{"total":22,"rows":[{"id":"2307.13304","title":"QuIP: 2-Bit Quantization of Large Language Models With Guarantees","created":"2023-07-25","cited_by_count":414,"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":"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":"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":"2111.10854","title":"XnODR and XnIDR: Two Accurate and Fast Fully Connected Layers For Convolutional Neural Networks","created":"2021-11-21","cited_by_count":5,"area":null},{"id":"2112.09181","title":"Approximation of functions with one-bit neural networks","created":"2021-12-16","cited_by_count":5,"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":"2209.03450","title":"Seeking Interpretability and Explainability in Binary Activated Neural Networks","created":"2022-09-07","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":"2501.06417","title":"DiscQuant: A Quantization Method for Neural Networks Inspired by Discrepancy Theory","created":"2025-01-11","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":"2606.10890","title":"Optimal Post-Training Quantization Scales and Where to Find Them","created":"2026-06-09","cited_by_count":3,"area":null},{"id":"2404.08131","title":"Frame Quantization of Neural Networks","created":"2024-04-11","cited_by_count":2,"area":null},{"id":"2512.06288","title":"Theoretical Compression Bounds for Wide Multilayer Perceptrons","created":"2025-12-06","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":"2209.01147","title":"Algorithms for Discrepancy, Matchings, and Approximations: Fast, Simple, and Practical","created":"2022-09-02","cited_by_count":0,"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":"2507.09687","title":"Post-Training Quantization of Generative and Discriminative LSTM Text Classifiers: A Study of Calibration, Class Balance, and Robustness","created":"2025-07-13","cited_by_count":0,"area":null},{"id":"2601.18782","title":"Low-Bit Quantization of Bandlimited Graph Signals via Iterative Methods","created":"2026-01-26","cited_by_count":0,"area":null}],"next_cursor":null}