_count":4,"area":null},{"id":"2207.14696","title":"BiFeat: Supercharge GNN Training via Graph Feature Quantization","created":"2022-07-29","cited_by_count":4,"area":null},{"id":"2212.05326","title":"Vertical Layering of Quantized Neural Networks for Heterogeneous Inference","created":"2022-12-10","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":"2303.14470","title":"Compacting Binary Neural Networks by Sparse Kernel Selection","created":"2023-03-25","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":"2303.03645","title":"Filter Pruning based on Information Capacity and Independence","created":"2023-03-07","cited_by_count":2,"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":"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":"2211.06739","title":"Partial Binarization of Neural Networks for Budget-Aware Efficient Learning","created":"2022-11-12","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":"2403.01845","title":"NASH: Neural Architecture Search for Hardware-Optimized Machine Learning Models","created":"2024-03-04","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":"2503.07107","title":"Towards Experience Replay for Class-Incremental Learning in Fully-Binary Networks","created":"2025-03-10","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":"2608.09388","title":"Efficient Human-Contact Representation for Human-Scene Interaction","created":"2026-08-10","cited_by_count":0,"area":null}],"next_cursor":null}