{"total":166,"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":"2211.05102","title":"Efficiently Scaling Transformer Inference","created":"2022-11-09","cited_by_count":539,"area":null},{"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":"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":"2108.00708","title":"Group Fisher Pruning for Practical Network Compression","created":"2021-08-02","cited_by_count":131,"area":null},{"id":"2312.11983","title":"Fluctuation-based Adaptive Structured Pruning for Large Language Models","created":"2023-12-19","cited_by_count":111,"area":null},{"id":"2102.08124","title":"Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Masks","created":"2021-02-16","cited_by_count":103,"area":null},{"id":"2111.12763","title":"Sparse is Enough in Scaling Transformers","created":"2021-11-24","cited_by_count":86,"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":"2402.02834","title":"Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods","created":"2024-02-05","cited_by_count":82,"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":"2310.01382","title":"Compressing LLMs: The Truth is Rarely Pure and Never Simple","created":"2023-10-02","cited_by_count":62,"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":"2106.12379","title":"AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks","created":"2021-06-23","cited_by_count":59,"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":"2106.04217","title":"Dynamic Sparse Training for Deep Reinforcement Learning","created":"2021-06-08","cited_by_count":49,"area":null},{"id":"2207.04606","title":"SparseTIR: Composable Abstractions for Sparse Compilation in Deep Learning","created":"2022-07-11","cited_by_count":47,"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":"2306.03805","title":"The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that Matter","created":"2023-06-06","cited_by_count":42,"area":null},{"id":"2412.20522","title":"MaskGaussian: Adaptive 3D Gaussian Representation from Probabilistic Masks","created":"2024-12-29","cited_by_count":41,"area":null},{"id":"2305.02299","title":"Dynamic Sparse Training with Structured Sparsity","created":"2023-05-03","cited_by_count":38,"area":null},{"id":"2312.17244","title":"The LLM Surgeon","created":"2023-12-28","cited_by_count":38,"area":null},{"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":"2410.20011","title":"A Survey of Small Language Models","created":"2024-10-25","cited_by_count":31,"area":null},{"id":"2208.06118","title":"An Algorithm-Hardware Co-Optimized Framework for Accelerating N:M Sparse Transformers","created":"2022-08-12","cited_by_count":29,"area":null},{"id":"2303.10464","title":"SPDF: Sparse Pre-training and Dense Fine-tuning for Large Language Models","created":"2023-03-18","cited_by_count":28,"area":null},{"id":"2202.04736","title":"Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets","created":"2022-02-09","cited_by_count":27,"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":"2312.00678","title":"The Efficiency Spectrum of Large Language Models: An Algorithmic Survey","created":"2023-12-01","cited_by_count":26,"area":null},{"id":"2302.02596","title":"Ten Lessons We Have Learned in the New \"Sparseland\": A Short Handbook for Sparse Neural Network Researchers","created":"2023-02-06","cited_by_count":25,"area":null},{"id":"2109.06133","title":"Neuro-Symbolic AI: An Emerging Class of AI Workloads and their Characterization","created":"2021-09-13","cited_by_count":22,"area":null},{"id":"2206.10451","title":"Winning the Lottery Ahead of Time: Efficient Early Network Pruning","created":"2022-06-21","cited_by_count":21,"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":"2110.15766","title":"NxMTransformer: Semi-Structured Sparsification for Natural Language Understanding via ADMM","created":"2021-10-28","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":"2207.08629","title":"Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networks","created":"2022-07-18","cited_by_count":18,"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":"2402.04744","title":"Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers","created":"2024-02-07","cited_by_count":18,"area":null},{"id":"2306.12230","title":"Fantastic Weights and How to Find Them: Where to Prune in Dynamic Sparse Training","created":"2023-06-21","cited_by_count":17,"area":null},{"id":"2105.14713","title":"1xN Pattern for Pruning Convolutional Neural Networks","created":"2021-05-31","cited_by_count":16,"area":null},{"id":"2202.07190","title":"Pruning Networks with Cross-Layer Ranking & k-Reciprocal Nearest Filters","created":"2022-02-15","cited_by_count":16,"area":null},{"id":"2301.05219","title":"Why is the State of Neural Network Pruning so Confusing? On the Fairness, Comparison Setup, and Trainability in Network Pruning","created":"2023-01-12","cited_by_count":16,"area":null},{"id":"2312.12791","title":"Model-Based Control with Sparse Neural Dynamics","created":"2023-12-20","cited_by_count":16,"area":null},{"id":"2211.14627","title":"Where to Pay Attention in Sparse Training for Feature Selection?","created":"2022-11-26","cited_by_count":15,"area":null},{"id":"2310.15929","title":"E-Sparse: Boosting the Large Language Model Inference through Entropy-based N:M Sparsity","created":"2023-10-24","cited_by_count":15,"area":null},{"id":"2203.00091","title":"Dynamic N:M Fine-grained Structured Sparse Attention Mechanism","created":"2022-02-28","cited_by_count":14,"area":null},{"id":"2309.07438","title":"Towards