{"total":74,"rows":[{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202,"area":null},{"id":"2104.08378","title":"Accelerating Sparse Deep Neural Networks","created":"2021-04-16","cited_by_count":223,"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":"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":"2106.03517","title":"Top-KAST: Top-K Always Sparse Training","created":"2021-06-07","cited_by_count":79,"area":null},{"id":"2106.09129","title":"A Winning Hand: Compressing Deep Networks Can Improve Out-Of-Distribution Robustness","created":"2021-06-16","cited_by_count":62,"area":null},{"id":"2106.05933","title":"PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition","created":"2021-06-10","cited_by_count":53,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2305.19268","title":"Intriguing Properties of Quantization at Scale","created":"2023-05-30","cited_by_count":49,"area":null},{"id":"2110.03036","title":"The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation","created":"2021-10-06","cited_by_count":47,"area":null},{"id":"2307.02973","title":"Pruning vs Quantization: Which is Better?","created":"2023-07-06","cited_by_count":46,"area":null},{"id":"2202.07105","title":"A Survey on Model Compression and Acceleration for Pretrained Language Models","created":"2022-02-15","cited_by_count":45,"area":null},{"id":"2111.06061","title":"Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI","created":"2021-11-11","cited_by_count":39,"area":null},{"id":"2310.08670","title":"Every Parameter Matters: Ensuring the Convergence of Federated Learning with Dynamic Heterogeneous Models Reduction","created":"2023-10-12","cited_by_count":24,"area":null},{"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":"2312.15398","title":"Fairness-Aware Structured Pruning in Transformers","created":"2023-12-24","cited_by_count":22,"area":null},{"id":"2108.12594","title":"Layer-wise Model Pruning based on Mutual Information","created":"2021-08-28","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":"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":"2501.02086","title":"Instruction-Following Pruning for Large Language Models","created":"2025-01-03","cited_by_count":17,"area":null},{"id":"2102.01732","title":"Truly Sparse Neural Networks at Scale","created":"2021-02-02","cited_by_count":16,"area":null},{"id":"2104.10640","title":"The NLP Cookbook: Modern Recipes for Transformer based Deep Learning Architectures","created":"2021-03-23","cited_by_count":16,"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":"2305.19059","title":"Geometry-aware training of factorized layers in tensor Tucker format","created":"2023-05-30","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":"2308.07163","title":"HyperSparse Neural Networks: Shifting Exploration to Exploitation through Adaptive Regularization","created":"2023-08-14","cited_by_count":9,"area":null},{"id":"2102.04932","title":"Sparsification via Compressed Sensing for Automatic Speech Recognition","created":"2021-02-09","cited_by_count":8,"area":null},{"id":"2111.02351","title":"Weight, Block or Unit? Exploring Sparsity Tradeoffs for Speech Enhancement on Tiny Neural Accelerators","created":"2021-11-03","cited_by_count":8,"area":null},{"id":"2203.03324","title":"Dynamic ConvNets on Tiny Devices via Nested Sparsity","created":"2022-03-07","cited_by_count":8,"area":null},{"id":"2204.12430","title":"Federated Progressive Sparsification (Purge, Merge, Tune)+","created":"2022-04-26","cited_by_count":8,"area":null},{"id":"2211.01522","title":"Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing","created":"2022-11-02","cited_by_count":7,"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":"2310.01886","title":"BYOM: Building Your Own Multi-Task Model For Free","created":"2023-10-03","cited_by_count":5,"area":null},{"id":"2201.05020","title":"Automatic Sparse Connectivity Learning for Neural Networks","created":"2022-01-13","cited_by_count":4,"area":null},{"id":"2201.11803","title":"On the Convergence of Heterogeneous Federated Learning with Arbitrary Adaptive Online Model Pruning","created":"2022-01-27","cited_by_count":4,"area":null},{"id":"2307.08657","title":"Neural Image Compression: Generalization, Robustness, and Spectral Biases","created":"2023-07-17","cited_by_count":4,"area":null},{"id":"2510.17700","title":"Elastic ViTs from Pretrained Models without Retraining","created":"2025-10-20","cited_by_count":4,"area":null},{"id":"2105.10832","title":"Spectral Pruning for Recurrent Neural Networks","created":"2021-05-23","cited_by_count":3,"area":null},{"id":"2110.04252","title":"LCS: Learning Compressible Subspaces for Adaptive Network Compression at Inference Time","created":"2021-10-08","cited_by_count":3,"area":null},{"id":"2202.09284","title":"Amenable Sparse Network Investigator","created":"2022-02-18","cited_by_count":3,"area":null},{"id":"2303.16999","title":"PopSparse: Accelerated block sparse matrix multiplication on