{"total":79,"rows":[{"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":"2209.13325","title":"Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models","created":"2022-09-27","cited_by_count":181,"area":null},{"id":"2109.12948","title":"Understanding and Overcoming the Challenges of Efficient Transformer Quantization","created":"2021-09-27","cited_by_count":141,"area":null},{"id":"2304.13013","title":"Stable and low-precision training for large-scale vision-language models","created":"2023-04-25","cited_by_count":75,"area":"mllm"},{"id":"2103.01049","title":"Diversifying Sample Generation for Accurate Data-Free Quantization","created":"2021-03-01","cited_by_count":63,"area":null},{"id":"2306.11987","title":"Training Transformers with 4-bit Integers","created":"2023-06-21","cited_by_count":60,"area":null},{"id":"2205.13016","title":"BiT: Robustly Binarized Multi-distilled Transformer","created":"2022-05-25","cited_by_count":52,"area":null},{"id":"2103.15263","title":"Zero-shot Adversarial Quantization","created":"2021-03-29","cited_by_count":44,"area":null},{"id":"2407.08296","title":"Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients","created":"2024-07-11","cited_by_count":38,"area":null},{"id":"2104.14235","title":"Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety","created":"2021-04-29","cited_by_count":35,"area":null},{"id":"2410.19313","title":"COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training","created":"2024-10-25","cited_by_count":33,"area":null},{"id":"2403.12422","title":"Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization","created":"2024-03-19","cited_by_count":31,"area":null},{"id":"2409.16694","title":"A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms","created":"2024-09-25","cited_by_count":31,"area":null},{"id":"2102.04782","title":"Distribution Adaptive INT8 Quantization for Training CNNs","created":"2021-02-09","cited_by_count":28,"area":null},{"id":"2202.05239","title":"F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization","created":"2022-02-10","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":"2502.12913","title":"GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning","created":"2025-02-18","cited_by_count":21,"area":null},{"id":"2502.20853","title":"Oscillation-Reduced MXFP4 Training for Vision Transformers","created":"2025-02-28","cited_by_count":21,"area":null},{"id":"2101.09868","title":"CPT: Efficient Deep Neural Network Training via Cyclic Precision","created":"2021-01-25","cited_by_count":19,"area":null},{"id":"2303.07129","title":"AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environments","created":"2023-03-13","cited_by_count":19,"area":null},{"id":"2405.12725","title":"Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks","created":"2024-05-21","cited_by_count":18,"area":null},{"id":"2302.04453","title":"Data Quality-aware Mixed-precision Quantization via Hybrid Reinforcement Learning","created":"2023-02-09","cited_by_count":17,"area":null},{"id":"2303.11906","title":"Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective","created":"2023-03-21","cited_by_count":17,"area":null},{"id":"2503.08040","title":"Accurate INT8 Training Through Dynamic Block-Level Fallback","created":"2025-03-11","cited_by_count":14,"area":null},{"id":"2302.02390","title":"Quantized Distributed Training of Large Models with Convergence Guarantees","created":"2023-02-05","cited_by_count":13,"area":null},{"id":"2207.08822","title":"Is Integer Arithmetic Enough for Deep Learning Training?","created":"2022-07-18","cited_by_count":12,"area":null},{"id":"2202.11453","title":"Bitwidth Heterogeneous Federated Learning with Progressive Weight Dequantization","created":"2022-02-23","cited_by_count":11,"area":null},{"id":"2505.01043","title":"Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities","created":"2025-05-02","cited_by_count":11,"area":null},{"id":"2306.01381","title":"Adaptive Message Quantization and Parallelization for Distributed Full-graph GNN Training","created":"2023-06-02","cited_by_count":10,"area":null},{"id":"2112.15131","title":"Resource-Efficient Deep Learning: A Survey on Model-, Arithmetic-, and Implementation-Level Techniques","created":"2021-12-30","cited_by_count":9,"area":null},{"id":"2105.04246","title":"In-Hindsight Quantization Range Estimation for Quantized Training","created":"2021-05-10","cited_by_count":7,"area":null},{"id":"2106.13914","title":"LNS-Madam: Low-Precision Training in Logarithmic Number System using Multiplicative Weight Update","created":"2021-06-26","cited_by_count":7,"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":"2210.12924","title":"OLLA: Optimizing the Lifetime and Location of Arrays to Reduce the Memory Usage of Neural Networks","created":"2022-10-24","cited_by_count":6,"area":null},{"id":"2212.03246","title":"MobileTL: On-device Transfer Learning with Inverted Residual Blocks","created":"2022-12-05","cited_by_count":6,"area":null},{"id":"2411.05873","title":"Poor Man's Training on MCUs: A Memory-Efficient Quantized Back-Propagation-Free Approach","created":"2024-11-07","cited_by_count":5,"area":null},{"id":"2302.03390","title":"Learning Discretized Neural Networks under Ricci Flow","created":"2023-02-07","cited_by_count":4,"area":null},{"id":"2302.07612","title":"Towards Optimal Compression: Joint Pruning and Quantization","created":"2023-02-15","cited_by_count":4,"area":null},{"id":"2308.00890","title":"Tango: rethinking quantization for graph neural network training on GPUs","created":"2023-08-02","cited_by_count":4,"area":null},{"id":"2312.13380","title":"Fed-QSSL: A Framework for Personalized Federated Learning under Bitwidth and Data Heterogeneity","created":"2023-12-20","cited_by_count":4,"area":null},{"id":"2209.09815","title":"Towards Fine-tuning Pre-trained Language Models with Integer Forward and Backward