{"total":165,"rows":[{"id":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152,"area":"inference"},{"id":"2402.12374","title":"Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding","created":"2024-02-19","cited_by_count":103,"area":"inference"},{"id":"2406.11617","title":"DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling","created":"2024-06-17","cited_by_count":81,"area":null},{"id":"2403.04797","title":"Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding","created":"2024-03-05","cited_by_count":72,"area":null},{"id":"2408.09600","title":"Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning","created":"2024-08-18","cited_by_count":72,"area":"alignment"},{"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":"2502.05795","title":"The Curse of Depth in Large Language Models","created":"2025-02-09","cited_by_count":62,"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":"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":"2406.02924","title":"Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for Large Language Models","created":"2024-06-05","cited_by_count":40,"area":null},{"id":"2412.13795","title":"Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN","created":"2024-12-18","cited_by_count":37,"area":null},{"id":"2406.10594","title":"BlockPruner: Fine-grained Pruning for Large Language Models","created":"2024-06-15","cited_by_count":36,"area":null},{"id":"2410.10912","title":"AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models","created":"2024-10-14","cited_by_count":36,"area":null},{"id":"2502.06415","title":"Systematic Outliers in Large Language Models","created":"2025-02-10","cited_by_count":33,"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":"2409.06211","title":"STUN: Structured-Then-Unstructured Pruning for Scalable MoE Pruning","created":"2024-09-10","cited_by_count":30,"area":"moe"},{"id":"2411.05282","title":"MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization","created":"2024-11-08","cited_by_count":28,"area":null},{"id":"2312.00678","title":"The Efficiency Spectrum of Large Language Models: An Algorithmic Survey","created":"2023-12-01","cited_by_count":26,"area":null},{"id":"2407.11239","title":"From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications","created":"2024-07-15","cited_by_count":25,"area":null},{"id":"2602.10825","title":"Flow caching for autoregressive video generation","created":"2026-02-11","cited_by_count":25,"area":null},{"id":"2404.03865","title":"FFN-SkipLLM: A Hidden Gem for Autoregressive Decoding with Adaptive Feed Forward Skipping","created":"2024-04-05","cited_by_count":23,"area":"inference"},{"id":"2411.17525","title":"Pushing the Limits of Large Language Model Quantization via the Linearity Theorem","created":"2024-11-26","cited_by_count":21,"area":null},{"id":"2504.19449","title":"R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference","created":"2025-04-28","cited_by_count":21,"area":"inference"},{"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":"2410.07461","title":"Is C4 Dataset Optimal for Pruning? An Investigation of Calibration Data for LLM Pruning","created":"2024-10-09","cited_by_count":20,"area":null},{"id":"2410.14649","title":"EvoPress: Accurate Dynamic Model Compression via Evolutionary Search","created":"2024-10-18","cited_by_count":20,"area":null},{"id":"2504.05586","title":"Finding Fantastic Experts in MoEs: A Unified Study for Expert Dropping Strategies and Observations","created":"2025-04-08","cited_by_count":20,"area":"moe"},{"id":"2502.07780","title":"DarwinLM: Evolutionary Structured Pruning of Large Language Models","created":"2025-02-11","cited_by_count":18,"area":null},{"id":"2505.22689","title":"SlimLLM: Accurate Structured Pruning for Large Language Models","created":"2025-05-28","cited_by_count":18,"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":"2405.03594","title":"Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment","created":"2024-05-06","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":"2312.15230","title":"PERP: Rethinking the Prune-Retrain Paradigm in the Era of LLMs","created":"2023-12-23","cited_by_count":14,"area":"lr"},{"id":"2504.02010","title":"When Reasoning Meets Compression: Understanding the Effects of LLMs Compression on Large Reasoning Models","created":"2025-04-02","cited_by_count":13,"area":"lr"},{"id":"2506.14562","title":"AlphaDecay: Module-wise Weight Decay for Heavy-Tailed Balancing in