{"total":84,"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":"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":"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":"2106.04533","title":"Chasing Sparsity in Vision Transformers: An End-to-End Exploration","created":"2021-06-08","cited_by_count":183,"area":null},{"id":"2106.08962","title":"Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better","created":"2021-06-16","cited_by_count":154,"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":"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":"2106.12379","title":"AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks","created":"2021-06-23","cited_by_count":59,"area":null},{"id":"2112.09824","title":"Federated Dynamic Sparse Training: Computing Less, Communicating Less, Yet Learning Better","created":"2021-12-18","cited_by_count":55,"area":null},{"id":"2111.13445","title":"How Well Do Sparse Imagenet Models Transfer?","created":"2021-11-26","cited_by_count":50,"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":"2104.11832","title":"Playing Lottery Tickets with Vision and Language","created":"2021-04-23","cited_by_count":45,"area":null},{"id":"2208.02507","title":"ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsity","created":"2022-08-04","cited_by_count":45,"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":"2309.08520","title":"Scaling Laws for Sparsely-Connected Foundation Models","created":"2023-09-15","cited_by_count":43,"area":null},{"id":"2104.08682","title":"Rethinking Network Pruning -- under the Pre-train and Fine-tune Paradigm","created":"2021-04-18","cited_by_count":40,"area":null},{"id":"2305.02299","title":"Dynamic Sparse Training with Structured Sparsity","created":"2023-05-03","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":"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":"2102.08329","title":"An Information-Theoretic Justification for Model Pruning","created":"2021-02-16","cited_by_count":25,"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":"2104.15023","title":"Post-training deep neural network pruning via layer-wise calibration","created":"2021-04-30","cited_by_count":24,"area":null},{"id":"2103.16547","title":"The Elastic Lottery Ticket Hypothesis","created":"2021-03-30","cited_by_count":23,"area":null},{"id":"2110.08190","title":"Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm","created":"2021-10-15","cited_by_count":21,"area":null},{"id":"2104.00749","title":"Anytime Dense Prediction with Confidence Adaptivity","created":"2021-04-01","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":"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":"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":"2203.07808","title":"Interspace Pruning: Using Adaptive Filter Representations to Improve Training of Sparse CNNs","created":"2022-03-15","cited_by_count":16,"area":null},{"id":"2206.04662","title":"DiSparse: Disentangled Sparsification for Multitask Model Compression","created":"2022-06-09","cited_by_count":14,"area":null},{"id":"2101.07948","title":"SparseDNN: Fast Sparse Deep Learning Inference on CPUs","created":"2021-01-20","cited_by_count":13,"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":"2304.14082","title":"JaxPruner: A concise library for sparsity research","created":"2023-04-27","cited_by_count":13,"area":null},{"id":"2112.06539","title":"MinkLoc3D-SI: 3D LiDAR place recognition with sparse convolutions, spherical coordinates, and intensity","created":"2021-12-13","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":"2308.13504","title":"A2Q: Accumulator-Aware Quantization with Guaranteed Overflow Avoidance","created":"2023-08-25","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":"2304.12622","title":"Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures","created":"2023-04-25","cited_by_count":11,"area":null},{"id":"2104.08700","title":"Lottery Jackpots Exist in Pre-trained Models","created":"2021-04-18","cited_by_count":10,"area":null},{"id":"2204.11218","title":"Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training","created":"2022-04-24","cited_by_count":10,"area":null},{"id":"2406.01820","title":"Finding Lottery Tickets in Vision Models via Data-driven Spectral Foresight Pruning","created":"2024-06-03","cited_by_count":10,"area":null},{"id":"2401.06426","title":"UPDP: A Unified Progressive Depth Pruner for CNN and Vision Transformer","created":"2024-01-12","cited_by_count":9,"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":"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":"2402.15978","title":"Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks Using the Marginal Likelihood","created":"2024-02-25","cited_by_count":7,"area":null},{"id":"2403.07688","title":"Maxwell's