Propagation","created":"2022-09-20","cited_by_count":3,"area":null},{"id":"2302.06405","title":"An Optical XNOR-Bitcount Based Accelerator for Efficient Inference of Binary Neural Networks","created":"2023-02-03","cited_by_count":3,"area":null},{"id":"2405.05808","title":"Fast and Controllable Post-training Sparsity: Learning Optimal Sparsity Allocation with Global Constraint in Minutes","created":"2024-05-09","cited_by_count":3,"area":null},{"id":"2408.14267","title":"1-Bit FQT: Pushing the Limit of Fully Quantized Training to 1-bit","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2507.07149","title":"DAF: An Efficient End-to-End Dynamic Activation Framework for on-Device DNN Training","created":"2025-07-09","cited_by_count":3,"area":null},{"id":"2509.22536","title":"A Comprehensive FP8 Training Recipe for Reasoning-Enhanced Language Models","created":"2025-09-26","cited_by_count":3,"area":"lr"},{"id":"2510.09647","title":"Rounding-Guided Backdoor Injection in Deep Learning Model Quantization","created":"2025-10-05","cited_by_count":3,"area":null},{"id":"2201.07634","title":"FAT: An In-Memory Accelerator with Fast Addition for Ternary Weight Neural Networks","created":"2022-01-19","cited_by_count":2,"area":null},{"id":"2203.01156","title":"Engineering the Neural Automatic Passenger Counter","created":"2022-03-02","cited_by_count":2,"area":null},{"id":"2211.08544","title":"Exploiting the Partly Scratch-off Lottery Ticket for Quantization-Aware Training","created":"2022-11-12","cited_by_count":2,"area":null},{"id":"2312.09211","title":"Mitigating Outlier Activations in Low-Precision Fine-Tuning of Language Models","created":"2023-12-14","cited_by_count":2,"area":null},{"id":"2401.16694","title":"EdgeOL: Efficient in-situ Online Learning on Edge Devices","created":"2024-01-30","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":"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":"2506.22771","title":"FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precision","created":"2025-06-28","cited_by_count":2,"area":null},{"id":"2107.01559","title":"Smoothed Differential Privacy","created":"2021-07-04","cited_by_count":1,"area":null},{"id":"2112.14834","title":"Training Quantized Deep Neural Networks via Cooperative Coevolution","created":"2021-12-23","cited_by_count":1,"area":null},{"id":"2209.12982","title":"Going Further With Winograd Convolutions: Tap-Wise Quantization for Efficient Inference on 4x4 Tile","created":"2022-09-26","cited_by_count":1,"area":null},{"id":"2302.14458","title":"Ultra-low Precision Multiplication-free Training for Deep Neural Networks","created":"2023-02-28","cited_by_count":1,"area":null},{"id":"2303.02347","title":"MetaGrad: Adaptive Gradient Quantization with Hypernetworks","created":"2023-03-04","cited_by_count":1,"area":null},{"id":"2403.07339","title":"IM-Unpack: Training and Inference with Arbitrarily Low Precision Integers","created":"2024-03-12","cited_by_count":1,"area":null},{"id":"2405.01920","title":"Lightweight Change Detection in Heterogeneous Remote Sensing Images with Online All-Integer Pruning Training","created":"2024-05-03","cited_by_count":1,"area":null},{"id":"2405.13358","title":"AdpQ: A Zero-shot Calibration Free Adaptive Post Training Quantization Method for LLMs","created":"2024-05-22","cited_by_count":1,"area":null},{"id":"2407.12637","title":"Toward INT4 Fixed-Point Training via Exploring Quantization Error for Gradients","created":"2024-07-17","cited_by_count":1,"area":null},{"id":"2506.11469","title":"Structure-Aware Automatic Channel Pruning by Searching with Graph Embedding","created":"2025-06-13","cited_by_count":1,"area":null},{"id":"2510.24061","title":"FALQON: Accelerating LoRA Fine-tuning with Low-Bit Floating-Point Arithmetic","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2104.01681","title":"Faster Convolution Inference Through Using Pre-Calculated Lookup Tables","created":"2021-04-04","cited_by_count":0,"area":null},{"id":"2105.11166","title":"AirNet: Neural Network Transmission over the Air","created":"2021-05-24","cited_by_count":0,"area":null},{"id":"2205.04665","title":"A 14uJ/Decision Keyword Spotting Accelerator with In-SRAM-Computing and On Chip Learning for Customization","created":"2022-05-10","cited_by_count":0,"area":null},{"id":"2305.14405","title":"NeuralMatrix: Compute the Entire Neural Networks with Linear Matrix Operations for Efficient Inference","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2307.14381","title":"EdgeConvEns: Convolutional Ensemble Learning for Edge Intelligence","created":"2023-07-25","cited_by_count":0,"area":null},{"id":"2308.15003","title":"Generative Model for Models: Rapid DNN Customization for Diverse Tasks and Resource Constraints","created":"2023-08-29","cited_by_count":0,"area":null},{"id":"2310.19295","title":"ROAM: memory-efficient large DNN training via optimized operator ordering and memory layout","created":"2023-10-30","cited_by_count":0,"area":null},{"id":"2412.19002","title":"Tempus Core: Area-Power Efficient Temporal-Unary Convolution Core for Low-Precision Edge DLAs","created":"2024-12-25","cited_by_count":0,"area":null},{"id":"2606.30516","title":"HASTE: A Framework for Training-Free, Dynamic, and Steerable Compression of Pre-Trained Convolutional Neural Networks","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2608.11116","title":"You Only Charge Once 2.0 : A End-to-End Analog Computing-in-Memory Architecture with Reconfigurable Switched Capacitors","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.29667","title":"A Target-Centric Survey of Quantization-Aware Training","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.32195","title":"High-Probability Guarantees for SGD under $\\beta$-Heavy-Tailed Gradient Noise","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.16298","title":"Memory-Efficient Integer-Only Training of Deep Neural Networks","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}