{"total":127,"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":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2310.05175","title":"Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity","created":"2023-10-08","cited_by_count":165,"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":"2110.15343","title":"Scatterbrain: Unifying Sparse and Low-rank Attention Approximation","created":"2021-10-28","cited_by_count":130,"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":"2110.12894","title":"The Efficiency Misnomer","created":"2021-10-25","cited_by_count":98,"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":"2202.07471","title":"SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation","created":"2022-02-14","cited_by_count":55,"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":"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":"2207.04606","title":"SparseTIR: Composable Abstractions for Sparse Compilation in Deep Learning","created":"2022-07-11","cited_by_count":47,"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":"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":"2410.10912","title":"AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models","created":"2024-10-14","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":"2301.10936","title":"PIT: Optimization of Dynamic Sparse Deep Learning Models via Permutation Invariant Transformation","created":"2023-01-26","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":"2306.11197","title":"Sparse Modular Activation for Efficient Sequence Modeling","created":"2023-06-19","cited_by_count":20,"area":null},{"id":"2110.11299","title":"Transformer Acceleration with Dynamic Sparse Attention","created":"2021-10-21","cited_by_count":19,"area":null},{"id":"2212.00824","title":"On-device Training: A First Overview on Existing Systems","created":"2022-12-01","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":"2110.10221","title":"The CoRa Tensor Compiler: Compilation for Ragged Tensors with Minimal Padding","created":"2021-10-19","cited_by_count":17,"area":null},{"id":"2309.10285","title":"Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity","created":"2023-09-19","cited_by_count":17,"area":null},{"id":"2405.02596","title":"Random Masking Finds Winning Tickets for Parameter Efficient Fine-tuning","created":"2024-05-04","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":"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":"2209.06979","title":"Efficient Quantized Sparse Matrix Operations on Tensor Cores","created":"2022-09-14","cited_by_count":16,"area":null},{"id":"2112.13896","title":"Two Sparsities Are Better Than One: Unlocking the Performance Benefits of Sparse-Sparse Networks","created":"2021-12-27","cited_by_count":15,"area":null},{"id":"2403.15173","title":"LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels","created":"2024-03-22","cited_by_count":15,"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":"2310.02065","title":"VENOM: A Vectorized N:M Format for Unleashing the Power of Sparse Tensor Cores","created":"2023-10-03","cited_by_count":13,"area":null},{"id":"2103.00959","title":"CogDL: A Comprehensive Library for Graph Deep Learning","created":"2021-03-01","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":"2401.04829","title":"GNNShap: Scalable and Accurate GNN Explanation using Shapley Values","created":"2024-01-09","cited_by_count":12,"area":null},{"id":"2212.11142","title":"BaCO: A Fast and Portable Bayesian Compiler Optimization Framework","created":"2022-12-01","cited_by_count":11,"area":null},{"id":"2303.11934","title":"Sparse Distributed Memory is a Continual Learner","created":"2023-03-20","cited_by_count":11,"area":null},{"id":"2108.09376","title":"BlockCopy: High-Resolution Video Processing with Block-Sparse Feature Propagation and Online Policies","created":"2021-08-20","cited_by_count":9,"area":null},{"id":"2305.14135","title":"Reparo: Loss-Resilient Generative Codec for Video Conferencing","created":"2023-05-23","cited_by_count":8,"area":null},{"id":"2203.02549","title":"Structured Pruning is All You Need for Pruning CNNs at Initialization","created":"2022-03-04","cited_by_count":7,"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":"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":"2409.18850","title":"Two Sparse Matrices are Better than One: Sparsifying Neural Networks with Double Sparse Factorization","created":"2024-09-27","cited_by_count":6,"area":null},{"id":"2508.02932","title":"PLoRA: Efficient Concurrent LoRA Training for Large Language Models","created":"2025-08-04","cited_by_count":6,"area":null},{"id":"2511.13061","title":"MACKO: Sparse Matrix-Vector Multiplication for Low Sparsity","created":"2025-11-17","cited_by_count":6,"area":null},{"id":"2107.07110","title":"Compact and Optimal Deep Learning with Recurrent Parameter Generators","created":"2021-07-15","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":"2207.07338","title":"Context-sensitive neocortical neurons transform the effectiveness and efficiency of neural information processing","created":"2022-07-15","cited_by_count":5,"area":null},{"id":"2211.01950","title":"Unlocking the potential of two-point cells for energy-efficient and resilient training of deep nets","created":"2022-10-24","cited_by_count":5,"area":null},{"id":"2302.05045","title":"Exploiting Sparsity in Pruned Neural Networks to Optimize Large Model Training","created":"2023-02-10","cited_by_count":5,"area":null},{"id":"2308.12093","title":"Cached Operator Reordering: A Unified View for Fast GNN Training","created":"2023-08-23","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":"2407.16847","title":"SPLAT: A framework for optimised GPU code-generation for SParse reguLar ATtention","created":"2024-07-23","cited_by_count":5,"area":null},{"id":"2410.19274","title":"Neuralink: