{"total":44,"rows":[{"id":"2402.17764","title":"The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits","created":"2024-02-27","cited_by_count":308,"area":null},{"id":"2310.11453","title":"BitNet: Scaling 1-bit Transformers for Large Language Models","created":"2023-10-17","cited_by_count":189,"area":null},{"id":"2504.12285","title":"BitNet b1.58 2B4T Technical Report","created":"2025-04-16","cited_by_count":38,"area":null},{"id":"2406.03287","title":"SpikeLM: Towards General Spike-Driven Language Modeling via Elastic Bi-Spiking Mechanisms","created":"2024-06-05","cited_by_count":31,"area":null},{"id":"2407.04752","title":"SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spiking","created":"2024-07-05","cited_by_count":31,"area":null},{"id":"2301.11233","title":"BiBench: Benchmarking and Analyzing Network Binarization","created":"2023-01-26","cited_by_count":22,"area":null},{"id":"2301.09858","title":"PowerQuant: Automorphism Search for Non-Uniform Quantization","created":"2023-01-24","cited_by_count":20,"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":"2302.04907","title":"Binarized Neural Machine Translation","created":"2023-02-09","cited_by_count":13,"area":null},{"id":"2406.09477","title":"Q-S5: Towards Quantized State Space Models","created":"2024-06-13","cited_by_count":10,"area":null},{"id":"2204.07439","title":"INSTA-BNN: Binary Neural Network with INSTAnce-aware Threshold","created":"2022-04-15","cited_by_count":9,"area":null},{"id":"2308.05600","title":"NUPES : Non-Uniform Post-Training Quantization via Power Exponent Search","created":"2023-08-10","cited_by_count":8,"area":null},{"id":"2508.15008","title":"Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applications","created":"2025-08-20","cited_by_count":7,"area":null},{"id":"2203.14645","title":"REx: Data-Free Residual Quantization Error Expansion","created":"2022-03-28","cited_by_count":6,"area":null},{"id":"2308.03290","title":"FLIQS: One-Shot Mixed-Precision Floating-Point and Integer Quantization Search","created":"2023-08-07","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":"2206.07741","title":"Edge Inference with Fully Differentiable Quantized Mixed Precision Neural Networks","created":"2022-06-15","cited_by_count":4,"area":null},{"id":"2210.16621","title":"Empirical Evaluation of Post-Training Quantization Methods for Language Tasks","created":"2022-10-29","cited_by_count":4,"area":null},{"id":"2305.02522","title":"BitGNN: Unleashing the Performance Potential of Binary Graph Neural Networks on GPUs","created":"2023-05-04","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":"2308.07641","title":"Ternary Singular Value Decomposition as a Better Parameterized Form in Linear Mapping","created":"2023-08-15","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":"2409.09245","title":"Robust Training of Neural Networks at Arbitrary Precision and Sparsity","created":"2024-09-14","cited_by_count":3,"area":null},{"id":"2410.05911","title":"Accelerating Error Correction Code Transformers","created":"2024-10-08","cited_by_count":3,"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":"2505.03254","title":"PROM: Prioritize Reduction of Multiplications Over Lower Bit-Widths for Efficient CNNs","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2507.03504","title":"Information-Bottleneck Driven Binary Neural Network for Change Detection","created":"2025-07-04","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":"2308.06227","title":"Comprehensive Benchmarking of Binary Neural Networks on NVM Crossbar Architectures","created":"2023-08-11","cited_by_count":1,"area":null},{"id":"2309.17361","title":"Network Memory Footprint Compression Through Jointly Learnable Codebooks and Mappings","created":"2023-09-29","cited_by_count":1,"area":null},{"id":"2401.17544","title":"Trainable Fixed-Point Quantization for Deep Learning Acceleration on FPGAs","created":"2024-01-31","cited_by_count":1,"area":null},{"id":"2405.01775","title":"Torch2Chip: An End-to-end Customizable Deep Neural Network Compression and Deployment Toolkit for Prototype Hardware Accelerator Design","created":"2024-05-02","cited_by_count":1,"area":null},{"id":"2410.09734","title":"Gradient-Free Training of Quantized Neural Networks","created":"2024-10-13","cited_by_count":1,"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":"2303.02452","title":"Understanding weight-magnitude hyperparameters in training binary networks","created":"2023-03-04","cited_by_count":0,"area":null},{"id":"2308.07662","title":"Gradient-Based Post-Training Quantization: Challenging the Status Quo","created":"2023-08-15","cited_by_count":0,"area":null},{"id":"2311.15806","title":"PIPE : Parallelized Inference Through Post-Training Quantization Ensembling of Residual Expansions","created":"2023-11-27","cited_by_count":0,"area":null},{"id":"2405.17037","title":"BDC-Occ: Binarized Deep Convolution Unit For Binarized Occupancy Network","created":"2024-05-27","cited_by_count":0,"area":null},{"id":"2410.11553","title":"Efficiera Residual Networks: Hardware-Friendly Fully Binary Weight with 2-bit Activation Model Achieves Practical ImageNet Accuracy","created":"2024-10-15","cited_by_count":0,"area":null},{"id":"2505.17791","title":"Bruno: Backpropagation Running Undersampled for Novel device Optimization","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2507.02222","title":"High-Fidelity Differential-information Driven Binary Vision Transformer","created":"2025-07-03","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":"2607.06217","title":"EeveeDark: A Binary Neural Framework for Low-Light Video Enhancement via Event-Guided Sensor-Level Fusion","created":"2026-07-07","cited_by_count":0,"area":null}],"next_cursor":null}