Artificial General Intelligence (AGI) in the Internet of Things (IoT): Opportunities and Challenges","created":"2023-09-14","cited_by_count":14,"area":null},{"id":"2103.01636","title":"Sparse Training Theory for Scalable and Efficient Agents","created":"2021-03-02","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":"2302.06548","title":"Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement Learning","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":"2310.02277","title":"Junk DNA Hypothesis: Pruning Small Pre-Trained Weights Irreversibly and Monotonically Impairs \"Difficult\" Downstream Tasks in LLMs","created":"2023-09-29","cited_by_count":13,"area":null},{"id":"2108.06277","title":"Towards Structured Dynamic Sparse Pre-Training of BERT","created":"2021-08-13","cited_by_count":12,"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":"2208.13092","title":"Lottery Aware Sparsity Hunting: Enabling Federated Learning on Resource-Limited Edge","created":"2022-08-27","cited_by_count":12,"area":null},{"id":"2211.02206","title":"Soft Masking for Cost-Constrained Channel Pruning","created":"2022-11-04","cited_by_count":12,"area":null},{"id":"2305.11203","title":"PDP: Parameter-free Differentiable Pruning is All You Need","created":"2023-05-18","cited_by_count":12,"area":null},{"id":"2305.12718","title":"HighLight: Efficient and Flexible DNN Acceleration with Hierarchical Structured Sparsity","created":"2023-05-22","cited_by_count":12,"area":null},{"id":"2411.10606","title":"AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment","created":"2024-11-15","cited_by_count":12,"area":null},{"id":"2209.07617","title":"Training Recipe for N:M Structured Sparsity with Decaying Pruning Mask","created":"2022-09-15","cited_by_count":11,"area":null},{"id":"2405.16057","title":"SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models","created":"2024-05-25","cited_by_count":11,"area":null},{"id":"2410.03030","title":"Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption Robustness","created":"2024-10-03","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":"2405.03637","title":"Collage: Light-Weight Low-Precision Strategy for LLM Training","created":"2024-05-06","cited_by_count":10,"area":null},{"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":"2302.08687","title":"VEGETA: Vertically-Integrated Extensions for Sparse/Dense GEMM Tile Acceleration on CPUs","created":"2023-02-17","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":"2402.07839","title":"Towards Meta-Pruning via Optimal Transport","created":"2024-02-12","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":"2503.01874","title":"CABS: Conflict-Aware and Balanced Sparsification for Enhancing Model Merging","created":"2025-02-26","cited_by_count":8,"area":null},{"id":"2203.02770","title":"Don't Be So Dense: Sparse-to-Sparse GAN Training Without Sacrificing Performance","created":"2022-03-05","cited_by_count":7,"area":null},{"id":"2204.02965","title":"LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification","created":"2022-04-06","cited_by_count":7,"area":null},{"id":"2207.14200","title":"CrAM: A Compression-Aware Minimizer","created":"2022-07-28","cited_by_count":7,"area":null},{"id":"2304.05511","title":"Training Large Language Models Efficiently with Sparsity and Dataflow","created":"2023-04-11","cited_by_count":7,"area":null},{"id":"2402.09773","title":"NutePrune: Efficient Progressive Pruning with Numerous Teachers for Large Language Models","created":"2024-02-15","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":"2310.11096","title":"Sparse-DySta: Sparsity-Aware Dynamic and Static Scheduling for Sparse Multi-DNN Workloads","created":"2023-10-17","cited_by_count":6,"area":null},{"id":"2105.12686","title":"Dynamic Probabilistic Pruning: A general framework for hardware-constrained pruning at different granularities","created":"2021-05-26","cited_by_count":5,"area":null},{"id":"2110.04824","title":"Haar Wavelet Feature Compression for Quantized Graph Convolutional Networks","created":"2021-10-10","cited_by_count":5,"area":null},{"id":"2201.12826","title":"OptG: Optimizing Gradient-driven Criteria in Network Sparsity","created":"2022-01-30","cited_by_count":5,"area":null},{"id":"2206.07422","title":"Deep Neural Network Pruning for Nuclei Instance Segmentation in Hematoxylin & Eosin-Stained Histological Images","created":"2022-06-15","cited_by_count":5,"area":null},{"id":"2309.13015","title":"Efficient N:M Sparse DNN Training Using Algorithm, Architecture, and Dataflow Co-Design","created":"2023-09-22","cited_by_count":5,"area":null},{"id":"2504.02168","title":"MDP: Multidimensional Vision Model Pruning with Latency Constraint","created":"2025-04-02","cited_by_count":5,"area":null},{"id":"2504.21174","title":"Efficient LLMs with AMP: Attention Heads and MLP Pruning","created":"2025-04-29","cited_by_count":5,"area":null},{"id":"2601.07892","title":"Sherry: Hardware-Efficient 1.25-Bit Ternary Quantization via Fine-grained Sparsification","created":"2026-01-12","cited_by_count":5,"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":"2406.12079","title":"Multi-Dimensional Pruning: Joint Channel, Layer and Block Pruning with Latency Constraint","created":"2024-06-17","cited_by_count":4,"area":null},{"id":"2503.09657","title":"T\\'yr-the-Pruner: Structural Pruning LLMs via Global Sparsity Distribution Optimization","created":"2025-03-12","cited_by_count":4,"area":null}],"next_cursor":"100"}