{"total":61,"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":"2311.12023","title":"LQ-LoRA: Low-rank Plus Quantized Matrix Decomposition for Efficient Language Model Finetuning","created":"2023-11-20","cited_by_count":92,"area":null},{"id":"2406.02542","title":"Loki: Low-rank Keys for Efficient Sparse Attention","created":"2024-06-04","cited_by_count":89,"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":"2402.18158","title":"Evaluating Quantized Large Language Models","created":"2024-02-28","cited_by_count":77,"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":"2304.09145","title":"Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling","created":"2023-04-18","cited_by_count":61,"area":null},{"id":"2405.18886","title":"Compressing Large Language Models using Low Rank and Low Precision Decomposition","created":"2024-05-29","cited_by_count":59,"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":"2307.08072","title":"Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical Study","created":"2023-07-16","cited_by_count":43,"area":null},{"id":"2411.02355","title":"\"Give Me BF16 or Give Me Death\"? Accuracy-Performance Trade-Offs in LLM Quantization","created":"2024-11-04","cited_by_count":34,"area":null},{"id":"2309.02784","title":"Norm Tweaking: High-performance Low-bit Quantization of Large Language Models","created":"2023-09-06","cited_by_count":33,"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":"2309.01885","title":"QuantEase: Optimization-based Quantization for Language Models","created":"2023-09-05","cited_by_count":29,"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":"2403.06408","title":"What Makes Quantization for Large Language Models Hard? An Empirical Study from the Lens of Perturbation","created":"2024-03-11","cited_by_count":23,"area":null},{"id":"2410.06040","title":"QERA: an Analytical Framework for Quantization Error Reconstruction","created":"2024-10-08","cited_by_count":22,"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":"2308.15987","title":"FPTQ: Fine-grained Post-Training Quantization for Large Language Models","created":"2023-08-30","cited_by_count":16,"area":null},{"id":"2401.15347","title":"A Comprehensive Survey of Compression Algorithms for Language Models","created":"2024-01-27","cited_by_count":15,"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":"2409.11055","title":"Exploring the Trade-Offs: Quantization Methods, Task Difficulty, and Model Size in Large Language Models From Edge to Giant","created":"2024-09-17","cited_by_count":14,"area":null},{"id":"2401.14112","title":"FP6-LLM: Efficiently Serving Large Language Models Through FP6-Centric Algorithm-System Co-Design","created":"2024-01-25","cited_by_count":12,"area":null},{"id":"2404.04748","title":"Multilingual Brain Surgeon: Large Language Models Can be Compressed Leaving No Language Behind","created":"2024-04-06","cited_by_count":11,"area":null},{"id":"2311.09550","title":"A Speed Odyssey for Deployable Quantization of LLMs","created":"2023-11-16","cited_by_count":10,"area":null},{"id":"2405.03637","title":"Collage: Light-Weight Low-Precision Strategy for LLM Training","created":"2024-05-06","cited_by_count":10,"area":null},{"id":"2407.09111","title":"Inference Optimization of Foundation Models on AI Accelerators","created":"2024-07-12","cited_by_count":9,"area":null},{"id":"2412.01129","title":"RILQ: Rank-Insensitive LoRA-based Quantization Error Compensation for Boosting 2-bit Large Language Model Accuracy","created":"2024-12-02","cited_by_count":9,"area":null},{"id":"2505.02309","title":"Optimizing LLMs for Resource-Constrained Environments: A Survey of Model Compression Techniques","created":"2025-05-05","cited_by_count":9,"area":null},{"id":"2502.05376","title":"LO-BCQ: Block Clustered Quantization for 4-bit (W4A4) LLM Inference","created":"2025-02-07","cited_by_count":7,"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":"2407.13069","title":"Dynamic Sentiment Analysis with Local Large Language Models using Majority Voting: A Study on Factors Affecting Restaurant Evaluation","created":"2024-07-18","cited_by_count":5,"area":null},{"id":"2501.18475","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","created":"2025-01-30","cited_by_count":5,"area":null},{"id":"2308.02432","title":"Performance of Large Language Models in a Computer Science Degree Program","created":"2023-07-24","cited_by_count":4,"area":null},{"id":"2401.10733","title":"Dynamic Q&A of Clinical Documents with Large Language Models","created":"2024-01-19","cited_by_count":4,"area":null},{"id":"2410.14740","title":"Harnessing Your DRAM and SSD for Sustainable and Accessible LLM Inference with Mixed-Precision and Multi-level Caching","created":"2024-10-17","cited_by_count":3,"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":"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":"2403.06497","title":"QuantTune: Optimizing Model Quantization with Adaptive Outlier-Driven Fine Tuning","created":"2024-03-11","cited_by_count":2,"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":"2506.13472","title":"ROSAQ: Rotation-based Saliency-Aware Weight Quantization for Efficiently Compressing Large Language Models","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2603.13346","title":"Post Training Quantization for Efficient Dataset Condensation","created":"2026-03-07","cited_by_count":2,"area":null},{"id":"2604.14493","title":"Pushing the Limits of On-Device Streaming ASR: A Compact, High-Accuracy English Model for Low-Latency Inference","created":"2026-04-16","cited_by_count":2,"area":null},{"id":"2605.25469","title":"JacQuant: STE-Free Quantization-Aware Training via Learned Jacobian Surrogates","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2310.17723","title":"ZeroQuant-HERO: Hardware-Enhanced Robust Optimized Post-Training Quantization Framework for W8A8 Transformers","created":"2023-10-26","cited_by_count":1,"area":null},{"id":"2408.02341","title":"An approach to optimize inference of the DIART speaker diarization pipeline","created":"2024-08-05","cited_by_count":1,"area":null},{"id":"2503.23924","title":"Model Hemorrhage and the Robustness Limits of Large Language Models","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2505.08620","title":"Resource-Efficient Language Models: Quantization for Fast and Accessible Inference","created":"2025-05-13","cited_by_count":1,"area":null},{"id":"2506.05300","title":"Power Law Guided Dynamic Sifting for Efficient Attention","created":"2025-06-05","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":"2603.08185","title":"SERQ: Saliency-Aware Low-Rank Error Reconstruction for LLM Quantization","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2603.22324","title":"DAQ: Delta-Aware Quantization for Post-Training LLM Weight Compression","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2606.01412","title":"GPTQ-intrinsic LoRA: A Near-optimal Algorithm for Low-precision Quantization with Low-rank Adaptation","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2309.12071","title":"Benchmarking quantized LLaMa-based models on the Brazilian Secondary School Exam","created":"2023-09-21","cited_by_count":0,"area":null},{"id":"2603.25385","title":"GlowQ: Group-Shared LOw-Rank Approximation for Quantized LLMs","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.21026","title":"MCAP: Deployment-Time Layer Profiling for Memory-Constrained LLM Inference","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2607.13735","title":"Constraint-Driven Model Optimization: An Industry Framework for Selecting Compression and Acceleration Techniques in Modern Machine Learning Systems","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2609.36437","title":"Bits Under ZK-LLM: Evaluating Zero-Knowledge-Friendly Quantization for Verifiable Private LLM Inference","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}