{"total":21,"rows":[{"id":"2510.06213","title":"Training Dynamics Impact Post-Training Quantization Robustness","created":"2025-10-07","cited_by_count":15,"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":"2603.11021","title":"Leech Lattice Vector Quantization for Efficient LLM Compression","created":"2026-03-11","cited_by_count":7,"area":null},{"id":"2602.05902","title":"CoreQ: Learning-Free Mismatch Correction and Successive Rounding for Quantization","created":"2026-02-05","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":"2604.00821","title":"Optimal Brain Decomposition for Accurate LLM Low-Rank Approximation","created":"2026-04-01","cited_by_count":4,"area":null},{"id":"2605.13768","title":"High-Rate Quantized Matrix Multiplication II","created":"2026-05-13","cited_by_count":4,"area":null},{"id":"2606.10531","title":"LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization","created":"2026-06-09","cited_by_count":3,"area":null},{"id":"2607.07964","title":"KronQ: LLM Quantization via Kronecker-Factored Hessian","created":"2026-07-08","cited_by_count":3,"area":null},{"id":"2607.27042","title":"GPTQ-2D: Cubic-Time Two-Sided Adaptive Rounding","created":"2026-07-29","cited_by_count":2,"area":null},{"id":"2608.06291","title":"FastKron: Efficient Quantization with Kronecker-Factored Hessians","created":"2026-08-06","cited_by_count":1,"area":null},{"id":"2608.13966","title":"QUASAR: Lowering the Loss Floor of Quantization-Aware Training with Loss-Aware Reconstruction","created":"2026-08-14","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":"2607.14630","title":"Cross-Layer Error Compensation and Finite-Sample Feature-Statistics Matching for Extreme Low-Bit Quantization of Large Language Models","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2608.15810","title":"Pricing the Risk of Runtime Compression: Anytime-Valid Admission and a Served-Output Law for Compressed Serving State","created":"2026-08-16","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":"2609.28270","title":"Predicting Quantization Price for Selecting PTQ Configurations Before Deployment","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.31009","title":"G$^2$PTQ: Improving LLM Post-Training Quantization with Generalized Gradient Compensation","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2610.00432","title":"XOR-Trellis: Ultra-Low-Complexity Dequantization and Curvature-Aware Hadamard-Free LLM Quantization","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.18139","title":"Revisiting Error Feedback for Model Quantization","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.18516","title":"Two For The Price Of One: Curvature-Aware Pruning Preserves Influence Functions Too","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}