Fast LLM Inference on Smartphones with Neuron Co-Activation Linking","created":"2024-10-25","cited_by_count":5,"area":null},{"id":"2103.05600","title":"unzipFPGA: Enhancing FPGA-based CNN Engines with On-the-Fly Weights Generation","created":"2021-03-09","cited_by_count":4,"area":null},{"id":"2208.03559","title":"Triple Sparsification of Graph Convolutional Networks without Sacrificing the Accuracy","created":"2022-08-06","cited_by_count":4,"area":null},{"id":"2302.07612","title":"Towards Optimal Compression: Joint Pruning and Quantization","created":"2023-02-15","cited_by_count":4,"area":null},{"id":"2311.04386","title":"Harnessing Manycore Processors with Distributed Memory for Accelerated Training of Sparse and Recurrent Models","created":"2023-11-07","cited_by_count":4,"area":null},{"id":"2104.06357","title":"GPU Semiring Primitives for Sparse Neighborhood Methods","created":"2021-04-13","cited_by_count":3,"area":null},{"id":"2105.12920","title":"Search Spaces for Neural Model Training","created":"2021-05-27","cited_by_count":3,"area":null},{"id":"2205.14014","title":"What Dense Graph Do You Need for Self-Attention?","created":"2022-05-27","cited_by_count":3,"area":null},{"id":"2301.13376","title":"Quantized Neural Networks for Low-Precision Accumulation with Guaranteed Overflow Avoidance","created":"2023-01-31","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":"2402.16731","title":"PyGim: An Efficient Graph Neural Network Library for Real Processing-In-Memory Architectures","created":"2024-02-26","cited_by_count":3,"area":null},{"id":"2404.04118","title":"GNNBENCH: Fair and Productive Benchmarking for Single-GPU GNN System","created":"2024-04-05","cited_by_count":3,"area":null},{"id":"2411.03171","title":"Navigating Extremes: Dynamic Sparsity in Large Output Spaces","created":"2024-11-05","cited_by_count":3,"area":null},{"id":"2412.11007","title":"FlashSparse: Minimizing Computation Redundancy for Fast Sparse Matrix Multiplications on Tensor Cores","created":"2024-12-15","cited_by_count":3,"area":null},{"id":"2505.09361","title":"Efficient Mixed Precision Quantization in Graph Neural Networks","created":"2025-05-14","cited_by_count":3,"area":null},{"id":"2603.17484","title":"Learning When to Attend: Conditional Memory Access for Long-Context LLMs","created":"2026-03-18","cited_by_count":3,"area":null},{"id":"2104.10716","title":"Accelerating SpMM Kernel with Cache-First Edge Sampling for Graph Neural Networks","created":"2021-04-21","cited_by_count":2,"area":null},{"id":"2107.07305","title":"Training for temporal sparsity in deep neural networks, application in video processing","created":"2021-07-15","cited_by_count":2,"area":null},{"id":"2204.09917","title":"SinTra: Learning an inspiration model from a single multi-track music segment","created":"2022-04-21","cited_by_count":2,"area":null},{"id":"2207.01260","title":"CPrune: Compiler-Informed Model Pruning for Efficient Target-Aware DNN Execution","created":"2022-07-04","cited_by_count":2,"area":null},{"id":"2209.05683","title":"One-shot Network Pruning at Initialization with Discriminative Image Patches","created":"2022-09-13","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":"2503.09184","title":"Exploiting Unstructured Sparsity in Fully Homomorphic Encrypted DNNs","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2505.08098","title":"Fused3S: Fast Sparse Attention on Tensor Cores","created":"2025-05-12","cited_by_count":2,"area":null},{"id":"2505.24037","title":"Leave it to the Specialist: Repair Sparse LLMs with Sparse Fine-Tuning via Sparsity Evolution","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2510.15964","title":"Long Exposure: Accelerating Parameter-Efficient Fine-Tuning for LLMs under Shadowy Sparsity","created":"2025-10-12","cited_by_count":2,"area":null},{"id":"2601.06562","title":"Mosaic: Unlocking Long-Context Inference for Diffusion LLMs via Global Memory Planning and Dynamic Peak Taming","created":"2026-01-10","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":"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":"2207.09955","title":"Operation-Level Performance Benchmarking of Graph Neural Networks for Scientific Applications","created":"2022-07-20","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":"2304.07613","title":"STen: Productive and Efficient Sparsity in PyTorch","created":"2023-04-15","cited_by_count":1,"area":null},{"id":"2306.10388","title":"Breaking On-device Training Memory Wall: A Systematic Survey","created":"2023-06-17","cited_by_count":1,"area":null},{"id":"2307.13412","title":"Mitigating Memory Wall Effects in CNN Engines with On-the-Fly Weights Generation","created":"2023-07-25","cited_by_count":1,"area":null},{"id":"2310.00496","title":"The Sparsity Roofline: Understanding the Hardware Limits of Sparse Neural Networks","created":"2023-09-30","cited_by_count":1,"area":null},{"id":"2311.00368","title":"Performance Optimization of Deep Learning Sparse Matrix Kernels on Intel Max Series GPU","created":"2023-11-01","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":"2405.16883","title":"Scorch: A Library for Sparse Deep Learning","created":"2024-05-27","cited_by_count":1,"area":null},{"id":"2409.18324","title":"Input-Dependent Power Usage in GPUs","created":"2024-09-26","cited_by_count":1,"area":null},{"id":"2411.01109","title":"Optimization of GNN Training Through Half-precision","created":"2024-11-02","cited_by_count":1,"area":null},{"id":"2502.11439","title":"An Efficient Sparse Fine-Tuning with Low Quantization Error via Neural Network Pruning","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2506.22714","title":"Libra: Unleashing GPU Heterogeneity for High-Performance Sparse Matrix Multiplication","created":"2025-06-28","cited_by_count":1,"area":null}],"next_cursor":"100"}