LLMs","created":"2025-06-17","cited_by_count":13,"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":"2505.23811","title":"LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions","created":"2025-05-27","cited_by_count":12,"area":null},{"id":"2506.00772","title":"LIFT the Veil for the Truth: Principal Weights Emerge after Rank Reduction for Reasoning-Focused Supervised Fine-Tuning","created":"2025-06-01","cited_by_count":12,"area":"lr"},{"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":"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":"2502.00258","title":"ProxSparse: Regularized Learning of Semi-Structured Sparsity Masks for Pretrained LLMs","created":"2025-02-01","cited_by_count":11,"area":null},{"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":"2412.00069","title":"Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning","created":"2024-11-26","cited_by_count":10,"area":"moe"},{"id":"2502.14816","title":"Dynamic Low-Rank Sparse Adaptation for Large Language Models","created":"2025-02-20","cited_by_count":10,"area":null},{"id":"2506.06280","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","created":"2025-06-06","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":"2504.09897","title":"TAMP: Token-Adaptive Layerwise Pruning in Multimodal Large Language Models","created":"2025-04-14","cited_by_count":9,"area":"mllm"},{"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":"2603.06003","title":"EvoESAP: Non-Uniform Expert Pruning for Sparse MoE","created":"2026-03-06","cited_by_count":9,"area":"moe"},{"id":"2405.18380","title":"Outlier-weighed Layerwise Sampling for LLM Fine-tuning","created":"2024-05-28","cited_by_count":8,"area":null},{"id":"2408.15300","title":"GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs","created":"2024-08-27","cited_by_count":8,"area":null},{"id":"2503.01874","title":"CABS: Conflict-Aware and Balanced Sparsification for Enhancing Model Merging","created":"2025-02-26","cited_by_count":8,"area":null},{"id":"2505.01731","title":"Efficient Shapley Value-based Non-Uniform Pruning of Large Language Models","created":"2025-05-03","cited_by_count":8,"area":null},{"id":"2403.02799","title":"DPPA: Pruning Method for Large Language Model to Model Merging","created":"2024-03-05","cited_by_count":7,"area":null},{"id":"2412.00143","title":"Is Oracle Pruning the True Oracle?","created":"2024-11-28","cited_by_count":7,"area":null},{"id":"2502.00840","title":"Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense","created":"2025-02-02","cited_by_count":7,"area":null},{"id":"2507.18725","title":"The Right to be Forgotten in Pruning: Unveil Machine Unlearning on Sparse Models","created":"2025-07-24","cited_by_count":7,"area":"safety"},{"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":"2411.18077","title":"MiniKV: Pushing the Limits of LLM Inference via 2-Bit Layer-Discriminative KV Cache","created":"2024-11-27","cited_by_count":6,"area":"inference"},{"id":"2505.23807","title":"DLP: Dynamic Layerwise Pruning in Large Language Models","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2510.18030","title":"From Local to Global: Revisiting Structured Pruning Paradigms for Large Language Models","created":"2025-10-20","cited_by_count":6,"area":null},{"id":"2512.02185","title":"Think Before You Prune: Self-Reflective Structured Pruning for Reasoning Language Models","created":"2025-12-01","cited_by_count":6,"area":"lr"},{"id":"2512.08819","title":"Do Depth-Grown Models Overcome the Curse of Depth? An In-Depth Analysis","created":"2025-12-09","cited_by_count":6,"area":null},{"id":"2605.02404","title":"Statistically-Lossless Quantization of Large Language Models","created":"2026-05-04","cited_by_count":6,"area":"inference"},{"id":"2510.01650","title":"The Unseen Frontier: Pushing the Limits of LLM Sparsity with Surrogate-Free ADMM","created":"2025-10-02","cited_by_count":5,"area":null},{"id":"2602.00398","title":"MemoryLLM: Plug-n-Play Interpretable Feed-Forward Memory for Transformers","created":"2026-01-30","cited_by_count":5,"area":null},{"id":"2406.13868","title":"SDQ: Sparse Decomposed Quantization for LLM Inference","created":"2024-06-19","cited_by_count":4,"area":null},{"id":"2407.06483","title":"Composable Interventions for Language Models","created":"2024-07-09","cited_by_count":4,"area":"safety"},{"id":"2501.19090","title":"Pivoting Factorization: A Compact Meta Low-Rank Representation of Sparsity for Efficient Inference in Large Language Models","created":"2025-01-31","cited_by_count":4,"area":null},{"id":"2502.12594","title":"PASER: Post-Training Data Selection for Efficient Pruned Large Language Model