{"total":462,"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":"2106.08295","title":"A White Paper on Neural Network Quantization","created":"2021-06-15","cited_by_count":472,"area":null},{"id":"2305.17888","title":"LLM-QAT: Data-Free Quantization Aware Training for Large Language Models","created":"2023-05-29","cited_by_count":324,"area":null},{"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":"2110.13903","title":"NeRV: Neural Representations for Videos","created":"2021-10-26","cited_by_count":256,"area":null},{"id":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255,"area":null},{"id":"2212.09720","title":"The case for 4-bit precision: k-bit Inference Scaling Laws","created":"2022-12-19","cited_by_count":251,"area":null},{"id":"2103.03123","title":"COIN: COmpression with Implicit Neural representations","created":"2021-03-03","cited_by_count":233,"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":"2106.08962","title":"Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better","created":"2021-06-16","cited_by_count":154,"area":null},{"id":"2306.12929","title":"Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing","created":"2023-06-22","cited_by_count":151,"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":"2212.08254","title":"RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers","created":"2022-12-16","cited_by_count":137,"area":null},{"id":"2311.18159","title":"CompGS: Smaller and Faster Gaussian Splatting with Vector Quantization","created":"2023-11-30","cited_by_count":130,"area":null},{"id":"2203.11086","title":"Overcoming Oscillations in Quantization-Aware Training","created":"2022-03-21","cited_by_count":119,"area":null},{"id":"2304.02633","title":"HNeRV: A Hybrid Neural Representation for Videos","created":"2023-04-05","cited_by_count":100,"area":null},{"id":"2207.01405","title":"I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference","created":"2022-07-04","cited_by_count":95,"area":null},{"id":"2302.08890","title":"Deep Learning for Event-based Vision: A Comprehensive Survey and Benchmarks","created":"2023-02-17","cited_by_count":90,"area":null},{"id":"2208.09225","title":"FP8 Quantization: The Power of the Exponent","created":"2022-08-19","cited_by_count":88,"area":null},{"id":"2201.12904","title":"COIN++: Neural Compression Across Modalities","created":"2022-01-30","cited_by_count":82,"area":null},{"id":"2402.18158","title":"Evaluating Quantized Large Language Models","created":"2024-02-28","cited_by_count":77,"area":null},{"id":"2212.07048","title":"PD-Quant: Post-Training Quantization based on Prediction Difference Metric","created":"2022-12-14","cited_by_count":73,"area":null},{"id":"2211.16386","title":"Compressing Volumetric Radiance Fields to 1 MB","created":"2022-11-29","cited_by_count":68,"area":null},{"id":"2102.04503","title":"VS-Quant: Per-vector Scaled Quantization for Accurate Low-Precision Neural Network Inference","created":"2021-02-08","cited_by_count":64,"area":null},{"id":"2203.02250","title":"Patch Similarity Aware Data-Free Quantization for Vision Transformers","created":"2022-03-04","cited_by_count":56,"area":null},{"id":"2112.11312","title":"Implicit Neural Video Compression","created":"2021-12-21","cited_by_count":52,"area":null},{"id":"2203.10681","title":"Online Continual Learning for Embedded Devices","created":"2022-03-21","cited_by_count":49,"area":null},{"id":"2305.19268","title":"Intriguing Properties of Quantization at Scale","created":"2023-05-30","cited_by_count":49,"area":null},{"id":"2502.02631","title":"ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization","created":"2025-02-04","cited_by_count":46,"area":null},{"id":"2101.08940","title":"Hessian-Aware Pruning and Optimal Neural Implant","created":"2021-01-22","cited_by_count":45,"area":null},{"id":"2104.09987","title":"Differentiable Model Compression via Pseudo Quantization Noise","created":"2021-04-20","cited_by_count":45,"area":null},{"id":"2105.07576","title":"Rethinking \"Batch\" in BatchNorm","created":"2021-05-17","cited_by_count":45,"area":null},{"id":"2111.09136","title":"IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization","created":"2021-11-17","cited_by_count":43,"area":null},{"id":"2302.08469","title":"Hardware-aware training for large-scale and diverse deep learning inference workloads using in-memory computing-based accelerators","created":"2023-02-16","cited_by_count":43,"area":null},{"id":"2406.06385","title":"Low-Rank Quantization-Aware Training for LLMs","created":"2024-06-10","cited_by_count":43,"area":null},{"id":"2209.05687","title":"PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision Transformers","created":"2022-09-13","cited_by_count":42,"area":null},{"id":"2111.03759","title":"MQBench: Towards Reproducible and Deployable Model Quantization Benchmark","created":"2021-11-05","cited_by_count":40,"area":null},{"id":"2112.08429","title":"Torch.fx: Practical Program Capture and Transformation for Deep Learning in Python","created":"2021-12-15","cited_by_count":40,"area":null},{"id":"2203.08737","title":"Hardware Approximate Techniques for Deep Neural Network Accelerators: A Survey","created":"2022-03-16","cited_by_count":39,"area":null},{"id":"2107.01807","title":"Q-SpiNN: A Framework for Quantizing Spiking Neural Networks","created":"2021-07-05","cited_by_count":37,"area":null},{"id":"2307.07982","title":"A Survey of Techniques for Optimizing Transformer Inference","created":"2023-07-16","cited_by_count":35,"area":null},{"id":"2201.11113","title":"Post-training Quantization for Neural Networks with Provable Guarantees","created":"2022-01-26","cited_by_count":33,"area":null},{"id":"2303.17951","title":"FP8 versus INT8 for efficient deep learning inference","created":"2023-03-31","cited_by_count":31,"area":null},{"id":"2403.00025","title":"On the Challenges and Opportunities in Generative AI","created":"2024-02-28","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":"2108.13041","title":"Auto-Split: A General Framework of Collaborative Edge-Cloud AI","created":"2021-08-30","cited_by_count":30,"area":null},{"id":"2109.02220","title":"GDP: Stabilized Neural Network Pruning via Gates with Differentiable Polarization","created":"2021-09-06","cited_by_count":29,"area":null},{"id":"2401.15865","title":"LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection","created":"2024-01-29","cited_by_count":29,"area":null},{"id":"2407.12951","title":"AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer","created":"2024-07-17","cited_by_count":29,"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":"2205.14550","title":"Machine Learning for Microcontroller-Class Hardware: A Review","created":"2022-05-29","cited_by_count":28,"area":null},{"id":"2207.10345","title":"CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution","created":"2022-07-21","cited_by_count":27,"area":null},{"id":"2309.11932","title":"A Machine Learning-oriented Survey on Tiny Machine Learning","created":"2023-09-21","cited_by_count":27,"area":null},{"id":"2411.17713","title":"Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations","created":"2024-11-18","cited_by_count":26,"area":null},{"id":"2201.08442","title":"Neural Network Quantization with AI Model Efficiency Toolkit (AIMET)","created":"2022-01-20","cited_by_count":24,"area":null},{"id":"2302.05397","title":"A Practical Mixed Precision Algorithm for Post-Training Quantization","created":"2023-02-10","cited_by_count":24,"area":null},{"id":"2407.06794","title":"Towards Accurate Post-Training Quantization of Vision Transformers via Error Reduction","created":"2024-07-09","cited_by_count":23,"area":null},{"id":"2207.13417","title":"Hardly Perceptible Trojan Attack against Neural Networks with Bit Flips","created":"2022-07-27","cited_by_count":22,"area":null},{"id":"2212.01593","title":"Make RepVGG Greater Again: A Quantization-aware Approach","created":"2022-12-03","cited_by_count":22,"area":null},{"id":"2307.10554","title":"EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization","created":"2023-07-20","cited_by_count":22,"area":null},{"id":"2407.10032","title":"LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware Grid","created":"2024-07-14","cited_by_count":22,"area":null},{"id":"2203.03844","title":"Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution Networks","created":"2022-03-08","cited_by_count":21,"area":null},{"id":"2103.08870","title":"Learned Gradient Compression for Distributed Deep Learning","created":"2021-03-16","cited_by_count":20,"area":null},{"id":"2105.08952","title":"BatchQuant: Quantized-for-all Architecture Search with Robust Quantizer","created":"2021-05-19","cited_by_count":20,"area":null},{"id":"2106.02295","title":"Differentiable Dynamic Quantization with Mixed Precision and Adaptive Resolution","created":"2021-06-04","cited_by_count":20,"area":null},{"id":"2301.09858","title":"PowerQuant: Automorphism Search for Non-Uniform Quantization","created":"2023-01-24","cited_by_count":20,"area":null},{"id":"2305.10727","title":"Boost Vision Transformer with GPU-Friendly Sparsity and Quantization","created":"2023-05-18","cited_by_count":20,"area":null},{"id":"2307.01946","title":"ECG-Image-Kit: A Synthetic Image Generation Toolbox to Facilitate Deep Learning-Based Electrocardiogram Digitization","created":"2023-07-04","cited_by_count":20,"area":null},{"id":"2108.06983","title":"Distance-aware