{"total":40,"rows":[{"id":"2512.01546","title":"LPCD: Unified Framework from Layer-Wise to Submodule Quantization","created":"2025-12-01","cited_by_count":6,"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":"2509.06297","title":"LoaQ: Layer-wise Output Approximation Quantization","created":"2025-09-08","cited_by_count":5,"area":null},{"id":"2510.10693","title":"High-Dimensional Learning Dynamics of Quantized Models with Straight-Through Estimator","created":"2025-10-12","cited_by_count":4,"area":null},{"id":"2512.24545","title":"More Than Bits: Multi-Envelope Double Binary Factorization for Extreme Quantization","created":"2025-12-31","cited_by_count":3,"area":null},{"id":"2603.28845","title":"OneComp: One-Line Revolution for Generative AI Model Compression","created":"2026-03-30","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":"2602.02546","title":"D$^2$Quant: Accurate Low-bit Post-Training Weight Quantization for LLMs","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2606.13300","title":"Quantizing Time-Series Models As Dynamical Systems: Trajectory-Based Quantization Sensitivity Score","created":"2026-06-11","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":"2602.06694","title":"NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2602.08376","title":"OJBKQ: Objective-Joint Babai-Klein Quantization","created":"2026-02-09","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":"2604.13806","title":"Robust Ultra Low-Bit Post-Training Quantization via Stable Diagonal Curvature Estimate","created":"2026-04-15","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":"2609.11716","title":"Why Does Post-Training Quantization Work?","created":"2026-09-10","cited_by_count":1,"area":null},{"id":"2609.25916","title":"Beyond Scalar Sensitivity: Activation-Aware Mixed-Precision LLM Quantization with Cross-Layer Refinement","created":"2026-09-22","cited_by_count":1,"area":null},{"id":"2509.18172","title":"SBVR: Summation of BitVector Representation for Efficient LLM Quantization","created":"2025-09-17","cited_by_count":0,"area":null},{"id":"2601.02455","title":"Diagnostic-Driven Layer-Wise Compensation for Post-Training Quantization of Encoder-Decoder ASR Models","created":"2026-01-05","cited_by_count":0,"area":null},{"id":"2602.00377","title":"DecompressionLM: Deterministic, Diagnostic, and Zero-Shot Concept Graph Extraction from Language Models","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2605.24058","title":"Signs Beat Floats: Low-Rank Double-Binary Adaptation for On-Device Fine-Tuning","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.07819","title":"Joint Structural Pruning and Mixed-Precision Quantization for LLM Compression","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.08565","title":"EinSort: Sorting is All We Need for Tensorizing LLM","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2607.11359","title":"Efficient Tuning Before Low-Bit Post-Training Quantization for Stochastic Gradient Descent-optimized Models","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.12266","title":"Saturation Makes Quantization Error Additive: A Coverage Model with a Certificate","created":"2026-07-14","cited_by_count":0,"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":"2608.05240","title":"One Qubit Can Beat One Bit: Quantum Advantage for Post-Training Quantization","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.09595","title":"From Sweep to Seam: Interleaved Cross-Block Post-Training Quantization","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.14149","title":"QuaSAR: Quantization Compensation via Stable Activation-Aware Rank Truncation","created":"2026-08-14","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":"2609.21450","title":"Understanding LLM Quantization through Activation-Guided Compensation and Orthogonal Residuals","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.26173","title":"Component Type, Not Reconstruction Error, Predicts Attention Quantization Sensitivity","created":"2026-08-09","cited_by_count":0,"area":null},{"id":"2609.31155","title":"Teacher-Anchored Selection of Post-Training Quantized Models under Domain Shift","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.32060","title":"Depth Laws for the Precision Floor of Trained Neural Networks: Amplification, Residual Scaling, and a Quantization-Aware Training Paradox","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":"2610.09877","title":"Layerwise Error Attribution for Fast and Robust Mixed-Precision Post-Training Quantization","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.14745","title":"SAGE: Pushing 2-Bit Vector-Quantized LLMs toward Real-World Usability","created":"2026-10-10","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},{"id":"2610.18139","title":"Revisiting Error Feedback for Model Quantization","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}