{"total":322,"rows":[{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919,"area":null},{"id":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121,"area":null},{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800,"area":null},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"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":"2401.15024","title":"SliceGPT: Compress Large Language Models by Deleting Rows and Columns","created":"2024-01-26","cited_by_count":385,"area":null},{"id":"2306.03078","title":"SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression","created":"2023-06-05","cited_by_count":367,"area":null},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269,"area":null},{"id":"2401.06118","title":"Extreme Compression of Large Language Models via Additive Quantization","created":"2024-01-11","cited_by_count":232,"area":null},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2402.04291","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","created":"2024-02-06","cited_by_count":144,"area":null},{"id":"2306.02272","title":"OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models","created":"2023-06-04","cited_by_count":114,"area":null},{"id":"2402.09025","title":"SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks","created":"2024-02-14","cited_by_count":97,"area":null},{"id":"2305.11391","title":"A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation","created":"2023-05-19","cited_by_count":93,"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":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2402.15319","title":"GPTVQ: The Blessing of Dimensionality for LLM Quantization","created":"2024-02-23","cited_by_count":82,"area":null},{"id":"2303.08302","title":"ZeroQuant-V2: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation","created":"2023-03-15","cited_by_count":79,"area":null},{"id":"2305.15805","title":"Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers","created":"2023-05-25","cited_by_count":67,"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":"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":"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":"2504.02692","title":"GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibration","created":"2025-04-03","cited_by_count":60,"area":null},{"id":"2311.09755","title":"On the Impact of Calibration Data in Post-training Quantization and Pruning","created":"2023-11-16","cited_by_count":58,"area":null},{"id":"2403.15447","title":"Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression","created":"2024-03-18","cited_by_count":57,"area":null},{"id":"2402.12048","title":"Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models","created":"2024-02-19","cited_by_count":54,"area":"mllm"},{"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":"2302.04089","title":"ZipLM: Inference-Aware Structured Pruning of Language Models","created":"2023-02-07","cited_by_count":49,"area":null},{"id":"2401.04679","title":"RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptation","created":"2024-01-09","cited_by_count":48,"area":null},{"id":"2408.09632","title":"MoDeGPT: Modular Decomposition for Large Language Model Compression","created":"2024-08-19","cited_by_count":48,"area":null},{"id":"2307.02973","title":"Pruning vs Quantization: Which is Better?","created":"2023-07-06","cited_by_count":46,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2305.17455","title":"CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers","created":"2023-05-27","cited_by_count":44,"area":"mllm"},{"id":"2307.09782","title":"ZeroQuant-FP: A Leap Forward in LLMs Post-Training W4A8 Quantization Using Floating-Point Formats","created":"2023-07-19","cited_by_count":44,"area":null},{"id":"2412.18110","title":"SlimGPT: Layer-wise Structured Pruning for Large Language Models","created":"2024-12-24","cited_by_count":44,"area":null},{"id":"2511.13653","title":"Weight-sparse transformers have interpretable circuits","created":"2025-11-17","cited_by_count":44,"area":"mechinterp"},{"id":"2403.01267","title":"Dissecting Language Models: Machine Unlearning via Selective Pruning","created":"2024-03-02","cited_by_count":42,"area":"safety"},{"id":"2504.09629","title":"Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization","created":"2025-04-13","cited_by_count":41,"area":null},{"id":"2312.17244","title":"The LLM Surgeon","created":"2023-12-28","cited_by_count":38,"area":null},{"id":"2410.03765","title":"Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model Compression","created":"2024-10-02","cited_by_count":35,"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":"2402.14866","title":"APTQ: Attention-aware Post-Training Mixed-Precision Quantization for Large Language Models","created":"2024-02-21","cited_by_count":34,"area":null},{"id":"2505.07004","title":"GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance","created":"2025-05-11","cited_by_count":32,"area":null},{"id":"2509.23202","title":"Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization","created":"2025-09-27","cited_by_count":32,"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":"2410.03129","title":"ARB-LLM: Alternating Refined Binarizations for Large Language Models","created":"2024-10-04","cited_by_count":31,"area":null},{"id":"2311.04902","title":"Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models","created":"2023-11-08","cited_by_count":30,"area":null},{"id":"2406.05981","title":"ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization","created":"2024-06-10","cited_by_count":30,"area":null},{"id":"2502.02421","title":"Activation-Informed Merging of Large Language Models","created":"2025-02-04","cited_by_count":30,"area":null},{"id":"2309.01885","title":"QuantEase: Optimization-based Quantization for Language