{"total":85,"rows":[{"id":"2308.13137","title":"OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models","created":"2023-08-25","cited_by_count":424,"area":null},{"id":"2307.13304","title":"QuIP: 2-Bit Quantization of Large Language Models With Guarantees","created":"2023-07-25","cited_by_count":414,"area":null},{"id":"2306.07629","title":"SqueezeLLM: Dense-and-Sparse Quantization","created":"2023-06-13","cited_by_count":294,"area":null},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269,"area":null},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"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":"2407.11062","title":"EfficientQAT: Efficient Quantization-Aware Training for Large Language Models","created":"2024-07-10","cited_by_count":127,"area":null},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2310.00034","title":"PB-LLM: Partially Binarized Large Language Models","created":"2023-09-29","cited_by_count":83,"area":null},{"id":"2402.18158","title":"Evaluating Quantized Large Language Models","created":"2024-02-28","cited_by_count":77,"area":null},{"id":"2403.12544","title":"AffineQuant: Affine Transformation Quantization for Large Language Models","created":"2024-03-19","cited_by_count":67,"area":null},{"id":"2310.08041","title":"QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models","created":"2023-10-12","cited_by_count":64,"area":null},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2309.05516","title":"Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs","created":"2023-09-11","cited_by_count":50,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2406.06385","title":"Low-Rank Quantization-Aware Training for LLMs","created":"2024-06-10","cited_by_count":43,"area":null},{"id":"2310.09259","title":"QUIK: Towards End-to-End 4-Bit Inference on Generative Large Language Models","created":"2023-10-13","cited_by_count":39,"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":"2312.07950","title":"CBQ: Cross-Block Quantization for Large Language Models","created":"2023-12-13","cited_by_count":34,"area":null},{"id":"2312.15159","title":"Understanding the Potential of FPGA-Based Spatial Acceleration for Large Language Model Inference","created":"2023-12-23","cited_by_count":33,"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":"2409.16694","title":"A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms","created":"2024-09-25","cited_by_count":31,"area":null},{"id":"2406.12930","title":"Tender: Accelerating Large Language Models via Tensor Decomposition and Runtime Requantization","created":"2024-06-16","cited_by_count":28,"area":null},{"id":"2309.14021","title":"LORD: Low Rank Decomposition Of Monolingual Code LLMs For One-Shot Compression","created":"2023-09-25","cited_by_count":26,"area":null},{"id":"2404.03605","title":"Mitigating the Impact of Outlier Channels for Language Model Quantization with Activation Regularization","created":"2024-04-04","cited_by_count":23,"area":null},{"id":"2405.17849","title":"I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models","created":"2024-05-28","cited_by_count":23,"area":null},{"id":"2407.06794","title":"Towards Accurate Post-Training Quantization of Vision Transformers via Error Reduction","created":"2024-07-09","cited_by_count":23,"area":null},{"id":"2505.02214","title":"An Empirical Study of Qwen3 Quantization","created":"2025-05-04","cited_by_count":21,"area":null},{"id":"2506.17188","title":"Towards AI Search Paradigm","created":"2025-06-20","cited_by_count":19,"area":null},{"id":"2308.15987","title":"FPTQ: Fine-grained Post-Training Quantization for Large Language Models","created":"2023-08-30","cited_by_count":16,"area":null},{"id":"2410.21352","title":"LLMCBench: Benchmarking Large Language Model Compression for Efficient Deployment","created":"2024-10-28","cited_by_count":16,"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":"2312.08583","title":"ZeroQuant(4+2): Redefining LLMs Quantization with a New FP6-Centric Strategy for Diverse Generative Tasks","created":"2023-12-14","cited_by_count":14,"area":null},{"id":"2402.14833","title":"CliqueParcel: An Approach For Batching LLM Prompts That Jointly Optimizes Efficiency And Faithfulness","created":"2024-02-17","cited_by_count":12,"area":null},{"id":"2410.13056","title":"Channel-Wise Mixed-Precision Quantization for Large Language Models","created":"2024-10-16","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":"2402.05628","title":"RepQuant: Towards Accurate Post-Training Quantization of Large Transformer Models via Scale Reparameterization","created":"2024-02-08","cited_by_count":10,"area":null},{"id":"2503.06862","title":"FIGLUT: An Energy-Efficient Accelerator Design for FP-INT GEMM Using Look-Up Tables","created":"2025-03-10","cited_by_count":9,"area":null},{"id":"2507.11017","title":"First-Order Error Matters: Accurate Compensation for Quantized Large Language Models","created":"2025-07-15","cited_by_count":8,"area":null},{"id":"2409.01990","title":"Designing Large Foundation Models for Efficient Training and Inference: A Survey","created":"2024-09-03","cited_by_count":7,"area":null},{"id":"2309.16119","title":"ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers","created":"2023-09-28","cited_by_count":6,"area":null},{"id":"2406.16893","title":"A Survey of Transformer-based Language