{"total":31,"rows":[{"id":"2310.10537","title":"Microscaling Data Formats for Deep Learning","created":"2023-10-16","cited_by_count":152,"area":null},{"id":"2406.00800","title":"MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization","created":"2024-06-02","cited_by_count":28,"area":null},{"id":"2505.11695","title":"Qronos: Correcting the Past by Shaping the Future... in Post-Training Quantization","created":"2025-05-16","cited_by_count":28,"area":null},{"id":"2508.04853","title":"Provable Post-Training Quantization: Theoretical Analysis of OPTQ and Qronos","created":"2025-08-06","cited_by_count":16,"area":null},{"id":"2403.07134","title":"COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization","created":"2024-03-11","cited_by_count":12,"area":null},{"id":"2209.03487","title":"A simple approach for quantizing neural networks","created":"2022-09-07","cited_by_count":8,"area":null},{"id":"2409.17092","title":"Accumulator-Aware Post-Training Quantization for Large Language Models","created":"2024-09-25","cited_by_count":6,"area":null},{"id":"2302.08571","title":"A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniques","created":"2023-02-16","cited_by_count":4,"area":null},{"id":"2405.02543","title":"Exploring Extreme Quantization in Spiking Language Models","created":"2024-05-04","cited_by_count":4,"area":null},{"id":"2405.15006","title":"A Rescaling-Invariant Lipschitz Bound Based on Path-Metrics for Modern ReLU Network Parameterizations","created":"2024-05-23","cited_by_count":4,"area":null},{"id":"2306.07030","title":"Resource Efficient Neural Networks Using Hessian Based Pruning","created":"2023-06-12","cited_by_count":3,"area":null},{"id":"2409.00592","title":"Hyper-Compression: Model Compression via Hyperfunction","created":"2024-09-01","cited_by_count":3,"area":null},{"id":"2412.18184","title":"Unified Stochastic Framework for Neural Network Quantization and Pruning","created":"2024-12-24","cited_by_count":3,"area":null},{"id":"2502.02766","title":"Theoretical Guarantees for Low-Rank Compression of Deep Neural Networks","created":"2025-02-04","cited_by_count":3,"area":null},{"id":"2506.10205","title":"AWP: Activation-Aware Weight Pruning and Quantization with Projected Gradient Descent","created":"2025-06-11","cited_by_count":3,"area":null},{"id":"2508.20293","title":"Beacon: Post-Training Quantization with Integrated Grid Selection","created":"2025-08-27","cited_by_count":3,"area":null},{"id":"2207.04231","title":"CEG4N: Counter-Example Guided Neural Network Quantization Refinement","created":"2022-07-09","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":"2502.16286","title":"Verification of Bit-Flip Attacks against Quantized Neural Networks","created":"2025-02-22","cited_by_count":2,"area":null},{"id":"2303.03106","title":"Rotation Invariant Quantization for Model Compression","created":"2023-03-03","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":"2412.11186","title":"Efficient Quantization-Aware Training on Segment Anything Model in Medical Images and Its Deployment","created":"2024-12-15","cited_by_count":1,"area":null},{"id":"2503.12852","title":"ACT360: An Efficient 360-Degree Action Detection and Summarization Framework for Mission-Critical Training and Debriefing","created":"2025-03-17","cited_by_count":1,"area":null},{"id":"2509.23990","title":"The Hidden Costs of Translation Accuracy: Distillation, Quantization, and Environmental Impact","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2512.06288","title":"Theoretical Compression Bounds for Wide Multilayer Perceptrons","created":"2025-12-06","cited_by_count":1,"area":null},{"id":"2603.19296","title":"TTQ: Activation-Aware Test-Time Quantization to Accelerate LLM Inference On The Fly","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2606.01412","title":"GPTQ-intrinsic LoRA: A Near-optimal Algorithm for Low-precision Quantization with Low-rank Adaptation","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2309.10975","title":"SPFQ: A Stochastic Algorithm and Its Error Analysis for Neural Network Quantization","created":"2023-09-20","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":"2512.14090","title":"Arithmetic-Intensity-Aware Quantization","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2607.22872","title":"Same Predictions, Different Reasons: The Effect of Quantization on Model Explanations","created":"2026-07-24","cited_by_count":0,"area":null}],"next_cursor":null}