Demon at Work: Efficient Pruning by Leveraging Saturation of Neurons","created":"2024-03-12","cited_by_count":6,"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":"2206.04762","title":"Data-Efficient Double-Win Lottery Tickets from Robust Pre-training","created":"2022-06-09","cited_by_count":5,"area":null},{"id":"2401.10432","title":"A2Q+: Improving Accumulator-Aware Weight Quantization","created":"2024-01-19","cited_by_count":5,"area":null},{"id":"2302.07612","title":"Towards Optimal Compression: Joint Pruning and Quantization","created":"2023-02-15","cited_by_count":4,"area":null},{"id":"2404.03687","title":"DRIVE: Dual Gradient-Based Rapid Iterative Pruning","created":"2024-04-01","cited_by_count":3,"area":null},{"id":"2407.03331","title":"A Scene-aware Models Adaptation Scheme for Cross-scene Online Inference on Mobile Devices","created":"2024-05-09","cited_by_count":3,"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":"2201.09881","title":"Iterative Activation-based Structured Pruning","created":"2022-01-22","cited_by_count":2,"area":null},{"id":"2304.01914","title":"Accelerating and Compressing Deep Neural Networks for Massive MIMO CSI Feedback","created":"2023-01-20","cited_by_count":2,"area":null},{"id":"2405.04765","title":"When Foresight Pruning Meets Zeroth-Order Optimization: Efficient Federated Learning for Low-Memory Devices","created":"2024-05-08","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":"2602.18825","title":"Bayesian Lottery Ticket Hypothesis","created":"2026-02-21","cited_by_count":2,"area":null},{"id":"2106.08846","title":"Algorithm to Compilation Co-design: An Integrated View of Neural Network Sparsity","created":"2021-06-16","cited_by_count":1,"area":null},{"id":"2109.05432","title":"Prioritized Subnet Sampling for Resource-Adaptive Supernet Training","created":"2021-09-12","cited_by_count":1,"area":null},{"id":"2203.13802","title":"Playing Lottery Tickets in Style Transfer Models","created":"2022-03-25","cited_by_count":1,"area":null},{"id":"2205.00618","title":"LoopStack: a Lightweight Tensor Algebra Compiler Stack","created":"2022-05-02","cited_by_count":1,"area":null},{"id":"2207.00670","title":"DRESS: Dynamic REal-time Sparse Subnets","created":"2022-07-01","cited_by_count":1,"area":null},{"id":"2207.11912","title":"Dive into Big Model Training","created":"2022-07-25","cited_by_count":1,"area":null},{"id":"2304.07488","title":"SalientGrads: Sparse Models for Communication Efficient and Data Aware Distributed Federated Training","created":"2023-04-15","cited_by_count":1,"area":null},{"id":"2304.07613","title":"STen: Productive and Efficient Sparsity in PyTorch","created":"2023-04-15","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":"2310.06218","title":"SUBP: Soft Uniform Block Pruning for 1xN Sparse CNNs Multithreading Acceleration","created":"2023-10-10","cited_by_count":1,"area":null},{"id":"2312.05828","title":"Sparse Multitask Learning for Efficient Neural Representation of Motor Imagery and Execution","created":"2023-12-10","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":"2508.21394","title":"AI Compute Architecture and Evolution Trends","created":"2025-08-29","cited_by_count":1,"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":"2109.00170","title":"Architecture Aware Latency Constrained Sparse Neural Networks","created":"2021-09-01","cited_by_count":0,"area":null},{"id":"2110.08013","title":"Joint Channel and Weight Pruning for Model Acceleration on Moblie Devices","created":"2021-10-15","cited_by_count":0,"area":null},{"id":"2306.15656","title":"SparseOptimizer: Sparsify Language Models through Moreau-Yosida Regularization and Accelerate via Compiler Co-design","created":"2023-06-27","cited_by_count":0,"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":"2312.11555","title":"CR-SFP: Learning Consistent Representation for Soft Filter Pruning","created":"2023-12-17","cited_by_count":0,"area":null},{"id":"2403.00952","title":"MediSwift: Efficient Sparse Pre-trained Biomedical Language Models","created":"2024-03-01","cited_by_count":0,"area":null},{"id":"2403.08265","title":"Random Search as a Baseline for Sparse Neural Network Architecture Search","created":"2024-03-13","cited_by_count":0,"area":null},{"id":"2407.19644","title":"Realizing Unaligned Block-wise Pruning for DNN Acceleration on Mobile Devices","created":"2024-07-29","cited_by_count":0,"area":null},{"id":"2503.05761","title":"Geometric Properties and Graph-Based Optimization of Neural Networks: Addressing Non-Linearity, Dimensionality, and Scalability","created":"2025-02-24","cited_by_count":0,"area":null},{"id":"2606.14346","title":"Squeeze-Release: Iterative Pruning with Exact Structural Minimization","created":"2026-06-12","cited_by_count":0,"area":null}],"next_cursor":null}