{"total":103,"rows":[{"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":"2305.09781","title":"SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification","created":"2023-05-16","cited_by_count":365,"area":"inference"},{"id":"2208.11580","title":"Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning","created":"2022-08-24","cited_by_count":322,"area":null},{"id":"2104.08378","title":"Accelerating Sparse Deep Neural Networks","created":"2021-04-16","cited_by_count":223,"area":null},{"id":"2311.08252","title":"REST: Retrieval-Based Speculative Decoding","created":"2023-11-14","cited_by_count":150,"area":"inference"},{"id":"2402.14800","title":"Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models","created":"2024-02-22","cited_by_count":146,"area":"moe"},{"id":"2207.03620","title":"More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity","created":"2022-07-07","cited_by_count":142,"area":null},{"id":"2106.10404","title":"Sparse Training via Boosting Pruning Plasticity with Neuroregeneration","created":"2021-06-19","cited_by_count":84,"area":null},{"id":"2310.08915","title":"Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs","created":"2023-10-13","cited_by_count":61,"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":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2309.08520","title":"Scaling Laws for Sparsely-Connected Foundation Models","created":"2023-09-15","cited_by_count":43,"area":null},{"id":"2410.06270","title":"Mixture Compressor for Mixture-of-Experts LLMs Gains More","created":"2024-10-08","cited_by_count":41,"area":"moe"},{"id":"2201.13096","title":"SPDY: Accurate Pruning with Speedup Guarantees","created":"2022-01-31","cited_by_count":36,"area":null},{"id":"2206.06662","title":"Learning Best Combination for Efficient N:M Sparsity","created":"2022-06-14","cited_by_count":32,"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":"2305.11186","title":"Compress, Then Prompt: Improving Accuracy-Efficiency Trade-off of LLM Inference with Transferable Prompt","created":"2023-05-17","cited_by_count":28,"area":null},{"id":"2302.01172","title":"STEP: Learning N:M Structured Sparsity Masks from Scratch with Precondition","created":"2023-02-02","cited_by_count":26,"area":null},{"id":"2303.04185","title":"Gradient-Free Structured Pruning with Unlabeled Data","created":"2023-03-07","cited_by_count":26,"area":null},{"id":"2402.17946","title":"SparseLLM: Towards Global Pruning for Pre-trained Language Models","created":"2024-02-28","cited_by_count":23,"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":"2405.16325","title":"SLoPe: Double-Pruned Sparse Plus Lazy Low-Rank Adapter Pretraining of LLMs","created":"2024-05-25","cited_by_count":20,"area":null},{"id":"2407.20584","title":"Pruning Large Language Models with Semi-Structural Adaptive Sparse Training","created":"2024-07-30","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":"2410.15567","title":"Pruning Foundation Models for High Accuracy without Retraining","created":"2024-10-21","cited_by_count":20,"area":null},{"id":"2310.05015","title":"Compresso: Structured Pruning with Collaborative Prompting Learns Compact Large Language Models","created":"2023-10-08","cited_by_count":19,"area":null},{"id":"2404.01847","title":"Accelerating Transformer Pre-training with 2:4 Sparsity","created":"2024-04-02","cited_by_count":19,"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":"2305.19454","title":"Dynamic Sparsity Is Channel-Level Sparsity Learner","created":"2023-05-30","cited_by_count":18,"area":null},{"id":"2312.05215","title":"DeltaZip: Efficient Serving of Multiple Full-Model-Tuned LLMs","created":"2023-12-08","cited_by_count":18,"area":null},{"id":"2404.10445","title":"SparseDM: Toward Sparse Efficient Diffusion Models","created":"2024-04-16","cited_by_count":18,"area":"diffusion"},{"id":"2105.14713","title":"1xN Pattern for Pruning Convolutional Neural Networks","created":"2021-05-31","cited_by_count":16,"area":null},{"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":"2302.04852","title":"SparseProp: Efficient Sparse Backpropagation for Faster Training of Neural Networks","created":"2023-02-09","cited_by_count":13,"area":null},{"id":"2302.06058","title":"Bi-directional Masks for Efficient N:M Sparse Training","created":"2023-02-13","cited_by_count":13,"area":null},{"id":"2304.14082","title":"JaxPruner: A concise library for sparsity