{"total":26,"rows":[{"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":"2601.22347","title":"Pushing the Limits of Block Rotations in Post-Training Quantization","created":"2026-01-29","cited_by_count":11,"area":null},{"id":"2508.01077","title":"The Lattice Geometry of Neural Network Quantization -- A Short Equivalence Proof of GPTQ and Babai's Algorithm","created":"2025-08-01","cited_by_count":9,"area":null},{"id":"2603.04956","title":"WaterSIC: Information-Theoretically (Near) Optimal Linear Layer Quantization","created":"2026-03-05","cited_by_count":7,"area":null},{"id":"2512.01546","title":"LPCD: Unified Framework from Layer-Wise to Submodule Quantization","created":"2025-12-01","cited_by_count":6,"area":null},{"id":"2605.29843","title":"HARP: Hadamard-Preconditioned Adaptive Rotation Processor for Extreme LLM Quantization","created":"2026-05-28","cited_by_count":5,"area":null},{"id":"2605.13768","title":"High-Rate Quantized Matrix Multiplication II","created":"2026-05-13","cited_by_count":4,"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":"2602.04163","title":"BPDQ: Bit-Plane Decomposition Quantization on a Variable Grid for Large Language Models","created":"2026-02-04","cited_by_count":2,"area":null},{"id":"2608.08506","title":"Understanding Calibration and Truncation Error Propagation in Training-Free Low-Rank Compression for LLMs","created":"2026-08-09","cited_by_count":2,"area":null},{"id":"2608.12026","title":"SoftWater: Class-Aware Rate Allocation for Softmax Quantization","created":"2026-08-12","cited_by_count":2,"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":"2606.07116","title":"OffQ: Taming Structured Outliers in LLM Quantization by Offsetting","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2607.08779","title":"Signed Symmetric Quantization for Few-Bit Integers","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2607.23390","title":"When Can Depth Replace Precision? A Resource Theory of Quantized Neural Computation","created":"2026-07-25","cited_by_count":1,"area":null},{"id":"2609.11716","title":"Why Does Post-Training Quantization Work?","created":"2026-09-10","cited_by_count":1,"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":"2608.05240","title":"One Qubit Can Beat One Bit: Quantum Advantage for Post-Training Quantization","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.15567","title":"SchurQuant: Groupwise Discrete Optimization for Layer-Wise LLM Quantization","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.24173","title":"SandwichQuant: Which Parameters Matter Before and After Quantization?","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.25188","title":"Transforms for LLM Quantization: The Great Inversion and Format Co-Design","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.14706","title":"WaterKron and FlipFlop Hessian: Information-Theoretically Grounded Quantization with Kronecker-factored Hessians","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.31560","title":"Generalization behavior of OPTQ and the role of regularization","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.38599","title":"JARQ: Joint Alternating Refinement for Quantization","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.16020","title":"When Does Compensating Inherited Quantization Error Help? Mean-Square Guarantees for Layer-Wise Quantization and Their Limits","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}