{"total":131,"rows":[{"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":"2504.04823","title":"Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models","created":"2025-04-07","cited_by_count":73,"area":"lr"},{"id":"2412.19509","title":"MBQ: Modality-Balanced Quantization for Large Vision-Language Models","created":"2024-12-27","cited_by_count":45,"area":"mllm"},{"id":"2602.20309","title":"QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models","created":"2026-02-23","cited_by_count":30,"area":"vla"},{"id":"2601.20088","title":"Quantization-Aware Distillation for NVFP4 Inference Accuracy Recovery","created":"2026-01-27","cited_by_count":22,"area":"mllm"},{"id":"2511.04214","title":"Block Rotation is All You Need for MXFP4 Quantization","created":"2025-11-06","cited_by_count":20,"area":null},{"id":"2511.10645","title":"ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference","created":"2025-11-13","cited_by_count":17,"area":"lr"},{"id":"2506.04985","title":"FPTQuant: Function-Preserving Transforms for LLM Quantization","created":"2025-06-05","cited_by_count":16,"area":null},{"id":"2512.00956","title":"WUSH: Near-Optimal Adaptive Transforms for LLM Quantization","created":"2025-11-30","cited_by_count":15,"area":null},{"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":"2508.04016","title":"S$^2$Q-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token Distillation","created":"2025-08-06","cited_by_count":13,"area":"diffusion"},{"id":"2601.22347","title":"Pushing the Limits of Block Rotations in Post-Training Quantization","created":"2026-01-29","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":"2606.00206","title":"Quantized Reasoning Models Think They Need to Think Longer, but They Do Not","created":"2026-05-29","cited_by_count":10,"area":"lr"},{"id":"2510.10618","title":"Preserving LLM Capabilities through Calibration Data Curation: From Analysis to Optimization","created":"2025-10-12","cited_by_count":9,"area":null},{"id":"2506.09104","title":"Unifying Block-wise PTQ and Distillation-based QAT for Progressive Quantization toward 2-bit Instruction-Tuned LLMs","created":"2025-06-10","cited_by_count":8,"area":null},{"id":"2509.20214","title":"Q-Palette: Fractional-Bit Quantizers Toward Optimal Bit Allocation for Efficient LLM Deployment","created":"2025-09-24","cited_by_count":8,"area":null},{"id":"2602.11184","title":"KBVQ-MoE: KLT-guided SVD with Bias-Corrected Vector Quantization for MoE Large Language Models","created":"2026-01-30","cited_by_count":8,"area":"moe"},{"id":"2604.17789","title":"DuQuant++: Fine-grained Rotation Enhances Microscaling FP4 Quantization","created":"2026-04-20","cited_by_count":8,"area":"inference"},{"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":"2603.04956","title":"WaterSIC: Information-Theoretically (Near) Optimal Linear Layer Quantization","created":"2026-03-05","cited_by_count":7,"area":null},{"id":"2605.23078","title":"GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs","created":"2026-05-21","cited_by_count":7,"area":"moe"},{"id":"2509.11177","title":"Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs","created":"2025-09-14","cited_by_count":6,"area":null},{"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":"2604.18556","title":"GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling","created":"2026-04-20","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":"2606.26650","title":"CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs","created":"2026-06-25","cited_by_count":6,"area":null},{"id":"2607.02461","title":"OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers","created":"2026-07-02","cited_by_count":6,"area":"diffusion"},{"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":"2507.18212","title":"Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation","created":"2025-07-24","cited_by_count":5,"area":null},{"id":"2601.22101","title":"ECO: Quantized Training without Full-Precision Master Weights","created":"2026-01-29","cited_by_count":5,"area":"moe"},{"id":"2602.09883","title":"AdaTSQ: Pushing the Pareto Frontier of Diffusion Transformers via Temporal-Sensitivity