{"total":385,"rows":[{"id":"2404.00456","title":"QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs","created":"2024-03-30","cited_by_count":634,"area":"inference"},{"id":"2405.16406","title":"SpinQuant: LLM quantization with learned rotations","created":"2024-05-26","cited_by_count":471,"area":"inference"},{"id":"2403.03853","title":"ShortGPT: Layers in Large Language Models are More Redundant Than You Expect","created":"2024-03-06","cited_by_count":383,"area":null},{"id":"2403.07378","title":"SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression","created":"2024-03-12","cited_by_count":243,"area":null},{"id":"2402.05162","title":"Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications","created":"2024-02-07","cited_by_count":231,"area":"alignment"},{"id":"2403.17887","title":"The Unreasonable Ineffectiveness of the Deeper Layers","created":"2024-03-26","cited_by_count":226,"area":"lr"},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2407.14679","title":"Compact Language Models via Pruning and Knowledge Distillation","created":"2024-07-19","cited_by_count":148,"area":"distill"},{"id":"2402.11187","title":"LaCo: Large Language Model Pruning via Layer Collapse","created":"2024-02-17","cited_by_count":126,"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":"2408.11796","title":"LLM Pruning and Distillation in Practice: The Minitron Approach","created":"2024-08-21","cited_by_count":82,"area":null},{"id":"2403.00835","title":"CLLMs: Consistency Large Language Models","created":"2024-02-28","cited_by_count":72,"area":"inference"},{"id":"2503.12340","title":"SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression","created":"2025-03-16","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":"2407.21118","title":"Palu: Compressing KV-Cache with Low-Rank Projection","created":"2024-07-30","cited_by_count":64,"area":"inference"},{"id":"2409.17481","title":"MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models","created":"2024-09-26","cited_by_count":50,"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":"2406.10260","title":"Flextron: Many-in-One Flexible Large Language Model","created":"2024-06-11","cited_by_count":45,"area":null},{"id":"2402.05406","title":"Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes","created":"2024-02-08","cited_by_count":43,"area":null},{"id":"2406.02924","title":"Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for Large Language Models","created":"2024-06-05","cited_by_count":40,"area":null},{"id":"2411.10666","title":"SAM Decoding: Speculative Decoding via Suffix Automaton","created":"2024-11-16","cited_by_count":39,"area":"inference"},{"id":"2406.10594","title":"BlockPruner: Fine-grained Pruning for Large Language Models","created":"2024-06-15","cited_by_count":36,"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":"2402.16840","title":"MobiLlama: Towards Accurate and Lightweight Fully Transparent GPT","created":"2024-02-26","cited_by_count":34,"area":null},{"id":"2402.06262","title":"On the Efficacy of Eviction Policy for Key-Value Constrained Generative Language Model Inference","created":"2024-02-09","cited_by_count":32,"area":"inference"},{"id":"2407.09141","title":"Accuracy is Not All You Need","created":"2024-07-12","cited_by_count":31,"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":"2501.13484","title":"MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods","created":"2025-01-23","cited_by_count":29,"area":"ssm"},{"id":"2410.13229","title":"Quamba: A Post-Training Quantization Recipe for Selective State Space Models","created":"2024-10-17","cited_by_count":28,"area":"ssm"},{"id":"2411.05282","title":"MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization","created":"2024-11-08","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":"2502.14837","title":"Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs","created":"2025-02-20","cited_by_count":27,"area":"lr"},{"id":"2503.04992","title":"Wanda++: Pruning Large Language Models via Regional Gradients","created":"2025-03-06","cited_by_count":26,"area":"inference"},{"id":"2412.12441","title":"Numerical Pruning for Efficient Autoregressive Models","created":"2024-12-17","cited_by_count":25,"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":"2405.12250","title":"Your Transformer is Secretly Linear","created":"2024-05-19","cited_by_count":23,"area":null},{"id":"2407.16286","title":"A deeper look at depth pruning of LLMs","created":"2024-07-23","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":"2410.17770","title":"Small Singular Values Matter: A Random Matrix Analysis of Transformer