research","created":"2023-04-27","cited_by_count":13,"area":null},{"id":"2204.12266","title":"Attentive Fine-Grained Structured Sparsity for Image Restoration","created":"2022-04-26","cited_by_count":12,"area":null},{"id":"2205.08099","title":"Dimensionality Reduced Training by Pruning and Freezing Parts of a Deep Neural Network, a Survey","created":"2022-05-17","cited_by_count":12,"area":null},{"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":"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":"2407.03157","title":"Let the Code LLM Edit Itself When You Edit the Code","created":"2024-07-03","cited_by_count":10,"area":"inference"},{"id":"2203.10991","title":"Minimum Variance Unbiased N:M Sparsity for the Neural Gradients","created":"2022-03-21","cited_by_count":9,"area":null},{"id":"2505.11892","title":"Fast RoPE Attention: Combining the Polynomial Method and Fast Fourier Transform","created":"2025-05-17","cited_by_count":9,"area":null},{"id":"2202.00774","title":"Accelerating DNN Training with Structured Data Gradient Pruning","created":"2022-02-01","cited_by_count":8,"area":null},{"id":"2303.11525","title":"Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency","created":"2023-03-21","cited_by_count":8,"area":null},{"id":"2403.07953","title":"Enabling Unstructured Sparse Acceleration on Structured Sparse Accelerators","created":"2024-03-12","cited_by_count":8,"area":null},{"id":"2207.14200","title":"CrAM: A Compression-Aware Minimizer","created":"2022-07-28","cited_by_count":7,"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":"2406.12837","title":"LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging","created":"2024-06-18","cited_by_count":7,"area":null},{"id":"2409.09099","title":"S-STE: Continuous Pruning Function for Efficient 2:4 Sparse Pre-training","created":"2024-09-13","cited_by_count":7,"area":null},{"id":"2504.05346","title":"Thanos: A Block-wise Pruning Algorithm for Efficient Large Language Model Compression","created":"2025-04-06","cited_by_count":7,"area":null},{"id":"2505.16284","title":"Only Large Weights (And Not Skip Connections) Can Prevent the Perils of Rank Collapse","created":"2025-05-22","cited_by_count":7,"area":null},{"id":"2602.10144","title":"When LLMs get significantly worse: A statistical approach to detect model degradations","created":"2026-02-09","cited_by_count":7,"area":null},{"id":"2301.03573","title":"Balance is Essence: Accelerating Sparse Training via Adaptive Gradient Correction","created":"2023-01-09","cited_by_count":5,"area":null},{"id":"2303.04555","title":"Streaming Kernel PCA Algorithm With Small Space","created":"2023-03-08","cited_by_count":5,"area":null},{"id":"2405.11236","title":"TriLoRA: Integrating SVD for Advanced Style Personalization in Text-to-Image Generation","created":"2024-05-18","cited_by_count":5,"area":"diffusion"},{"id":"2506.06866","title":"SAFE: Finding Sparse and Flat Minima to Improve Pruning","created":"2025-06-07","cited_by_count":5,"area":null},{"id":"2204.02004","title":"Bimodal Distributed Binarized Neural Networks","created":"2022-04-05","cited_by_count":4,"area":null},{"id":"2306.17504","title":"Systematic Investigation of Sparse Perturbed Sharpness-Aware Minimization Optimizer","created":"2023-06-30","cited_by_count":4,"area":null},{"id":"2401.04044","title":"FFSplit: Split Feed-Forward Network For Optimizing Accuracy-Efficiency Trade-off in Language Model Inference","created":"2024-01-08","cited_by_count":4,"area":null},{"id":"2501.18015","title":"A Proximal Operator for Inducing 2:4-Sparsity","created":"2025-01-29","cited_by_count":4,"area":null},{"id":"2506.11449","title":"Dynamic Sparse Training of Diagonally Sparse Networks","created":"2025-06-13","cited_by_count":4,"area":null},{"id":"2105.12920","title":"Search Spaces for Neural Model Training","created":"2021-05-27","cited_by_count":3,"area":null},{"id":"2410.14852","title":"FedSpaLLM: Federated Pruning of Large Language Models","created":"2024-10-18","cited_by_count":3,"area":null},{"id":"2211.08544","title":"Exploiting the Partly Scratch-off Lottery Ticket for Quantization-Aware Training","created":"2022-11-12","cited_by_count":2,"area":null},{"id":"2303.09650","title":"Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution","created":"2023-03-16","cited_by_count":2,"area":null},{"id":"2303.14409","title":"Vision Models Can Be Efficiently Specialized via Few-Shot Task-Aware Compression","created":"2023-03-25","cited_by_count":2,"area":null},{"id":"2307.11904","title":"Model