Quantization","created":"2026-02-10","cited_by_count":5,"area":"diffusion"},{"id":"2603.04359","title":"Dissecting Quantization Error: A Concentration-Alignment Perspective","created":"2026-03-04","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":"2505.24680","title":"A Simple Linear Patch Revives Layer-Pruned Large Language Models","created":"2025-05-30","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":"2603.28765","title":"Adaptive Block-Scaled Data Types","created":"2026-03-30","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":"2511.07842","title":"Safety-Preserving PTQ via Contrastive Alignment Loss","created":"2025-11-11","cited_by_count":3,"area":"safety"},{"id":"2602.02110","title":"An Empirical Study of World Model Quantization","created":"2026-02-02","cited_by_count":3,"area":"wm"},{"id":"2605.19561","title":"TORQ: Two-Level Orthogonal Rotation for MXFP4 Quantization","created":"2026-05-19","cited_by_count":3,"area":null},{"id":"2606.01556","title":"TwinQuant: Learnable Subspace Decomposition for 4-Bit LLM Quantization","created":"2026-06-01","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":"2607.07964","title":"KronQ: LLM Quantization via Kronecker-Factored Hessian","created":"2026-07-08","cited_by_count":3,"area":null},{"id":"2506.01967","title":"Turning LLM Activations Quantization-Friendly","created":"2025-05-11","cited_by_count":2,"area":null},{"id":"2507.23035","title":"OASIS: Outlier-Aware LUT-Based GEMM with Dual-Side Quantization for LLM Inference Acceleration","created":"2025-07-30","cited_by_count":2,"area":"inference"},{"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":"2602.17681","title":"LATMiX: Learnable Affine Transformations for Microscaling Quantization of LLMs","created":"2026-02-04","cited_by_count":2,"area":null},{"id":"2604.11080","title":"ReSpinQuant: Efficient Layer-Wise LLM Quantization via Subspace Residual Rotation Approximation","created":"2026-04-13","cited_by_count":2,"area":null},{"id":"2604.24088","title":"TACO: Efficient Communication Compression of Intermediate Tensors for Scalable Tensor-Parallel LLM Training","created":"2026-04-27","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":"2605.17887","title":"Attention Sinks and Outliers in Attention Residuals","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2605.28803","title":"HoloQ-VLA: Uniform W4A4 Quantization of Vision-Language-Action Models","created":"2026-05-27","cited_by_count":2,"area":"vla"},{"id":"2606.01850","title":"Does Compression Preserve Uncertainty? A Unified Benchmark for Quantized and Sparse LLMs via Conformal Prediction","created":"2026-06-01","cited_by_count":2,"area":null},{"id":"2606.04050","title":"LiftQuant: Continuous Bit-Width LLM via Dimensional Lifting and Projection","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2606.10520","title":"UniSVQ: 2-bit Unified Scalar-Vector Quantization","created":"2026-06-09","cited_by_count":2,"area":"inference"},{"id":"2607.18745","title":"Contraction-Gauge Preconditioning for Quantized Matrix Multiplication","created":"2026-07-21","cited_by_count":2,"area":null},{"id":"2608.01847","title":"FOCUS: FP4 Optimization via Coupled-Relaxation and Dual-Granularity Scaling","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2508.03760","title":"FlashCommunication V2: Bit Splitting and Spike Reserving for Any Bit Communication","created":"2025-08-04","cited_by_count":1,"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":"2511.22316","title":"Outlier Smoothing with Closed-Form Rotations for W4A4 Large Language Model Quantization","created":"2025-11-27","cited_by_count":1,"area":null},{"id":"2512.24124","title":"OptRot: Mitigating Weight Outliers via Data-Free Rotations for Post-Training Quantization","created":"2025-12-30","cited_by_count":1,"area":null},{"id":"2601.21626","title":"HeRo-Q: A General Framework for Stable Low Bit Quantization via Hessian Conditioning","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2602.17693","title":"A Case Study of Selected PTQ Baselines for Reasoning LLMs on Ascend NPU","created":"2026-02-06","cited_by_count":1,"area":"lr"},{"id":"2604.12782","title":"OSC: Hardware Efficient W4A4 Quantization via Outlier Separation in Channel