{"total":67,"rows":[{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2406.01721","title":"DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs","created":"2024-06-03","cited_by_count":167,"area":null},{"id":"2410.09426","title":"FlatQuant: Flatness Matters for LLM Quantization","created":"2024-10-12","cited_by_count":131,"area":null},{"id":"2412.19442","title":"A Survey on Large Language Model Acceleration based on KV Cache Management","created":"2024-12-27","cited_by_count":131,"area":"lr"},{"id":"2501.13987","title":"OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting","created":"2025-01-23","cited_by_count":97,"area":null},{"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":"2407.04752","title":"SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spiking","created":"2024-07-05","cited_by_count":31,"area":null},{"id":"2406.00800","title":"MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization","created":"2024-06-02","cited_by_count":28,"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":"2411.09909","title":"AMXFP4: Taming Activation Outliers with Asymmetric Microscaling Floating-Point for 4-bit LLM Inference","created":"2024-11-15","cited_by_count":19,"area":null},{"id":"2509.21302","title":"Quantized Visual Geometry Grounded Transformer","created":"2025-09-25","cited_by_count":17,"area":null},{"id":"2511.04063","title":"DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization","created":"2025-11-06","cited_by_count":17,"area":null},{"id":"2412.14590","title":"MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design","created":"2024-12-19","cited_by_count":16,"area":null},{"id":"2510.16292","title":"QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models","created":"2025-10-18","cited_by_count":16,"area":"mllm"},{"id":"2502.06786","title":"Matryoshka Quantization","created":"2025-02-10","cited_by_count":14,"area":null},{"id":"2603.16859","title":"SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models","created":"2026-03-17","cited_by_count":13,"area":null},{"id":"2406.13474","title":"BoA: Attention-aware Post-training Quantization without Backpropagation","created":"2024-06-19","cited_by_count":12,"area":null},{"id":"2410.09615","title":"SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression","created":"2024-10-12","cited_by_count":12,"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":"2503.01901","title":"Identifying Sensitive Weights via Post-quantization Integral","created":"2025-02-28","cited_by_count":11,"area":null},{"id":"2505.05530","title":"Low-bit Model Quantization for Deep Neural Networks: A Survey","created":"2025-05-08","cited_by_count":11,"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":"2601.14888","title":"What Makes Low-Bit Quantization-Aware Training Work for Reasoning LLMs? A Systematic Study","created":"2026-01-21","cited_by_count":10,"area":"lr"},{"id":"2604.17789","title":"DuQuant++: Fine-grained Rotation Enhances Microscaling FP4 Quantization","created":"2026-04-20","cited_by_count":8,"area":"inference"},{"id":"2506.09932","title":"HadaNorm: Diffusion Transformer Quantization through Mean-Centered Transformations","created":"2025-06-11","cited_by_count":7,"area":"diffusion"},{"id":"2509.23681","title":"QuantSparse: Comprehensively Compressing Video Diffusion Transformer with Model Quantization and Attention Sparsification","created":"2025-09-28","cited_by_count":7,"area":"diffusion"},{"id":"2506.02006","title":"MorphServe: Efficient and Workload-Aware LLM Serving via Runtime Quantized Layer Swapping and KV Cache Resizing","created":"2025-05-24","cited_by_count":6,"area":"inference"},{"id":"2509.22944","title":"SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights","created":"2025-09-26","cited_by_count":6,"area":null},{"id":"2603.16590","title":"BATQuant: Outlier-resilient MXFP4 Quantization via Learnable Block-wise Optimization","created":"2026-03-17","cited_by_count":6,"area":null},{"id":"2605.01725","title":"Motion-Aware Caching for Efficient Autoregressive Video Generation","created":"2026-05-03","cited_by_count":6,"area":null},{"id":"2506.15689","title":"BASE-Q: Bias and Asymmetric Scaling Enhanced Rotational Quantization for Large Language Models","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2510.23926","title":"Improving the Straight-Through Estimator with Zeroth-Order Information","created":"2025-10-27","cited_by_count":5,"area":null},{"id":"2603.04800","title":"MASQuant: Modality-Aware Smoothing Quantization for Multimodal Large Language Models","created":"2026-03-05","cited_by_count":5,"area":"mllm"},{"id":"2603.25284","title":"SliderQuant: Accurate Post-Training Quantization