IPU","created":"2023-03-29","cited_by_count":3,"area":null},{"id":"2309.13018","title":"Dynamic ASR Pathways: An Adaptive Masking Approach Towards Efficient Pruning of A Multilingual ASR Model","created":"2023-09-22","cited_by_count":3,"area":null},{"id":"2405.05808","title":"Fast and Controllable Post-training Sparsity: Learning Optimal Sparsity Allocation with Global Constraint in Minutes","created":"2024-05-09","cited_by_count":3,"area":null},{"id":"2107.12917","title":"Experiments on Properties of Hidden Structures of Sparse Neural Networks","created":"2021-07-27","cited_by_count":2,"area":null},{"id":"2110.03298","title":"End-to-End Supermask Pruning: Learning to Prune Image Captioning Models","created":"2021-10-07","cited_by_count":2,"area":null},{"id":"2304.06941","title":"AUTOSPARSE: Towards Automated Sparse Training of Deep Neural Networks","created":"2023-04-14","cited_by_count":2,"area":null},{"id":"2309.01816","title":"Adaptive Model Pruning and Personalization for Federated Learning over Wireless Networks","created":"2023-09-04","cited_by_count":2,"area":null},{"id":"2311.07625","title":"Activity Sparsity Complements Weight Sparsity for Efficient RNN Inference","created":"2023-11-13","cited_by_count":2,"area":null},{"id":"2401.07456","title":"Only Send What You Need: Learning to Communicate Efficiently in Federated Multilingual Machine Translation","created":"2024-01-15","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},{"id":"2105.01869","title":"Encoding Weights of Irregular Sparsity for Fixed-to-Fixed Model Compression","created":"2021-05-05","cited_by_count":1,"area":null},{"id":"2208.05970","title":"WeightMom: Learning Sparse Networks using Iterative Momentum-based pruning","created":"2022-08-11","cited_by_count":1,"area":null},{"id":"2309.06951","title":"TransNet: A Transfer Learning-Based Network for Human Action Recognition","created":"2023-09-13","cited_by_count":1,"area":null},{"id":"2403.16215","title":"Systematic construction of continuous-time neural networks for linear dynamical systems","created":"2024-03-24","cited_by_count":1,"area":null},{"id":"2405.00433","title":"Weight Sparsity Complements Activity Sparsity in Neuromorphic Language Models","created":"2024-05-01","cited_by_count":1,"area":null},{"id":"2406.06290","title":"Geometric sparsification in recurrent neural networks","created":"2024-06-10","cited_by_count":1,"area":null},{"id":"2408.14055","title":"HAPM -- Hardware Aware Pruning Method for CNN hardware accelerators in resource constrained devices","created":"2024-08-26","cited_by_count":1,"area":null},{"id":"2502.03658","title":"Advancing Weight and Channel Sparsification with Enhanced Saliency","created":"2025-02-05","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":"2101.07415","title":"ES-ENAS: Efficient Evolutionary Optimization for Large Hybrid Search Spaces","created":"2021-01-19","cited_by_count":0,"area":null},{"id":"2103.16013","title":"Training Sparse Neural Network by Constraining Synaptic Weight on Unit Lp Sphere","created":"2021-03-30","cited_by_count":0,"area":null},{"id":"2106.12089","title":"Structured in Space, Randomized in Time: Leveraging Dropout in RNNs for Efficient Training","created":"2021-06-22","cited_by_count":0,"area":null},{"id":"2110.15829","title":"Holistic Deep Learning","created":"2021-10-29","cited_by_count":0,"area":null},{"id":"2205.08199","title":"Sharp asymptotics on the compression of two-layer neural networks","created":"2022-05-17","cited_by_count":0,"area":null},{"id":"2403.11100","title":"Graph Expansion in Pruned Recurrent Neural Network Layers Preserve Performance","created":"2024-03-17","cited_by_count":0,"area":null},{"id":"2408.08681","title":"A Mean Field Ansatz for Zero-Shot Weight Transfer","created":"2024-08-16","cited_by_count":0,"area":null},{"id":"2409.05368","title":"Application Specific Compression of Deep Learning Models","created":"2024-09-09","cited_by_count":0,"area":null},{"id":"2502.16525","title":"Lattice-Based Pruning in Recurrent Neural Networks via Poset Modeling","created":"2025-02-23","cited_by_count":0,"area":null},{"id":"2508.14140","title":"Neuro-inspired Ensemble-to-Ensemble Communication Primitives for Sparse and Efficient ANNs","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2606.21295","title":"Topological Neural Dynamics: A Neuron-wise Framework for Sequence Modeling","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2607.08786","title":"Accelerating GPU Inference of Large Language Models with Moderately Unstructured Sparse Weight Matrices","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2608.05464","title":"Effective pruning of task-trained recurrent neural networks using noisy fluctuations and connection rescaling","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.21126","title":"Layerwise Decoupling for Stable Structured Sparsification of Fully Connected Layers","created":"2026-09-17","cited_by_count":0,"area":null}],"next_cursor":null}