{"total":114,"rows":[{"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":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2402.02244","title":"Beyond the Limits: A Survey of Techniques to Extend the Context Length in Large Language Models","created":"2024-02-03","cited_by_count":76,"area":"lr"},{"id":"2405.14852","title":"PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression","created":"2024-05-23","cited_by_count":61,"area":null},{"id":"2409.17066","title":"VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models","created":"2024-09-25","cited_by_count":57,"area":null},{"id":"2501.17116","title":"Optimizing Large Language Model Training Using FP4 Quantization","created":"2025-01-28","cited_by_count":56,"area":null},{"id":"2402.10517","title":"Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs","created":"2024-02-16","cited_by_count":54,"area":null},{"id":"2411.07191","title":"The Super Weight in Large Language Models","created":"2024-11-11","cited_by_count":52,"area":null},{"id":"2406.05223","title":"CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuning","created":"2024-06-07","cited_by_count":44,"area":null},{"id":"2406.06385","title":"Low-Rank Quantization-Aware Training for LLMs","created":"2024-06-10","cited_by_count":43,"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":"2408.01803","title":"STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs","created":"2024-08-03","cited_by_count":31,"area":null},{"id":"2410.03129","title":"ARB-LLM: Alternating Refined Binarizations for Large Language Models","created":"2024-10-04","cited_by_count":31,"area":null},{"id":"2411.05282","title":"MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization","created":"2024-11-08","cited_by_count":28,"area":null},{"id":"2407.12327","title":"Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale","created":"2024-07-17","cited_by_count":21,"area":null},{"id":"2405.20935","title":"Effective Interplay between Sparsity and Quantization: From Theory to Practice","created":"2024-05-31","cited_by_count":19,"area":null},{"id":"2410.11305","title":"QSpec: Speculative Decoding with Complementary Quantization Schemes","created":"2024-10-15","cited_by_count":18,"area":"inference"},{"id":"2511.04063","title":"DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization","created":"2025-11-06","cited_by_count":17,"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":"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":"2505.19433","title":"Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression","created":"2025-05-26","cited_by_count":16,"area":"agents"},{"id":"2506.04985","title":"FPTQuant: Function-Preserving Transforms for LLM Quantization","created":"2025-06-05","cited_by_count":16,"area":null},{"id":"2406.12311","title":"Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language Models","created":"2024-06-18","cited_by_count":14,"area":null},{"id":"2503.18599","title":"Oaken: Fast and Efficient LLM Serving with Online-Offline Hybrid KV Cache Quantization","created":"2025-03-24","cited_by_count":14,"area":"inference"},{"id":"2405.07135","title":"Post Training Quantization of Large Language Models with Microscaling Formats","created":"2024-05-12","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":"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":"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":"2412.20386","title":"PTQ4VM: Post-Training Quantization for Visual Mamba","created":"2024-12-29","cited_by_count":10,"area":"ssm"},{"id":"2505.20355","title":"GraLoRA: Granular Low-Rank Adaptation for Parameter-Efficient Fine-Tuning","created":"2025-05-26","cited_by_count":10,"area":null},{"id":"2505.19481","title":"Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs","created":"2025-05-26","cited_by_count":9,"area":"agents"},{"id":"2505.00598","title":"Fast and Low-Cost Genomic Foundation Models via Outlier Removal","created":"2025-05-01","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":"2412.20185","title":"DecDEC: A Systems Approach to Advancing Low-Bit LLM Quantization","created":"2024-12-28","cited_by_count":7,"area":null},{"id":"2508.15008","title":"Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applications","created":"2025-08-20","cited_by_count":7,"area":null},{"id":"2604.12358","title":"Why and When Visual Token