for LLMs","created":"2026-03-26","cited_by_count":5,"area":null},{"id":"2503.19353","title":"QUAD: Quantization and Parameter-Efficient Tuning of LLM with Activation Decomposition","created":"2025-03-25","cited_by_count":4,"area":null},{"id":"2506.05413","title":"SmoothRot: Combining Channel-Wise Scaling and Rotation for Quantization-Friendly LLMs","created":"2025-06-04","cited_by_count":4,"area":null},{"id":"2506.12040","title":"BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook","created":"2025-05-24","cited_by_count":4,"area":null},{"id":"2603.01776","title":"FreeAct: Freeing Activations for LLM Quantization","created":"2026-03-02","cited_by_count":4,"area":null},{"id":"2603.15389","title":"When Does Sparsity Mitigate the Curse of Depth in LLMs","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2501.12956","title":"GANQ: GPU-Adaptive Non-Uniform Quantization for Large Language Models","created":"2025-01-22","cited_by_count":3,"area":null},{"id":"2509.23410","title":"PATCH: Learnable Tile-level Hybrid Sparsity for LLMs","created":"2025-09-27","cited_by_count":3,"area":null},{"id":"2509.25689","title":"Collaborative Compression for Large-Scale MoE Deployment on Edge","created":"2025-09-30","cited_by_count":3,"area":"moe"},{"id":"2601.19675","title":"LoPRo: Enhancing Low-Rank Quantization via Permuted Block-Wise Rotation","created":"2026-01-27","cited_by_count":3,"area":null},{"id":"2602.17681","title":"LATMiX: Learnable Affine Transformations for Microscaling Quantization of LLMs","created":"2026-02-04","cited_by_count":2,"area":null},{"id":"2607.18745","title":"Contraction-Gauge Preconditioning for Quantized Matrix Multiplication","created":"2026-07-21","cited_by_count":2,"area":null},{"id":"2510.26771","title":"STaMP: Sequence Transformation and Mixed Precision for Low-Precision Activation Quantization","created":"2025-10-30","cited_by_count":1,"area":null},{"id":"2511.17809","title":"Adaptive Layer-Wise Transformations for Post-Training Quantization of Large Language Models","created":"2025-11-21","cited_by_count":1,"area":null},{"id":"2511.19705","title":"CafeQ: Calibration-free Quantization via Learned Transformations and Adaptive Rounding","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2603.01599","title":"Boosting Entropy with Bell Box Quantization","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2605.09281","title":"TileQ: Efficient Low-Rank Quantization of Mixture-of-Experts with 2D Tiling","created":"2026-05-10","cited_by_count":1,"area":"moe"},{"id":"2605.19929","title":"Breaking Modality Heterogeneity in Low-Bit Quantization for Large Vision-Language Models","created":"2026-05-19","cited_by_count":1,"area":"mllm"},{"id":"2606.07116","title":"OffQ: Taming Structured Outliers in LLM Quantization by Offsetting","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2607.23193","title":"OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models","created":"2026-07-25","cited_by_count":1,"area":"inference"},{"id":"2609.05641","title":"A Nuclear-Norm Lower Bound for Dithered Scalar Quantization of Matrix Products","created":"2026-09-04","cited_by_count":1,"area":null},{"id":"2407.15508","title":"Compensate Quantization Errors+: Quantized Models Are Inquisitive Learners","created":"2024-07-22","cited_by_count":0,"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":"2604.16475","title":"Spike-driven Large Language Model","created":"2026-04-11","cited_by_count":0,"area":null},{"id":"2605.09357","title":"Split CNN Inference on Networked Microcontrollers","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.17278","title":"A2RBench: An Automatic Paradigm for Formally Verifiable Abstract Reasoning Benchmark Generation","created":"2026-05-17","cited_by_count":0,"area":"lr"},{"id":"2607.08643","title":"BiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compression","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2608.07855","title":"CommitKV: Lifecycle-Aware KV Cache Compression via Commit Transitions for Multi-Turn Agents","created":"2026-08-08","cited_by_count":0,"area":"inference"},{"id":"2608.24070","title":"Compression Trinity: Exploring Sparsity, Quantization, and Low-Rank Approximations for LLM Compression","created":"2026-08-25","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":"2609.32659","title":"Quantization-Aware Pre-Training with Constrained Empirical Weight Distribution","created":"2026-09-26","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":"2610.16261","title":"Hardware-Friendly Token-Group Activation Quantization for Low-Bit Mamba Super-Resolution","created":"2026-10-12","cited_by_count":0,"area":"ssm"}],"next_cursor":null}