Models","created":"2024-10-23","cited_by_count":21,"area":null},{"id":"2409.13652","title":"OATS: Outlier-Aware Pruning Through Sparse and Low Rank Decomposition","created":"2024-09-20","cited_by_count":20,"area":null},{"id":"2410.03960","title":"SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation","created":"2024-10-04","cited_by_count":19,"area":"inference"},{"id":"2410.19123","title":"Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design","created":"2024-10-24","cited_by_count":19,"area":"moe"},{"id":"2405.17890","title":"SLMRec: Distilling Large Language Models into Small for Sequential Recommendation","created":"2024-05-28","cited_by_count":18,"area":"distill"},{"id":"2508.01625","title":"EAC-MoE: Expert-Selection Aware Compressor for Mixture-of-Experts Large Language Models","created":"2025-08-03","cited_by_count":18,"area":"moe"},{"id":"2411.19146","title":"Puzzle: Distillation-Based NAS for Inference-Optimized LLMs","created":"2024-11-28","cited_by_count":17,"area":null},{"id":"2501.15296","title":"You Only Prune Once: Designing Calibration-Free Model Compression With Policy Learning","created":"2025-01-25","cited_by_count":17,"area":null},{"id":"2507.23279","title":"Unveiling Super Experts in Mixture-of-Experts Large Language Models","created":"2025-07-31","cited_by_count":17,"area":"moe"},{"id":"2511.04063","title":"DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization","created":"2025-11-06","cited_by_count":17,"area":null},{"id":"2503.22879","title":"Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models","created":"2025-03-28","cited_by_count":16,"area":"ssm"},{"id":"2506.04985","title":"FPTQuant: Function-Preserving Transforms for LLM Quantization","created":"2025-06-05","cited_by_count":16,"area":null},{"id":"2506.22712","title":"Generalized Linear Mode Connectivity for Transformers","created":"2025-06-28","cited_by_count":16,"area":null},{"id":"2410.05437","title":"ESPACE: Dimensionality Reduction of Activations for Model Compression","created":"2024-10-07","cited_by_count":15,"area":null},{"id":"2501.02625","title":"HALO: Hadamard-Assisted Lower-Precision Optimization for LLMs","created":"2025-01-05","cited_by_count":15,"area":null},{"id":"2505.12781","title":"A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone","created":"2025-05-19","cited_by_count":15,"area":"distill"},{"id":"2409.17372","title":"Search for Efficient Large Language Models","created":"2024-09-25","cited_by_count":14,"area":"inference"},{"id":"2410.10862","title":"Superficial Safety Alignment Hypothesis","created":"2024-10-07","cited_by_count":14,"area":"alignment"},{"id":"2502.04393","title":"UniCP: A Unified Caching and Pruning Framework for Efficient Video Generation","created":"2025-02-06","cited_by_count":14,"area":"diffusion"},{"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":"2509.04467","title":"PDTrim: Targeted Pruning for Prefill-Decode Disaggregation in Inference","created":"2025-08-29","cited_by_count":14,"area":"inference"},{"id":"2407.08044","title":"RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization","created":"2024-07-10","cited_by_count":13,"area":null},{"id":"2506.19697","title":"Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models","created":"2025-06-24","cited_by_count":13,"area":null},{"id":"2410.05265","title":"PrefixQuant: Eliminating Outliers by Prefixed Tokens for Large Language Models Quantization","created":"2024-10-07","cited_by_count":12,"area":null},{"id":"2501.17771","title":"2SSP: A Two-Stage Framework for Structured Pruning of LLMs","created":"2025-01-29","cited_by_count":12,"area":null},{"id":"2503.01483","title":"KurTail : Kurtosis-based LLM Quantization","created":"2025-03-03","cited_by_count":12,"area":null},{"id":"2602.03051","title":"SAES-SVD: Self-Adaptive Suppression of Accumulated and Local Errors for SVD-based LLM Compression","created":"2026-02-03","cited_by_count":12,"area":"mechinterp"},{"id":"2409.13199","title":"CFSP: An Efficient Structured Pruning Framework for LLMs with Coarse-to-Fine Activation Information","created":"2024-09-20","cited_by_count":11,"area":null},{"id":"2505.16162","title":"KNN-SSD: Enabling Dynamic Self-Speculative Decoding via Nearest Neighbor Layer Set Optimization","created":"2025-05-22","cited_by_count":11,"area":"inference"},{"id":"2505.18713","title":"Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer","created":"2025-05-24","cited_by_count":11,"area":null},{"id":"2506.04179","title":"SkipGPT: Dynamic Layer Pruning Reinvented with Token Awareness and Module Decoupling","created":"2025-06-04","cited_by_count":11,"area":null},{"id":"2405.10616","title":"Adaptive Feature-based Low-Rank