{"total":96,"rows":[{"id":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203,"area":null},{"id":"2308.06767","title":"A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations","created":"2023-08-13","cited_by_count":202,"area":null},{"id":"2305.10924","title":"Structural Pruning for Diffusion Models","created":"2023-05-18","cited_by_count":195,"area":"diffusion"},{"id":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","cited_by_count":122,"area":null},{"id":"2102.02887","title":"Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training","created":"2021-02-04","cited_by_count":110,"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":"2401.06187","title":"Scissorhands: Scrub Data Influence via Connection Sensitivity in Networks","created":"2024-01-11","cited_by_count":52,"area":"safety"},{"id":"2110.14678","title":"Meta-Learning Sparse Implicit Neural Representations","created":"2021-10-27","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":"2106.14568","title":"Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity","created":"2021-06-28","cited_by_count":44,"area":null},{"id":"2103.06460","title":"Recent Advances on Neural Network Pruning at Initialization","created":"2021-03-11","cited_by_count":41,"area":null},{"id":"2203.04466","title":"The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks","created":"2022-03-09","cited_by_count":41,"area":null},{"id":"2203.12217","title":"Training-free Transformer Architecture Search","created":"2022-03-23","cited_by_count":33,"area":null},{"id":"2210.13738","title":"Pruning's Effect on Generalization Through the Lens of Training and Regularization","created":"2022-10-25","cited_by_count":31,"area":null},{"id":"2209.13569","title":"Exploring Low Rank Training of Deep Neural Networks","created":"2022-09-27","cited_by_count":30,"area":null},{"id":"2304.02840","title":"NTK-SAP: Improving neural network pruning by aligning training dynamics","created":"2023-04-06","cited_by_count":30,"area":null},{"id":"2203.04248","title":"Dual Lottery Ticket Hypothesis","created":"2022-03-08","cited_by_count":27,"area":null},{"id":"2101.09048","title":"Selfish Sparse RNN Training","created":"2021-01-22","cited_by_count":26,"area":null},{"id":"2206.08684","title":"Sparse Double Descent: Where Network Pruning Aggravates Overfitting","created":"2022-06-17","cited_by_count":26,"area":null},{"id":"2206.12755","title":"Training Your Sparse Neural Network Better with Any Mask","created":"2022-06-26","cited_by_count":26,"area":null},{"id":"2310.07999","title":"LEMON: Lossless model expansion","created":"2023-10-12","cited_by_count":23,"area":"lr"},{"id":"2506.15544","title":"Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning","created":"2025-06-18","cited_by_count":23,"area":"deeprl"},{"id":"2102.01670","title":"Keep the Gradients Flowing: Using Gradient Flow to Study Sparse Network Optimization","created":"2021-02-02","cited_by_count":22,"area":null},{"id":"2205.02321","title":"Most Activation Functions Can Win the Lottery Without Excessive Depth","created":"2022-05-04","cited_by_count":21,"area":null},{"id":"2312.05284","title":"SlimSAM: 0.1% Data Makes Segment Anything Slim","created":"2023-12-08","cited_by_count":20,"area":null},{"id":"2102.07804","title":"Scaling Up Exact Neural Network Compression by ReLU Stability","created":"2021-02-15","cited_by_count":19,"area":null},{"id":"2105.14797","title":"RED : Looking for Redundancies for Data-Free Structured Compression of Deep Neural Networks","created":"2021-05-31","cited_by_count":19,"area":null},{"id":"2110.01397","title":"RED++ : Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Merging","created":"2021-09-30","cited_by_count":19,"area":null},{"id":"2110.14856","title":"An Operator Theoretic View on Pruning Deep Neural Networks","created":"2021-10-28","cited_by_count":18,"area":null},{"id":"2102.01732","title":"Truly Sparse Neural Networks at Scale","created":"2021-02-02","cited_by_count":16,"area":null},{"id":"2205.02343","title":"Convolutional and Residual Networks Provably Contain Lottery Tickets","created":"2022-05-04","cited_by_count":16,"area":null},{"id":"2207.12534","title":"Trainability Preserving Neural Pruning","created":"2022-07-25","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":"2405.15743","title":"Sparse maximal update parameterization: A holistic approach to sparse training dynamics","created":"2024-05-24","cited_by_count":16,"area":null},{"id":"2503.05156","title":"Accelerating Diffusion Transformer via Gradient-Optimized Cache","created":"2025-03-07","cited_by_count":15,"area":"diffusion"},{"id":"2101.10552","title":"A