Quantization","created":"2021-08-16","cited_by_count":19,"area":null},{"id":"2110.01397","title":"RED++ : Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Merging","created":"2021-09-30","cited_by_count":19,"area":null},{"id":"2205.11141","title":"OPQ: Compressing Deep Neural Networks with One-shot Pruning-Quantization","created":"2022-05-23","cited_by_count":19,"area":null},{"id":"2311.10126","title":"I&S-ViT: An Inclusive & Stable Method for Pushing the Limit of Post-Training ViTs Quantization","created":"2023-11-16","cited_by_count":19,"area":null},{"id":"2408.03291","title":"DopQ-ViT: Towards Distribution-Friendly and Outlier-Aware Post-Training Quantization for Vision Transformers","created":"2024-08-06","cited_by_count":19,"area":null},{"id":"2504.02508","title":"APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers","created":"2025-04-03","cited_by_count":19,"area":null},{"id":"2506.11543","title":"FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation","created":"2025-06-13","cited_by_count":19,"area":null},{"id":"2104.15129","title":"Stealthy Backdoors as Compression Artifacts","created":"2021-04-30","cited_by_count":18,"area":null},{"id":"2205.12295","title":"lpSpikeCon: Enabling Low-Precision Spiking Neural Network Processing for Efficient Unsupervised Continual Learning on Autonomous Agents","created":"2022-05-24","cited_by_count":18,"area":null},{"id":"2206.10526","title":"QuantFace: Towards Lightweight Face Recognition by Synthetic Data Low-bit Quantization","created":"2022-06-21","cited_by_count":18,"area":null},{"id":"2306.14052","title":"A Survey on Graph Neural Network Acceleration: Algorithms, Systems, and Customized Hardware","created":"2023-06-24","cited_by_count":18,"area":null},{"id":"2307.09988","title":"TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edge","created":"2023-07-19","cited_by_count":18,"area":null},{"id":"2411.17691","title":"Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens","created":"2024-11-26","cited_by_count":18,"area":null},{"id":"2105.06002","title":"Lightweight compression of neural network feature tensors for collaborative intelligence","created":"2021-05-12","cited_by_count":17,"area":null},{"id":"2105.11010","title":"Post-Training Sparsity-Aware Quantization","created":"2021-05-23","cited_by_count":17,"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":"2509.21302","title":"Quantized Visual Geometry Grounded Transformer","created":"2025-09-25","cited_by_count":17,"area":null},{"id":"2101.07985","title":"Network Pruning using Adaptive Exemplar Filters","created":"2021-01-20","cited_by_count":16,"area":null},{"id":"2102.03207","title":"Real-time Denoising and Dereverberation with Tiny Recurrent U-Net","created":"2021-02-05","cited_by_count":16,"area":null},{"id":"2205.01271","title":"Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation","created":"2022-05-03","cited_by_count":16,"area":null},{"id":"2506.04985","title":"FPTQuant: Function-Preserving Transforms for LLM Quantization","created":"2025-06-05","cited_by_count":16,"area":null},{"id":"2101.08430","title":"Generative Zero-shot Network Quantization","created":"2021-01-21","cited_by_count":15,"area":null},{"id":"2204.12322","title":"RAPQ: Rescuing Accuracy for Power-of-Two Low-bit Post-training Quantization","created":"2022-04-26","cited_by_count":15,"area":null},{"id":"2406.08413","title":"Memory Is All You Need: An Overview of Compute-in-Memory Architectures for Accelerating Large Language Model Inference","created":"2024-06-12","cited_by_count":15,"area":null},{"id":"2202.00441","title":"Few-Bit Backward: Quantized Gradients of Activation Functions for Memory Footprint Reduction","created":"2022-02-01","cited_by_count":14,"area":null},{"id":"2202.07513","title":"Post-Training Quantization for Cross-Platform Learned Image Compression","created":"2022-02-15","cited_by_count":14,"area":null},{"id":"2312.08583","title":"ZeroQuant(4+2): Redefining LLMs Quantization with a New FP6-Centric Strategy for Diverse Generative Tasks","created":"2023-12-14","cited_by_count":14,"area":null},{"id":"2404.10407","title":"Comprehensive Survey of Model Compression and Speed up for Vision Transformers","created":"2024-04-16","cited_by_count":14,"area":null},{"id":"2203.10135","title":"Learning Compressed Embeddings for On-Device Inference","created":"2022-03-18","cited_by_count":13,"area":null},{"id":"2404.19489","title":"EvGNN: An Event-driven Graph Neural Network Accelerator for Edge Vision","created":"2024-04-30","cited_by_count":13,"area":null},{"id":"2501.13492","title":"Quantized Spike-driven Transformer","created":"2025-01-23","cited_by_count":13,"area":null}],"next_cursor":"100"}