Compression Methods for YOLOv5: A Review","created":"2023-07-21","cited_by_count":2,"area":null},{"id":"2310.04519","title":"SPADE: Sparsity-Guided Debugging for Deep Neural Networks","created":"2023-10-06","cited_by_count":2,"area":null},{"id":"2312.00662","title":"Nonparametric Variational Regularisation of Pretrained Transformers","created":"2023-12-01","cited_by_count":2,"area":null},{"id":"2407.17437","title":"Nerva: a Truly Sparse Implementation of Neural Networks","created":"2024-07-24","cited_by_count":2,"area":null},{"id":"2410.16135","title":"Beyond 2:4: exploring V:N:M sparsity for efficient transformer inference on GPUs","created":"2024-10-21","cited_by_count":2,"area":null},{"id":"2502.10735","title":"Beyond One-Size-Fits-All Pruning via Evolutionary Metric Search for Large Language Models","created":"2025-02-15","cited_by_count":2,"area":null},{"id":"2503.14076","title":"Theoretical Foundation of Flow-Based Time Series Generation: Provable Approximation, Generalization, and Efficiency","created":"2025-03-18","cited_by_count":2,"area":"diffusion"},{"id":"2510.10962","title":"MC#: Mixture Compressor for Mixture-of-Experts Large Models","created":"2025-10-13","cited_by_count":2,"area":"mllm"},{"id":"2207.00670","title":"DRESS: Dynamic REal-time Sparse Subnets","created":"2022-07-01","cited_by_count":1,"area":null},{"id":"2306.05612","title":"Spatial Re-parameterization for N:M Sparsity","created":"2023-06-09","cited_by_count":1,"area":null},{"id":"2405.09037","title":"SSFL: Discovering Sparse Unified Subnetworks at Initialization for Efficient Federated Learning","created":"2024-05-15","cited_by_count":1,"area":null},{"id":"2503.22451","title":"STADE: Standard Deviation as a Pruning Metric","created":"2025-03-28","cited_by_count":1,"area":null},{"id":"2509.25996","title":"CAST: Continuous and Differentiable Semi-Structured Sparsity-Aware Training for Large Language Models","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2510.00192","title":"Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2510.10136","title":"PermLLM: Learnable Channel Permutation for N:M Sparse Large Language Models","created":"2025-10-11","cited_by_count":1,"area":null},{"id":"2605.21426","title":"Adaptive Signal Resuscitation: Channel-wise Post-Pruning Repair for Sparse Vision Networks","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2605.25508","title":"Relative Repairability: A Calibration-Based Diagnostic for High-Sparsity Post-Pruning Allocation","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2606.14150","title":"Small LLMs: Pruning vs. Training from Scratch","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2312.07061","title":"MaxQ: Multi-Axis Query for N:M Sparsity Network","created":"2023-12-12","cited_by_count":0,"area":null},{"id":"2407.20496","title":"Toward Efficient Permutation for Hierarchical N:M Sparsity on GPUs","created":"2024-07-30","cited_by_count":0,"area":null},{"id":"2409.20094","title":"Aggressive Post-Training Compression on Extremely Large Language Models","created":"2024-09-30","cited_by_count":0,"area":null},{"id":"2411.00288","title":"Inducing Semi-Structured Sparsity by Masking for Efficient Model Inference in Convolutional Networks","created":"2024-11-01","cited_by_count":0,"area":null},{"id":"2504.08620","title":"Efficient Mixture of Geographical Species for On Device Wildlife Monitoring","created":"2025-04-11","cited_by_count":0,"area":null},{"id":"2505.18313","title":"PLUMAGE: Probabilistic Low rank Unbiased Min Variance Gradient Estimator for Efficient Large Model Training","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2505.23949","title":"TSENOR: Highly-Efficient Algorithm for Finding Transposable N:M Sparse Masks","created":"2025-05-29","cited_by_count":0,"area":null},{"id":"2510.14812","title":"SHUFFLESPARSE: Learned Shuffles for Structured Sparse Networks","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2511.02681","title":"Optimal Singular Damage: Efficient LLM Inference in Low Storage Regimes","created":"2025-11-04","cited_by_count":0,"area":"inference"},{"id":"2511.08360","title":"Extreme Model Compression with Structured Sparsity at Low Precision","created":"2025-11-11","cited_by_count":0,"area":null},{"id":"2601.00007","title":"Yahtzee: Reinforcement Learning Techniques for Stochastic Combinatorial Games","created":"2025-12-18","cited_by_count":0,"area":"deeprl"}],"next_cursor":"100"}