{"total":25,"rows":[{"id":"2601.07475","title":"ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs","created":"2026-01-12","cited_by_count":15,"area":null},{"id":"2503.01483","title":"KurTail : Kurtosis-based LLM Quantization","created":"2025-03-03","cited_by_count":12,"area":null},{"id":"2508.02343","title":"MicroMix: Efficient Mixed-Precision Quantization with Microscaling Formats for Large Language Models","created":"2025-08-04","cited_by_count":11,"area":null},{"id":"2511.23225","title":"TWEO: Transformers Without Extreme Outliers Enables FP8 Training And Quantization For Dummies","created":"2025-11-28","cited_by_count":6,"area":null},{"id":"2605.16343","title":"LoopQ: Quantization for Looped Language Models","created":"2026-05-08","cited_by_count":6,"area":null},{"id":"2510.16805","title":"Mixed-Precision Quantization for Language Models: Techniques and Prospects","created":"2025-10-19","cited_by_count":5,"area":null},{"id":"2503.04704","title":"Universality of Layer-Level Entropy-Weighted Quantization Beyond Model Architecture and Size","created":"2025-03-06","cited_by_count":4,"area":null},{"id":"2507.17417","title":"A Comprehensive Evaluation on Quantization Techniques for Large Language Models","created":"2025-07-23","cited_by_count":3,"area":null},{"id":"2606.04115","title":"dMX: Differentiable Mixed-Precision Assignment for Low-Precision Floating-Point Formats","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2606.15652","title":"MosaicQuant: Inlier-Outlier Disaggregation for Unified 4-Bit LLM Quantization","created":"2026-06-14","cited_by_count":3,"area":null},{"id":"2604.00529","title":"MF-QAT: Multi-Format Quantization-Aware Training for Elastic Inference","created":"2026-04-01","cited_by_count":1,"area":null},{"id":"2604.09406","title":"OASIS: Online Activation Subspace Learning for Memory-Efficient Training","created":"2026-04-10","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":"2606.12876","title":"Multi-Bitwidth Quantization for LLMs Using Additive Codebooks","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2509.26277","title":"Cat: Post-Training Quantization Error Reduction via Cluster-based Affine Transformation","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2601.02728","title":"CRoPE: Efficient Parametrization of Rotary Positional Embedding","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2604.26378","title":"CoQuant: Joint Weight-Activation Subspace Projection for Mixed-Precision LLMs","created":"2026-04-29","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":"2606.26587","title":"SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2608.11786","title":"Language-Conditional Dequantization: Recovering What Quantization Steals from Non-English Languages","created":"2026-08-12","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":"2609.32429","title":"PrismQuant: Optimal Null-Space Rotations for Grouped Quantizers","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33601","title":"JustQuant: You Don't Need Smoothing, SVD, or Rotation for 4-Bit Activation Quantization","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.13767","title":"DualQuant: Dual-scale Calibration-free Weight-and-Activation Quantization for LLMs","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.16368","title":"LoopQuant: Accurate and Efficient Post-Training Quantization for Looped Transformers","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}