{"total":30,"rows":[{"id":"2405.14917","title":"SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models","created":"2024-05-23","cited_by_count":63,"area":null},{"id":"2504.09629","title":"Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization","created":"2025-04-13","cited_by_count":41,"area":null},{"id":"2411.02530","title":"A Comprehensive Study on Quantization Techniques for Large Language Models","created":"2024-10-30","cited_by_count":36,"area":null},{"id":"2412.14363","title":"ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals","created":"2024-12-18","cited_by_count":36,"area":null},{"id":"2511.04214","title":"Block Rotation is All You Need for MXFP4 Quantization","created":"2025-11-06","cited_by_count":20,"area":null},{"id":"2502.13178","title":"Benchmarking Post-Training Quantization in LLMs: Comprehensive Taxonomy, Unified Evaluation, and Comparative Analysis","created":"2025-02-18","cited_by_count":12,"area":null},{"id":"2509.09679","title":"ButterflyQuant: Ultra-low-bit LLM Quantization through Learnable Orthogonal Butterfly Transforms","created":"2025-09-11","cited_by_count":10,"area":null},{"id":"2504.03717","title":"RaanA: A Fast, Flexible, and Data-Efficient Post-Training Quantization Algorithm","created":"2025-03-29","cited_by_count":5,"area":null},{"id":"2505.03031","title":"Radio: Rate-Distortion Optimization for Large Language Model Compression","created":"2025-05-05","cited_by_count":5,"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":"2504.13932","title":"Enhancing Ultra-Low-Bit Quantization of Large Language Models Through Saliency-Aware Partial Retraining","created":"2025-04-14","cited_by_count":3,"area":null},{"id":"2511.06516","title":"You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations","created":"2025-11-09","cited_by_count":3,"area":null},{"id":"2602.17698","title":"ScaleBITS: Scalable Bitwidth Search for Hardware-Aligned Mixed-Precision LLMs","created":"2026-02-06","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":"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":"2409.02026","title":"Foundations of Large Language Model Compression -- Part 1: Weight Quantization","created":"2024-09-03","cited_by_count":2,"area":null},{"id":"2410.10849","title":"Continuous Approximations for Improving Quantization Aware Training of LLMs","created":"2024-10-06","cited_by_count":2,"area":null},{"id":"2502.19747","title":"HaLoRA: Hardware-aware Low-Rank Adaptation for Large Language Models Based on Hybrid Compute-in-Memory Architecture","created":"2025-02-27","cited_by_count":2,"area":null},{"id":"2602.01410","title":"SNIP: An Adaptive Mixed Precision Framework for Subbyte Large Language Model Training","created":"2026-02-01","cited_by_count":2,"area":null},{"id":"2605.04062","title":"EdgeRazor: A Lightweight Framework for Large Language Models via Mixed-Precision Quantization-Aware Distillation","created":"2026-04-10","cited_by_count":2,"area":null},{"id":"2408.10631","title":"LLM-Barber: Block-Aware Rebuilder for Sparsity Mask in One-Shot for Large Language Models","created":"2024-08-20","cited_by_count":1,"area":null},{"id":"2504.19746","title":"FineQ: Software-Hardware Co-Design for Low-Bit Fine-Grained Mixed-Precision Quantization of LLMs","created":"2025-04-28","cited_by_count":1,"area":null},{"id":"2505.00259","title":"Pack-PTQ: Advancing Post-training Quantization of Neural Networks by Pack-wise Reconstruction","created":"2025-05-01","cited_by_count":1,"area":null},{"id":"2507.18073","title":"Squeeze10-LLM: Squeezing LLMs' Weights by 10 Times via a Staged Mixed-Precision Quantization Method","created":"2025-07-24","cited_by_count":1,"area":null},{"id":"2607.00908","title":"Beyond Activation Alignment:The Alignment-Diversity Tradeoff in Task-Aware LLM Quantization","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2501.12896","title":"Irrational Complex Rotations Empower Low-bit Optimizers","created":"2025-01-22","cited_by_count":0,"area":null},{"id":"2608.12953","title":"Unifying Depth and Width Pruning for LLMs via Binary Knapsack Optimization","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2609.04724","title":"FlexPosit: Tunable Fractional Precision for LLM Inference Accelerators","created":"2026-09-04","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":"2609.34866","title":"From Attention Sensitivity to Layer Role: Revisiting Mixed-Precision Quantization of Transformers","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}