{"total":97,"rows":[{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919,"area":null},{"id":"2102.05426","title":"BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction","created":"2021-02-10","cited_by_count":479,"area":null},{"id":"2208.11580","title":"Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning","created":"2022-08-24","cited_by_count":322,"area":null},{"id":"2211.15736","title":"Post-training Quantization on Diffusion Models","created":"2022-11-28","cited_by_count":267,"area":"diffusion"},{"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":"2203.05740","title":"QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization","created":"2022-03-11","cited_by_count":180,"area":null},{"id":"2203.11086","title":"Overcoming Oscillations in Quantization-Aware Training","created":"2022-03-21","cited_by_count":119,"area":null},{"id":"2306.02272","title":"OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models","created":"2023-06-04","cited_by_count":114,"area":null},{"id":"2102.08124","title":"Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Masks","created":"2021-02-16","cited_by_count":103,"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":"2402.03666","title":"QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning","created":"2024-02-06","cited_by_count":49,"area":"diffusion"},{"id":"2306.00317","title":"FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization","created":"2023-06-01","cited_by_count":48,"area":null},{"id":"2305.18723","title":"Towards Accurate Post-training Quantization for Diffusion Models","created":"2023-05-30","cited_by_count":47,"area":"diffusion"},{"id":"2410.08119","title":"Q-VLM: Post-training Quantization for Large Vision-Language Models","created":"2024-10-10","cited_by_count":47,"area":"mllm"},{"id":"2109.15082","title":"Towards Efficient Post-training Quantization of Pre-trained Language Models","created":"2021-09-30","cited_by_count":39,"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":"2112.10769","title":"Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats","created":"2021-12-19","cited_by_count":26,"area":null},{"id":"2404.00928","title":"Instance-Aware Group Quantization for Vision Transformers","created":"2024-04-01","cited_by_count":25,"area":null},{"id":"2203.17008","title":"It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher","created":"2022-03-31","cited_by_count":20,"area":null},{"id":"2308.10814","title":"Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformers","created":"2023-08-21","cited_by_count":18,"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":"2410.04960","title":"On Efficient Variants of Segment Anything Model: A Survey","created":"2024-10-07","cited_by_count":16,"area":null},{"id":"2201.01709","title":"The Effect of Model Compression on Fairness in Facial Expression Recognition","created":"2022-01-05","cited_by_count":13,"area":null},{"id":"2206.10844","title":"Quantization Robust Federated Learning for Efficient Inference on Heterogeneous Devices","created":"2022-06-22","cited_by_count":12,"area":null},{"id":"2309.13220","title":"Poster: Self-Supervised Quantization-Aware Knowledge Distillation","created":"2023-09-22","cited_by_count":11,"area":"distill"},{"id":"2509.03704","title":"QuantV2X: A Fully Quantized Multi-Agent System for Cooperative Perception","created":"2025-09-03","cited_by_count":11,"area":null},{"id":"2109.09113","title":"HPTQ: Hardware-Friendly Post Training Quantization","created":"2021-09-19","cited_by_count":10,"area":null},{"id":"2211.02854","title":"Rate-Distortion Optimized Post-Training Quantization for Learned Image Compression","created":"2022-11-05","cited_by_count":10,"area":null},{"id":"2308.07650","title":"EQ-Net: Elastic Quantization Neural Networks","created":"2023-08-15","cited_by_count":10,"area":null},{"id":"2410.21759","title":"IntLoRA: Integral Low-rank Adaptation of Quantized Diffusion Models","created":"2024-10-29","cited_by_count":10,"area":"diffusion"},{"id":"2102.06366","title":"Confounding Tradeoffs for Neural Network Quantization","created":"2021-02-12","cited_by_count":9,"area":null},{"id":"2109.04186","title":"Fine-grained Data Distribution Alignment for Post-Training Quantization","created":"2021-09-09","cited_by_count":9,"area":null},{"id":"2203.10991","title":"Minimum Variance Unbiased N:M Sparsity for the Neural Gradients","created":"2022-03-21","cited_by_count":9,"area":null},{"id":"2312.05272","title":"GenQ: Quantization in Low Data Regimes with Generative Synthetic Data","created":"2023-12-07","cited_by_count":8,"area":null},{"id":"2507.04636","title":"Put Teacher in Student's Shoes: Cross-Distillation for Ultra-compact Model Compression Framework","created":"2025-07-07","cited_by_count":8,"area":null},{"id":"2210.07171","title":"SQuAT: Sharpness- and Quantization-Aware Training for BERT","created":"2022-10-13","cited_by_count":7,"area":null},{"id":"2410.08661","title":"QEFT: Quantization for Efficient Fine-Tuning of LLMs","created":"2024-10-11","cited_by_count":7,"area":null},{"id":"2309.11531","title":"EPTQ: Enhanced Post-Training Quantization via Hessian-guided Network-wise Optimization","created":"2023-09-20","cited_by_count":6,"area":null},{"id":"2412.15846","title":"Improving Quantization-aware Training of Low-Precision Network via Block Replacement on Full-Precision Counterpart","created":"2024-12-20","cited_by_count":6,"area":null},{"id":"2503.15465","title":"FP4DiT: Towards Effective Floating Point Quantization for Diffusion Transformers","created":"2025-03-19","cited_by_count":6,"area":"diffusion"},{"id":"2407.14726","title":"MetaAug: Meta-Data Augmentation for Post-Training Quantization","created":"2024-07-20","cited_by_count":5,"area":null},{"id":"2412.10059","title":"Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity","created":"2024-12-13","cited_by_count":5,"area":null},{"id":"2503.06921","title":"Task Vector Quantization for Memory-Efficient Model Merging","created":"2025-03-10","cited_by_count":5,"area":null},{"id":"2505.03031","title":"Radio: Rate-Distortion Optimization for Large Language Model Compression","created":"2025-05-05","cited_by_count":5,"area":null},{"id":"2510.07018","title":"Sharpness-Aware Data Generation for Zero-shot Quantization","created":"2025-10-08","cited_by_count":5,"area":null},{"id":"2210.09188","title":"Sub-8-bit quantization for on-device speech recognition: a regularization-free approach","created":"2022-10-17","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":"2309.17341","title":"MixQuant: Mixed Precision Quantization with a Bit-width Optimization Search","created":"2023-09-29","cited_by_count":4,"area":null},{"id":"2404.12759","title":"decoupleQ: Towards 2-bit Post-Training Uniform Quantization via decoupling Parameters into Integer and Floating Points","created":"2024-04-19","cited_by_count":4,"area":null},{"id":"2409.17020","title":"PTQ4RIS: Post-Training Quantization for Referring Image Segmentation","created":"2024-09-25","cited_by_count":4,"area":null},{"id":"2410.12119","title":"Scaling Laws for Post Training Quantized Large Language Models","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2412.06865","title":"FP=xINT:Representing Neural Networks via Low-Bit Series Basis Functions","created":"2024-12-09","cited_by_count":4,"area":null},{"id":"2103.04812","title":"Reliability-Aware Quantization for Anti-Aging NPUs","created":"2021-03-08","cited_by_count":3,"area":null},{"id":"2105.01353","title":"One Model for All Quantization: A Quantized Network Supporting Hot-Swap Bit-Width Adjustment","created":"2021-05-04","cited_by_count":3,"area":null},{"id":"2205.00179","title":"Towards Feature Distribution Alignment and Diversity Enhancement for Data-Free Quantization","created":"2022-04-30","cited_by_count":3,"area":null},{"id":"2205.15437","title":"AMED: Automatic Mixed-Precision Quantization for Edge Devices","created":"2022-05-30","cited_by_count":3,"area":null},{"id":"2208.00338","title":"Symmetry Regularization and Saturating Nonlinearity for Robust Quantization","created":"2022-07-31","cited_by_count":3,"area":null},{"id":"2302.01382","title":"Mixed Precision Post Training Quantization of Neural Networks with Sensitivity Guided Search","created":"2023-02-02","cited_by_count":3,"area":null},{"id":"2306.04879","title":"Augmenting Hessians with Inter-Layer Dependencies for Mixed-Precision Post-Training Quantization","created":"2023-06-08","cited_by_count":3,"area":null},{"id":"2310.07467","title":"AI/ML-based Load Prediction in IEEE 802.11 Enterprise Networks","created":"2023-10-11","cited_by_count":3,"area":null},{"id":"2301.07266","title":"ACQ: Improving Generative Data-free Quantization Via Attention Correction","created":"2023-01-18","cited_by_count":2,"area":null},{"id":"2304.09785","title":"Improving Post-Training Quantization on Object Detection with Task Loss-Guided Lp Metric","created":"2023-04-19","cited_by_count":2,"area":null},{"id":"2307.11904","title":"Model Compression Methods for YOLOv5: A Review","created":"2023-07-21","cited_by_count":2,"area":null},{"id":"2310.13315","title":"Zero-Shot Sharpness-Aware Quantization for Pre-trained Language Models","created":"2023-10-20","cited_by_count":2,"area":null},{"id":"2402.06606","title":"RQP-SGD: Differential Private Machine Learning through Noisy SGD and Randomized Quantization","created":"2024-02-09","cited_by_count":2,"area":null},{"id":"2404.08131","title":"Frame Quantization of Neural Networks","created":"2024-04-11","cited_by_count":2,"area":null},{"id":"2404.19668","title":"SQUAT: Stateful Quantization-Aware Training in Recurrent Spiking Neural Networks","created":"2024-04-15","cited_by_count":2,"area":null},{"id":"2409.02026","title":"Foundations of Large Language Model Compression -- Part 1: Weight Quantization","created":"2024-09-03","cited_by_count":2,"area":null},{"id":"2410.22110","title":"Data Generation for Hardware-Friendly Post-Training Quantization","created":"2024-10-29","cited_by_count":2,"area":null},{"id":"2604.03420","title":"Zero-Shot Quantization via Weight-Space Arithmetic","created":"2026-04-03","cited_by_count":2,"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":"2207.03088","title":"Attention Round for Post-Training Quantization","created":"2022-07-07","cited_by_count":1,"area":null},{"id":"2211.09643","title":"CPT-V: A Contrastive Approach to Post-Training Quantization of Vision Transformers","created":"2022-11-17","cited_by_count":1,"area":null},{"id":"2403.10569","title":"Achieving Pareto Optimality using Efficient Parameter Reduction for DNNs in Resource-Constrained Edge Environment","created":"2024-03-14","cited_by_count":1,"area":null},{"id":"2410.11203","title":"Error Diffusion: Post Training Quantization with Block-Scaled Number Formats for Neural Networks","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2505.14638","title":"Dual Precision Quantization for Efficient and Accurate Deep Neural Networks Inference","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2507.09616","title":"MLoRQ: Bridging Low-Rank and Quantization for Transformer Compression","created":"2025-07-13","cited_by_count":1,"area":null},{"id":"2603.16105","title":"Frequency Matters: Fast Model-Agnostic Data Curation for Pruning and Quantization","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2606.09012","title":"Understanding Quantization-Aware Training: Gradients at Quantized Weights Bias to the Low-Loss Basin","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2606.16131","title":"Shift-and-Sum Quantization for Visual Autoregressive Models","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2105.01868","title":"Q-Rater: Non-Convex Optimization for Post-Training Uniform Quantization","created":"2021-05-05","cited_by_count":0,"area":null},{"id":"2108.01192","title":"MOHAQ: Multi-Objective Hardware-Aware Quantization of Recurrent Neural Networks","created":"2021-08-02","cited_by_count":0,"area":null},{"id":"2202.02783","title":"Energy awareness in low precision neural networks","created":"2022-02-06","cited_by_count":0,"area":null},{"id":"2202.05137","title":"Quantization in Layer's Input is Matter","created":"2022-02-10","cited_by_count":0,"area":null},{"id":"2207.10083","title":"Mixed-Precision Inference Quantization: Radically Towards Faster inference speed, Lower Storage requirement, and Lower Loss","created":"2022-07-20","cited_by_count":0,"area":null},{"id":"2212.05603","title":"Error-aware Quantization through Noise Tempering","created":"2022-12-11","cited_by_count":0,"area":null},{"id":"2310.03049","title":"QuATON: Quantization Aware Training of Optical Neurons","created":"2023-10-04","cited_by_count":0,"area":null},{"id":"2403.11106","title":"Self-Supervised Quantization-Aware Knowledge Distillation","created":"2024-03-17","cited_by_count":0,"area":"distill"},{"id":"2410.12187","title":"DAQ: Density-Aware Post-Training Weight-Only Quantization For LLMs","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2501.04213","title":"UPAQ: A Framework for Real-Time and Energy-Efficient 3D Object Detection in Autonomous Vehicles","created":"2025-01-08","cited_by_count":0,"area":null},{"id":"2509.26277","title":"Cat: Post-Training Quantization Error Reduction via Cluster-based Affine Transformation","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2511.03201","title":"A Quantized VAE-MLP Botnet Detection Model: A Systematic Evaluation of Quantization-Aware Training and Post-Training Quantization Strategies","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2602.01289","title":"Gradient-Aligned Calibration for Post-Training Quantization of Diffusion Models","created":"2026-02-01","cited_by_count":0,"area":"diffusion"},{"id":"2606.25087","title":"Neural Network Quantization by Learning Low-Loss Subspaces","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2609.16391","title":"Where Post-Training Quantization Breaks Text Embedders: A Measured Map Across Four Embedder Families","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2610.15092","title":"VLCQ: Post-training quantization for deep neural networks using variable length coding","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.18575","title":"Detecting Unreliable Classifications from Quantized Models","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}