Models with Focus on Efficiency","created":"2024-05-15","cited_by_count":6,"area":null},{"id":"2410.12168","title":"COMET: Towards Partical W4A4KV4 LLMs Serving","created":"2024-10-16","cited_by_count":6,"area":null},{"id":"2409.20361","title":"Rotated Runtime Smooth: Training-Free Activation Smoother for accurate INT4 inference","created":"2024-09-30","cited_by_count":5,"area":null},{"id":"2412.10059","title":"Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity","created":"2024-12-13","cited_by_count":5,"area":null},{"id":"2501.16385","title":"FBQuant: FeedBack Quantization for Large Language Models","created":"2025-01-25","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":"2402.17985","title":"FlattenQuant: Breaking Through the Inference Compute-bound for Large Language Models with Per-tensor Quantization","created":"2024-02-28","cited_by_count":4,"area":null},{"id":"2406.18832","title":"OutlierTune: Efficient Channel-Wise Quantization for Large Language Models","created":"2024-06-27","cited_by_count":4,"area":null},{"id":"2503.07654","title":"MergeQuant: Accurate 4-bit Static Quantization of Large Language Models by Channel-wise Calibration","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2503.03088","title":"AHCQ-SAM: Toward Accurate and Hardware-Compatible Post-Training Segment Anything Model Quantization","created":"2025-03-05","cited_by_count":3,"area":null},{"id":"2509.00031","title":"End-to-End On-Device Quantization-Aware Training for LLMs at Inference Cost","created":"2025-08-21","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":"2309.05210","title":"Understanding the Impact of Post-Training Quantization on Large Language Models","created":"2023-09-11","cited_by_count":2,"area":null},{"id":"2310.04836","title":"Dual Grained Quantization: Efficient Fine-Grained Quantization for LLM","created":"2023-10-07","cited_by_count":2,"area":null},{"id":"2312.09211","title":"Mitigating Outlier Activations in Low-Precision Fine-Tuning of Language Models","created":"2023-12-14","cited_by_count":2,"area":null},{"id":"2410.16135","title":"Beyond 2:4: exploring V:N:M sparsity for efficient transformer inference on GPUs","created":"2024-10-21","cited_by_count":2,"area":null},{"id":"2506.11044","title":"Boost Post-Training Quantization via Null Space Optimization for Large Language Models","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2506.20251","title":"Q-resafe: Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models","created":"2025-06-25","cited_by_count":2,"area":null},{"id":"2605.04738","title":"OSAQ: Outlier Self-Absorption for Accurate Low-bit LLM Quantization","created":"2026-05-06","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":"2307.03712","title":"INT-FP-QSim: Mixed Precision and Formats For Large Language Models and Vision Transformers","created":"2023-07-07","cited_by_count":1,"area":null},{"id":"2403.09998","title":"FBPT: A Fully Binary Point Transformer","created":"2024-03-15","cited_by_count":1,"area":null},{"id":"2405.20973","title":"LCQ: Low-Rank Codebook based Quantization for Large Language Models","created":"2024-05-31","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":"2510.10136","title":"PermLLM: Learnable Channel Permutation for N:M Sparse Large Language Models","created":"2025-10-11","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":"2602.02001","title":"Preserve-Then-Quantize: Balancing Rank Budgets for Quantization Error Reconstruction in LLMs","created":"2026-02-02","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":"2406.06571","title":"SUBLLM: A Novel Efficient Architecture with Token Sequence Subsampling for LLM","created":"2024-06-03","cited_by_count":0,"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":"2510.14812","title":"SHUFFLESPARSE: Learned Shuffles for Structured Sparse Networks","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2511.22483","title":"Enhancing Trustworthiness with Mixed Precision: Benchmarks, Opportunities, and Challenges","created":"2025-11-27","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":"2606.21257","title":"An Empirical Study of openPangu Quantization on Ascend NPUs","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2606.25674","title":"BitNet Text Embeddings","created":"2026-06-24","cited_by_count":0,"area":null},{"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":"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":"2608.25188","title":"Transforms for LLM Quantization: The Great Inversion and Format Co-Design","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.25977","title":"When Personality Meets Quantization: A Layer-wise MBTI Analysis of Quantized LLMs","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.22106","title":"PRQuant: Permutation Residual Quantization for Low-Overhead Inference","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2609.23125","title":"Perplexity Cost Understates What Activation Quantisation Breaks","created":"2026-09-19","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":"2609.34259","title":"QuantaSpike: Short-Window Spike-Driven Quantization for Large Language Models","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36760","title":"QuantMLA: Function-Aligned Dual-Path Quantization for Low-Bit MLA KV Caching","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}