Unified Paths Perspective for Pruning at Initialization","created":"2021-01-26","cited_by_count":14,"area":null},{"id":"2107.02306","title":"Connectivity Matters: Neural Network Pruning Through the Lens of Effective Sparsity","created":"2021-07-05","cited_by_count":14,"area":null},{"id":"2604.22748","title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","created":"2026-04-24","cited_by_count":14,"area":"wm"},{"id":"2111.11153","title":"Plant 'n' Seek: Can You Find the Winning Ticket?","created":"2021-11-22","cited_by_count":13,"area":null},{"id":"2209.14624","title":"Is Complexity Required for Neural Network Pruning? A Case Study on Global Magnitude Pruning","created":"2022-09-29","cited_by_count":13,"area":null},{"id":"2504.10540","title":"AB-Cache: Training-Free Acceleration of Diffusion Models via Adams-Bashforth Cached Feature Reuse","created":"2025-04-13","cited_by_count":13,"area":"diffusion"},{"id":"2108.06277","title":"Towards Structured Dynamic Sparse Pre-Training of BERT","created":"2021-08-13","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":"2312.03459","title":"F3-Pruning: A Training-Free and Generalized Pruning Strategy towards Faster and Finer Text-to-Video Synthesis","created":"2023-12-06","cited_by_count":10,"area":"diffusion"},{"id":"2207.04089","title":"SInGE: Sparsity via Integrated Gradients Estimation of Neuron Relevance","created":"2022-07-08","cited_by_count":9,"area":null},{"id":"2302.14670","title":"Balanced Training for Sparse GANs","created":"2023-02-28","cited_by_count":8,"area":null},{"id":"2107.02550","title":"Universal approximation and model compression for radial neural networks","created":"2021-07-06","cited_by_count":7,"area":null},{"id":"2209.15208","title":"Scale-invariant Bayesian Neural Networks with Connectivity Tangent Kernel","created":"2022-09-30","cited_by_count":7,"area":null},{"id":"2210.05371","title":"On skip connections and normalisation layers in deep optimisation","created":"2022-10-10","cited_by_count":7,"area":null},{"id":"2308.07761","title":"NeFL: Nested Model Scaling for Federated Learning with System Heterogeneous Clients","created":"2023-08-15","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":"2107.12673","title":"COPS: Controlled Pruning Before Training Starts","created":"2021-07-27","cited_by_count":6,"area":null},{"id":"2208.08562","title":"Restructurable Activation Networks","created":"2022-08-17","cited_by_count":6,"area":null},{"id":"2402.00084","title":"EPSD: Early Pruning with Self-Distillation for Efficient Model Compression","created":"2024-01-31","cited_by_count":6,"area":"distill"},{"id":"2101.06475","title":"Slot Machines: Discovering Winning Combinations of Random Weights in Neural Networks","created":"2021-01-16","cited_by_count":5,"area":null},{"id":"2411.00147","title":"Mutual Information Preserving Neural Network Pruning","created":"2024-10-31","cited_by_count":5,"area":null},{"id":"2501.15014","title":"On Accelerating Edge AI: Optimizing Resource-Constrained Environments","created":"2025-01-25","cited_by_count":5,"area":null},{"id":"2110.11150","title":"Lottery Tickets with Nonzero Biases","created":"2021-10-21","cited_by_count":4,"area":null},{"id":"2204.11444","title":"Boosting Pruned Networks with Linear Over-parameterization","created":"2022-04-25","cited_by_count":4,"area":null},{"id":"2207.12773","title":"Quiver neural networks","created":"2022-07-26","cited_by_count":4,"area":null},{"id":"2409.14433","title":"OStr-DARTS: Differentiable Neural Architecture Search based on Operation Strength","created":"2024-09-22","cited_by_count":4,"area":null},{"id":"2102.09284","title":"Reduced-Order Neural Network Synthesis with Robustness Guarantees","created":"2021-02-18","cited_by_count":3,"area":null},{"id":"2210.12818","title":"Pushing the Efficiency Limit Using Structured Sparse Convolutions","created":"2022-10-23","cited_by_count":3,"area":null},{"id":"2210.16169","title":"LOFT: Finding Lottery Tickets through Filter-wise Training","created":"2022-10-28","cited_by_count":3,"area":null},{"id":"2312.16020","title":"Robust Neural Pruning with Gradient Sampling Optimization for Residual Neural Networks","created":"2023-12-26","cited_by_count":3,"area":null},{"id":"2404.03687","title":"DRIVE: Dual Gradient-Based Rapid Iterative Pruning","created":"2024-04-01","cited_by_count":3,"area":null},{"id":"2404.08016","title":"ONNXPruner: ONNX-Based General Model Pruning Adapter","created":"2024-04-10","cited_by_count":3,"area":null},{"id":"2406.01755","title":"Sparser, Better, Deeper, Stronger: Improving Sparse Training with Exact Orthogonal Initialization","created":"2024-06-03","cited_by_count":3,"area":null},{"id":"2604.24380","title":"Structural Pruning of Large Vision Language Models: A Comprehensive Study on Pruning Dynamics, Recovery, and Data Efficiency","created":"2026-04-27","cited_by_count":3,"area":"mllm"},{"id":"2105.05916","title":"Dynamical Isometry: The Missing Ingredient for Neural Network Pruning","created":"2021-05-12","cited_by_count":2,"area":null},{"id":"2212.00291","title":"The Effect of Data Dimensionality on Neural Network Prunability","created":"2022-12-01","cited_by_count":2,"area":null},{"id":"2305.17559","title":"Pruning at Initialization -- A Sketching Perspective","created":"2023-05-27","cited_by_count":2,"area":null},{"id":"2310.03915","title":"Leveraging Low-Rank and Sparse Recurrent Connectivity for Robust Closed-Loop Control","created":"2023-10-05","cited_by_count":2,"area":null},{"id":"2312.03236","title":"Multicoated and Folded Graph Neural Networks with Strong Lottery Tickets","created":"2023-12-06","cited_by_count":2,"area":null},{"id":"2410.08015","title":"Non-transferable Pruning","created":"2024-10-10","cited_by_count":2,"area":null},{"id":"2305.10964","title":"Learning Activation Functions for Sparse Neural Networks","created":"2023-05-18","cited_by_count":1,"area":null},{"id":"2308.06780","title":"Neural Networks at a Fraction with Pruned Quaternions","created":"2023-08-13","cited_by_count":1,"area":null},{"id":"2401.06898","title":"Always-Sparse Training by Growing Connections with Guided Stochastic Exploration","created":"2024-01-12","cited_by_count":1,"area":null},{"id":"2403.00155","title":"Towards Explaining Deep Neural Network Compression Through a Probabilistic Latent Space","created":"2024-02-29","cited_by_count":1,"area":null},{"id":"2506.07975","title":"Hyperpruning: Efficient Search through Pruned Variants of Recurrent Neural Networks Leveraging Lyapunov Spectrum","created":"2025-06-09","cited_by_count":1,"area":null},{"id":"2507.08841","title":"Zero-Shot Neural Architecture Search with Weighted Response Correlation","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2507.20749","title":"Investigating Structural Pruning and Recovery Techniques for Compressing Multimodal Large Language Models: An Empirical Study","created":"2025-07-28","cited_by_count":1,"area":"mllm"},{"id":"2103.08457","title":"RANP: Resource Aware Neuron Pruning at Initialization for 3D CNNs","created":"2021-02-09","cited_by_count":0,"area":null},{"id":"2209.13378","title":"Neural Network Panning: Screening the Optimal Sparse Network Before Training","created":"2022-09-27","cited_by_count":0,"area":null},{"id":"2305.08021","title":"TIPS: Topologically Important Path Sampling for Anytime Neural Networks","created":"2023-05-13","cited_by_count":0,"area":null},{"id":"2309.08171","title":"Unveiling Invariances via Neural Network Pruning","created":"2023-09-15","cited_by_count":0,"area":null},{"id":"2311.10549","title":"Archtree: on-the-fly tree-structured exploration for latency-aware pruning of deep neural networks","created":"2023-11-17","cited_by_count":0,"area":null},{"id":"2402.10339","title":"What to Do When Your Discrete Optimization Is the Size of a Neural Network?","created":"2024-02-15","cited_by_count":0,"area":null},{"id":"2407.04075","title":"Sparsest Models Elude Pruning: An Expos\\'e of Pruning's Current Capabilities","created":"2024-07-04","cited_by_count":0,"area":null},{"id":"2411.18578","title":"Pruning Deep Convolutional Neural Network Using Conditional Mutual Information","created":"2024-11-27","cited_by_count":0,"area":null},{"id":"2504.09803","title":"CUT: Pruning Pre-Trained Multi-Task Models into Compact Models for Edge Devices","created":"2025-04-14","cited_by_count":0,"area":null},{"id":"2506.22015","title":"Towards Universal & Efficient Model Compression via Exponential Torque Pruning","created":"2025-06-27","cited_by_count":0,"area":null},{"id":"2512.06003","title":"PrunedCaps: A Case For Primary Capsules Discrimination","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2602.08287","title":"Noise Stability of Transformer Models","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2602.22537","title":"LUMOS: Democratizing SciML Workflows with L0-Regularized Learning for Unified Feature and Parameter Adaptation","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2609.32162","title":"PruneForget: Joint Unlearning and Pruning of Vision Models","created":"2026-09-26","cited_by_count":0,"area":"safety"}],"next_cursor":null}