Recovery","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2502.18424","title":"Compressing Language Models for Specialized Domains","created":"2025-02-25","cited_by_count":4,"area":null},{"id":"2503.04982","title":"LVLM-Compress-Bench: Benchmarking the Broader Impact of Large Vision-Language Model Compression","created":"2025-03-06","cited_by_count":4,"area":"mllm"},{"id":"2512.10922","title":"SparseSwaps: Tractable LLM Pruning Mask Refinement at Scale","created":"2025-12-11","cited_by_count":4,"area":null},{"id":"2603.15389","title":"When Does Sparsity Mitigate the Curse of Depth in LLMs","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2604.03258","title":"SoLA: Leveraging Soft Activation Sparsity and Low-Rank Decomposition for Large Language Model Compression","created":"2026-03-12","cited_by_count":4,"area":null},{"id":"2410.08666","title":"DeltaDQ: Ultra-High Delta Compression for Fine-Tuned LLMs via Group-wise Dropout and Separate Quantization","created":"2024-10-11","cited_by_count":3,"area":null},{"id":"2501.17905","title":"DReSS: Data-driven Regularized Structured Streamlining for Large Language Models","created":"2025-01-29","cited_by_count":3,"area":null},{"id":"2504.14365","title":"Accelerating LLM Inference with Flexible N:M Sparsity via A Fully Digital Compute-in-Memory Accelerator","created":"2025-04-19","cited_by_count":3,"area":null},{"id":"2505.17138","title":"RAP: Runtime Adaptive Pruning for LLM Inference","created":"2025-05-22","cited_by_count":3,"area":"inference"},{"id":"2505.18232","title":"Two-Stage Regularization-Based Structured Pruning for LLMs","created":"2025-05-23","cited_by_count":3,"area":null},{"id":"2509.23410","title":"PATCH: Learnable Tile-level Hybrid Sparsity for LLMs","created":"2025-09-27","cited_by_count":3,"area":null},{"id":"2510.19389","title":"ARA: Adaptive Rank Allocation for Efficient Large Language Model SVD Compression","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2602.01997","title":"On the Limits of Layer Pruning for Generative Reasoning in Large Language Models","created":"2026-02-02","cited_by_count":3,"area":"lr"},{"id":"2602.03537","title":"MatGPTQ: Efficient and Accurate Inference over Nested Quantized Models","created":"2026-02-03","cited_by_count":3,"area":null},{"id":"2603.01376","title":"3BASiL: An Algorithmic Framework for Sparse plus Low-Rank Compression of LLMs","created":"2026-03-02","cited_by_count":3,"area":null},{"id":"2605.00649","title":"Model Compression with Exact Budget Constraints via Riemannian Manifolds","created":"2026-05-01","cited_by_count":3,"area":null},{"id":"2405.01943","title":"Dependency-Aware Semi-Structured Sparsity of GLU Variants in Large Language Models","created":"2024-05-03","cited_by_count":2,"area":null},{"id":"2411.07066","title":"Zeroth-Order Adaptive Neuron Alignment Based Pruning without Re-Training","created":"2024-11-11","cited_by_count":2,"area":null},{"id":"2503.18377","title":"Maximum Redundancy Pruning: A Principle-Driven Layerwise Sparsity Allocation for LLMs","created":"2025-03-24","cited_by_count":2,"area":null},{"id":"2505.12216","title":"One-for-All Pruning: A Universal Model for Customized Compression of Large Language Models","created":"2025-05-18","cited_by_count":2,"area":null},{"id":"2505.13547","title":"Exploring Federated Pruning for Large Language Models","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2505.21171","title":"M-Wanda: Improving One-Shot Pruning for Multilingual LLMs","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2505.24037","title":"Leave it to the Specialist: Repair Sparse LLMs with Sparse Fine-Tuning via Sparsity Evolution","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2506.03510","title":"Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2506.22049","title":"GPAS: Accelerating Convergence of LLM Pretraining via Gradient-Preserving Activation Scaling","created":"2025-06-27","cited_by_count":2,"area":null},{"id":"2509.00096","title":"Pruning Weights but Not Truth: Safeguarding Truthfulness While Pruning LLMs","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2510.05528","title":"ARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix Factorization","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2510.13713","title":"Don't Be Greedy, Just Relax! Pruning LLMs via Frank-Wolfe","created":"2025-10-15","cited_by_count":2,"area":null},{"id":"2510.22767","title":"TELL-TALE: Task Efficient LLMs with Task Aware Layer Elimination","created":"2025-10-26","cited_by_count":2,"area":null}],"next_cursor":"100"}