Compression of Large Language Models via Bayesian Optimization","created":"2024-05-17","cited_by_count":10,"area":null},{"id":"2501.15316","title":"ToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruning","created":"2025-01-25","cited_by_count":10,"area":"moe"},{"id":"2502.06663","title":"EfficientLLM: Scalable Pruning-Aware Pretraining for Architecture-Agnostic Edge Language Models","created":"2025-02-10","cited_by_count":10,"area":null},{"id":"2502.14816","title":"Dynamic Low-Rank Sparse Adaptation for Large Language Models","created":"2025-02-20","cited_by_count":10,"area":null},{"id":"2601.18091","title":"From LLMs to LRMs: Rethinking Pruning for Reasoning-Centric Models","created":"2026-01-26","cited_by_count":10,"area":"lr"},{"id":"2406.04801","title":"MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks","created":"2024-06-07","cited_by_count":9,"area":"moe"},{"id":"2407.00928","title":"FoldGPT: Simple and Effective Large Language Model Compression Scheme","created":"2024-07-01","cited_by_count":9,"area":null},{"id":"2411.03513","title":"Change Is the Only Constant: Dynamic LLM Slicing based on Layer Redundancy","created":"2024-11-05","cited_by_count":9,"area":null},{"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":"2603.16952","title":"Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategies","created":"2026-03-16","cited_by_count":9,"area":null},{"id":"2407.09527","title":"BitNet b1.58 Reloaded: State-of-the-art Performance Also on Smaller Networks","created":"2024-06-24","cited_by_count":8,"area":null},{"id":"2407.19126","title":"Greedy Output Approximation: Towards Efficient Structured Pruning for LLMs Without Retraining","created":"2024-07-26","cited_by_count":8,"area":null},{"id":"2410.13761","title":"GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning","created":"2024-10-17","cited_by_count":8,"area":null},{"id":"2411.05034","title":"Eguard: Defending LLM Embeddings Against Inversion Attacks via Text Mutual Information Optimization","created":"2024-11-06","cited_by_count":8,"area":null},{"id":"2502.04416","title":"Analytical FFN-to-MoE Restructuring via Activation Pattern Analysis","created":"2025-02-06","cited_by_count":8,"area":"moe"},{"id":"2503.10714","title":"ZSMerge: Zero-Shot KV Cache Compression for Memory-Efficient Long-Context LLMs","created":"2025-03-13","cited_by_count":8,"area":"inference"},{"id":"2509.25622","title":"Layer-wise dynamic rank for compressing large language models","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2601.06787","title":"Garbage Attention in Large Language Models: BOS Sink Heads and Sink-aware Pruning","created":"2026-01-11","cited_by_count":8,"area":null},{"id":"2602.02848","title":"Zero Sum SVD: Balancing Loss Sensitivity for Low Rank LLM Compression","created":"2026-02-02","cited_by_count":8,"area":null},{"id":"2607.13124","title":"ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation","created":"2026-07-14","cited_by_count":8,"area":"distill"},{"id":"2410.04808","title":"LPZero: Language Model Zero-cost Proxy Search from Zero","created":"2024-10-07","cited_by_count":7,"area":null},{"id":"2412.20677","title":"Align Attention Heads Before Merging Them: An Effective Way for Converting MHA to GQA","created":"2024-12-30","cited_by_count":7,"area":null},{"id":"2501.17088","title":"Mamba-Shedder: Post-Transformer Compression for Efficient Selective Structured State Space Models","created":"2025-01-28","cited_by_count":7,"area":"ssm"},{"id":"2502.10216","title":"Forget the Data and Fine-Tuning! Just Fold the Network to Compress","created":"2025-02-14","cited_by_count":7,"area":null},{"id":"2504.11409","title":"Minitron-SSM: Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning","created":"2025-04-15","cited_by_count":7,"area":null},{"id":"2604.02119","title":"AA-SVD : Anchored and Adaptive SVD for Large Language Model Compression","created":"2026-04-02","cited_by_count":7,"area":null},{"id":"2605.08738","title":"SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training","created":"2026-05-09","cited_by_count":7,"area":"moe"},{"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":"2406.10576","title":"Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient","created":"2024-06-15","cited_by_count":6,"area":null},{"id":"2408.11393","title":"First Activations Matter: Training-Free Methods for Dynamic Activation in Large Language Models","created":"2024-08-21","cited_by_count":6,"area":null},{"id":"2502.03460","title":"Adapt-Pruner: Adaptive Structural Pruning for Efficient Small Language Model Training","created":"2025-02-05","cited_by_count":6,"area":null}],"next_cursor":"100"}