Models","created":"2023-09-05","cited_by_count":29,"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":"2505.11695","title":"Qronos: Correcting the Past by Shaping the Future... in Post-Training Quantization","created":"2025-05-16","cited_by_count":28,"area":null},{"id":"2405.18218","title":"FinerCut: Finer-grained Interpretable Layer Pruning for Large Language Models","created":"2024-05-28","cited_by_count":27,"area":null},{"id":"2303.04185","title":"Gradient-Free Structured Pruning with Unlabeled Data","created":"2023-03-07","cited_by_count":26,"area":null},{"id":"2410.11988","title":"DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models","created":"2024-10-15","cited_by_count":24,"area":null},{"id":"2301.12017","title":"Understanding INT4 Quantization for Transformer Models: Latency Speedup, Composability, and Failure Cases","created":"2023-01-27","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":"2502.09720","title":"NestQuant: Nested Lattice Quantization for Matrix Products and LLMs","created":"2025-02-13","cited_by_count":23,"area":null},{"id":"2508.14896","title":"Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs","created":"2025-08-20","cited_by_count":23,"area":null},{"id":"2407.10032","title":"LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware Grid","created":"2024-07-14","cited_by_count":22,"area":null},{"id":"2408.13233","title":"Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time","created":"2024-08-23","cited_by_count":22,"area":null},{"id":"2210.09223","title":"CAP: Correlation-Aware Pruning for Highly-Accurate Sparse Vision Models","created":"2022-10-14","cited_by_count":20,"area":null},{"id":"2306.08162","title":"INT2.1: Towards Fine-Tunable Quantized Large Language Models with Error Correction through Low-Rank Adaptation","created":"2023-06-13","cited_by_count":20,"area":null},{"id":"2410.15567","title":"Pruning Foundation Models for High Accuracy without Retraining","created":"2024-10-21","cited_by_count":20,"area":null},{"id":"2507.18553","title":"The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm","created":"2025-07-24","cited_by_count":20,"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":"2406.07831","title":"ALPS: Improved Optimization for Highly Sparse One-Shot Pruning for Large Language Models","created":"2024-06-12","cited_by_count":19,"area":null},{"id":"2408.12151","title":"A Tighter Complexity Analysis of SparseGPT","created":"2024-08-22","cited_by_count":19,"area":null},{"id":"2510.06751","title":"OBS-Diff: Accurate Pruning For Diffusion Models in One-Shot","created":"2025-10-08","cited_by_count":19,"area":"diffusion"},{"id":"2403.06082","title":"FrameQuant: Flexible Low-Bit Quantization for Transformers","created":"2024-03-10","cited_by_count":18,"area":null},{"id":"2502.15799","title":"Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models","created":"2025-02-18","cited_by_count":18,"area":"lr"},{"id":"2310.09499","title":"One-Shot Sensitivity-Aware Mixed Sparsity Pruning for Large Language Models","created":"2023-10-14","cited_by_count":16,"area":null},{"id":"2311.09335","title":"Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization","created":"2023-11-15","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":"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":"2508.04853","title":"Provable Post-Training Quantization: Theoretical Analysis of OPTQ and Qronos","created":"2025-08-06","cited_by_count":16,"area":null},{"id":"2309.01729","title":"Softmax Bias Correction for Quantized Generative Models","created":"2023-09-04","cited_by_count":15,"area":"diffusion"},{"id":"2402.04902","title":"L4Q: Parameter Efficient Quantization-Aware Fine-Tuning on Large Language Models","created":"2024-02-07","cited_by_count":15,"area":null},{"id":"2410.17711","title":"Beware of Calibration Data for Pruning Large Language Models","created":"2024-10-23","cited_by_count":15,"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":"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":"2410.10862","title":"Superficial Safety Alignment Hypothesis","created":"2024-10-07","cited_by_count":14,"area":"alignment"},{"id":"2502.16638","title":"Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression","created":"2025-02-23","cited_by_count":14,"area":null},{"id":"2410.06020","title":"QT-DoG: Quantization-aware Training for Domain Generalization","created":"2024-10-08","cited_by_count":13,"area":null},{"id":"2410.17170","title":"Self-calibration for Language Model Quantization and Pruning","created":"2024-10-22","cited_by_count":13,"area":null},{"id":"2403.07134","title":"COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization","created":"2024-03-11","cited_by_count":12,"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":"2407.07093","title":"FBI-LLM: Scaling Up Fully Binarized LLMs from Scratch via Autoregressive Distillation","created":"2024-07-09","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":"2507.04290","title":"MPQ-DMv2: Flexible Residual Mixed Precision Quantization for Low-Bit Diffusion Models with Temporal Distillation","created":"2025-07-06","cited_by_count":12,"area":"diffusion"},{"id":"2401.02938","title":"Fast and Effective Weight Update for Pruned Large Language Models","created":"2024-01-01","cited_by_count":11,"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":"2411.18376","title":"Preserving Deep Representations In One-Shot Pruning: A Hessian-Free Second-Order Optimization Framework","created":"2024-11-27","cited_by_count":11,"area":null},{"id":"2503.01901","title":"Identifying Sensitive Weights via Post-quantization Integral","created":"2025-02-28","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":"2312.15322","title":"Hardware-Aware DNN Compression via Diverse Pruning and Mixed-Precision Quantization","created":"2023-12-23","cited_by_count":10,"area":null}],"next_cursor":"100"}