Pruning Fails? A Study on Relevant Visual Information Shift in MLLMs Decoding","created":"2026-04-14","cited_by_count":7,"area":"mllm"},{"id":"2402.10076","title":"QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference","created":"2024-02-15","cited_by_count":6,"area":"inference"},{"id":"2503.15465","title":"FP4DiT: Towards Effective Floating Point Quantization for Diffusion Transformers","created":"2025-03-19","cited_by_count":6,"area":"diffusion"},{"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":"2605.06014","title":"Quantizing With Randomized Hadamard Transforms: Efficient Heuristic Now Proven","created":"2026-05-07","cited_by_count":6,"area":"inference"},{"id":"2502.09003","title":"RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models","created":"2025-02-13","cited_by_count":5,"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":"2509.18763","title":"Bi-VLM: Pushing Ultra-Low Precision Post-Training Quantization Boundaries in Vision-Language Models","created":"2025-09-23","cited_by_count":5,"area":"mllm"},{"id":"2510.16805","title":"Mixed-Precision Quantization for Language Models: Techniques and Prospects","created":"2025-10-19","cited_by_count":5,"area":null},{"id":"2409.05902","title":"OPAL: Outlier-Preserved Microscaling Quantization Accelerator for Generative Large Language Models","created":"2024-09-06","cited_by_count":4,"area":null},{"id":"2410.12119","title":"Scaling Laws for Post Training Quantized Large Language Models","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2501.13331","title":"Qrazor: Reliable and Effortless 4-bit LLM Quantization by Significant Data Razoring","created":"2025-01-23","cited_by_count":4,"area":null},{"id":"2506.13187","title":"Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence","created":"2025-06-16","cited_by_count":4,"area":null},{"id":"2510.03267","title":"PT$^2$-LLM: Post-Training Ternarization for Large Language Models","created":"2025-09-27","cited_by_count":4,"area":null},{"id":"2601.10155","title":"LOOKAT: Lookup-Optimized Key-Attention for Memory-Efficient Transformers","created":"2026-01-15","cited_by_count":4,"area":"inference"},{"id":"2410.14570","title":"Understanding the Difficulty of Low-Precision Post-Training Quantization for LLMs","created":"2024-10-18","cited_by_count":3,"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":"2507.11959","title":"PoTPTQ: A Two-step Power-of-Two Post-training for LLMs","created":"2025-07-16","cited_by_count":3,"area":null},{"id":"2509.23729","title":"LUQ: Layerwise Ultra-Low Bit Quantization for Multimodal Large Language Models","created":"2025-09-28","cited_by_count":3,"area":"mllm"},{"id":"2509.25689","title":"Collaborative Compression for Large-Scale MoE Deployment on Edge","created":"2025-09-30","cited_by_count":3,"area":"moe"},{"id":"2602.02047","title":"Dissecting Outlier Dynamics in LLM NVFP4 Pretraining","created":"2026-02-02","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":"2603.18426","title":"Prune-then-Quantize or Quantize-then-Prune? Understanding the Impact of Compression Order in Joint Model Compression","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2608.04048","title":"Recurrent Residual Quantization: A Progressive Multi-Precision Representation for LLMs","created":"2026-08-04","cited_by_count":3,"area":null},{"id":"2408.03130","title":"Inference Optimizations for Large Language Models: Effects, Challenges, and Practical Considerations","created":"2024-08-06","cited_by_count":2,"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":"2505.07289","title":"Semantic Retention and Extreme Compression in LLMs: Can We Have Both?","created":"2025-05-12","cited_by_count":2,"area":null},{"id":"2505.22811","title":"Highly Efficient and Effective LLMs with Multi-Boolean Architectures","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2506.05664","title":"BAQ: Efficient Bit Allocation Quantization for Large Language Models","created":"2025-06-06","cited_by_count":2,"area":null},{"id":"2509.23472","title":"Memory-Efficient Fine-Tuning via Low-Rank Activation Compression","created":"2025-09-27","cited_by_count":2,"area":null},{"id":"2509.25214","title":"On-the-Fly Adaptation to Quantization: Configuration-Aware LoRA for Efficient Fine-Tuning of Quantized LLMs","created":"2025-09-22","cited_by_count":2,"area":null},{"id":"2511.15300","title":"Quant-Trim