Dimension","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2604.17320","title":"Towards Joint Quantization and Token Pruning of Vision-Language Models","created":"2026-04-19","cited_by_count":1,"area":"mllm"},{"id":"2604.22577","title":"QuantClaw: Precision Where It Matters for OpenClaw","created":"2026-04-24","cited_by_count":1,"area":null},{"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":"2606.02823","title":"Qift: Shift-Friendly No-Zero W2 Post-Training Quantization for Rotated W2A4/KV4 LLM Inference","created":"2026-06-01","cited_by_count":1,"area":"inference"},{"id":"2606.06547","title":"FAIR-Calib: Frontier-Aware Instability-Reweighted Calibration for Post-Training Quantization of Diffusion Large Language Models","created":"2026-06-04","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":"2606.12487","title":"DynamicPTQ: Mitigating Activation Quantization Collapse via Residual-Stream Dynamics","created":"2026-06-10","cited_by_count":1,"area":"inference"},{"id":"2610.00930","title":"Joint Branch-Space Transform Coding for Diffusion Activation Quantization with Classifier-Free Guidance","created":"2026-10-01","cited_by_count":1,"area":"diffusion"},{"id":"2511.21736","title":"R2Q: Towards Robust 2-Bit Large Language Models via Residual Refinement Quantization","created":"2025-11-21","cited_by_count":0,"area":null},{"id":"2512.04746","title":"SignRoundV2: Toward Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs","created":"2025-12-04","cited_by_count":0,"area":null},{"id":"2512.21651","title":"Rethinking Output Alignment For 1-bit Post-Training Quantization of Large Language Models","created":"2025-12-25","cited_by_count":0,"area":"lr"},{"id":"2601.21069","title":"Any Orthogonal Transform Will Do: Range Reduction Explains Rotation-Based Quantization for Super-Resolution","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2602.12609","title":"QuEPT: Quantized Elastic Precision Transformers with One-Shot Calibration for Multi-Bit Switching","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2604.02525","title":"AdaHOP: Fast and Accurate Low-Precision Training via Outlier-Pattern-Aware Rotation","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.09742","title":"Efficient Matrix Implementation for Rotary Position Embedding","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2604.18128","title":"Depth Registers Unlock W4A4 on SwiGLU: A Reader/Generator Decomposition","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.15572","title":"Measuring Maximum Activations in Open Large Language Models","created":"2026-05-15","cited_by_count":0,"area":"moe"},{"id":"2605.15828","title":"Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.18800","title":"Theory-optimal Quantization Based on Flatness","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.19218","title":"Rotation-Aligned Key Channel Pruning for Efficient Vision-Language Model Inference","created":"2026-05-19","cited_by_count":0,"area":"mllm"},{"id":"2605.26175","title":"InfoQuant: Shaping Activation Distributions for Low-Bit LLM Quantization","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.09927","title":"Trainable Smooth-Rotation Transforms with Learned Channel Scales for LLM Quantization","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2606.20437","title":"HEPTv2: End-to-End Efficient Point Transformer for Charged Particle Reconstruction","created":"2026-06-18","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":"2607.02584","title":"RotateAttention: RoPE-Aware Rotation and Range Rectification for INT4 Quantized Attention in Video Generation","created":"2026-07-01","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":"2607.14181","title":"Quantize with Confidence? An Empirical Study of Quantization for Code Generation","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2607.20538","title":"Codec-Gauge: Learning Compression-Friendly Gauges for Transformer KV Caches","created":"2026-07-10","cited_by_count":0,"area":"inference"},{"id":"2607.27694","title":"GyRot: Leveraging Hidden Synergy between Rotation and Fine-grained Group Quantization for Low-bit LLM Inference","created":"2026-07-30","cited_by_count":0,"area":"inference"}],"next_cursor":"100"}