in Practice: Improved Cross-Platform Low-Bit Deployment on Edge NPUs","created":"2025-11-19","cited_by_count":2,"area":null},{"id":"2601.15287","title":"Towards Understanding Best Practices for Quantization of Vision-Language Models","created":"2026-01-21","cited_by_count":2,"area":"mllm"},{"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":"2603.14591","title":"FlashHead: Efficient Drop-In Replacement for the Classification Head in Language Model Inference","created":"2026-03-15","cited_by_count":2,"area":null},{"id":"2605.05693","title":"Saliency-Aware Regularized Quantization Calibration for Large Language Models","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2605.06366","title":"Layer Collapse in Diffusion Language Models","created":"2026-05-07","cited_by_count":2,"area":"diffusion"},{"id":"2605.17887","title":"Attention Sinks and Outliers in Attention Residuals","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2405.17233","title":"CLAQ: Pushing the Limits of Low-Bit Post-Training Quantization for LLMs","created":"2024-05-27","cited_by_count":1,"area":null},{"id":"2410.04454","title":"Inner-Probe: Discovering Copyright-related Data Generation in LLM Architecture","created":"2024-10-06","cited_by_count":1,"area":null},{"id":"2502.15077","title":"Hardware-Friendly Static Quantization Method for Video Diffusion Transformers","created":"2025-02-20","cited_by_count":1,"area":"diffusion"},{"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":"2505.08981","title":"ITERA-LLM: Boosting Sub-8-Bit Large Language Model Inference via Iterative Tensor Decomposition","created":"2025-05-13","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":"2508.19078","title":"Federated Fine-Tuning of Sparsely-Activated Large Language Models on Resource-Constrained Devices","created":"2025-08-26","cited_by_count":1,"area":"moe"},{"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":"2512.12930","title":"SeVeDo: A Heterogeneous Transformer Accelerator for Low-Bit Inference via Hierarchical Group Quantization and SVD-Guided Mixed Precision","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2512.23367","title":"Post-Training Quantization of OpenPangu Models for Efficient Deployment on Atlas A2","created":"2025-12-29","cited_by_count":1,"area":null},{"id":"2601.03484","title":"From Bits to Chips: An LLM-based Hardware-Aware Quantization Agent for Streamlined Deployment of LLMs","created":"2026-01-07","cited_by_count":1,"area":"agents"},{"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":"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":"2607.01876","title":"SAB-LVLM: Significance-Aware Binarization for Large Vision-Language Models","created":"2026-07-02","cited_by_count":1,"area":"mllm"},{"id":"2607.17733","title":"MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference","created":"2026-07-20","cited_by_count":1,"area":"inference"},{"id":"2607.24148","title":"A Motion-Aware Vector Quantization Framework with Centroid Reuse for Efficient VLA Inference","created":"2026-07-27","cited_by_count":1,"area":"vla"},{"id":"2407.15508","title":"Compensate Quantization Errors+: Quantized Models Are Inquisitive Learners","created":"2024-07-22","cited_by_count":0,"area":null},{"id":"2410.12513","title":"FiRST: Finetuning Router-Selective Transformers for Input-Adaptive Latency Reduction","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2501.12896","title":"Irrational Complex Rotations Empower Low-bit Optimizers","created":"2025-01-22","cited_by_count":0,"area":null},{"id":"2502.19662","title":"HALO: Hardware-aware quantization with low critical-path-delay weights for LLM acceleration","created":"2025-02-27","cited_by_count":0,"area":null},{"id":"2506.11087","title":"Enhancing Delta Compression in LLMs via SVD-based Quantization Error Minimization","created":"2025-06-05","cited_by_count":0,"area":null},{"id":"2509.15206","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2511.17801","title":"Layer-Wise High-Impact Parameter Ratio Optimization in Post-Training Quantization for Large Language Models","created":"2025-11-21","cited_by_count":0,"area":null},{"id":"2512.05409","title":"SQ-format: A Unified Sparse-Quantized Hardware-friendly Data Format for LLMs","created":"2025-12-05","cited_by_count":0,"area":null}],"next_cursor":"100"}