{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"1908.09791","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","created":"2019-08-26","cited_by_count":787},{"id":"2305.11627","title":"LLM-Pruner: On the Structural Pruning of Large Language Models","created":"2023-05-19","cited_by_count":650},{"id":"1608.03665","title":"Learning Structured Sparsity in Deep Neural Networks","created":"2016-08-12","cited_by_count":541},{"id":"1902.09574","title":"The State of Sparsity in Deep Neural Networks","created":"2019-02-25","cited_by_count":476},{"id":"2401.15024","title":"SliceGPT: Compress Large Language Models by Deleting Rows and Columns","created":"2024-01-26","cited_by_count":385},{"id":"1802.03494","title":"AMC: AutoML for Model Compression and Acceleration on Mobile Devices","created":"2018-02-10","cited_by_count":378},{"id":"1808.06866","title":"Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks","created":"2018-08-21","cited_by_count":315},{"id":"1803.08664","title":"Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network","created":"2018-03-23","cited_by_count":264},{"id":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203},{"id":"1707.01213","title":"Data-Driven Sparse Structure Selection for Deep Neural Networks","created":"2017-07-05","cited_by_count":181},{"id":"2109.04838","title":"Block Pruning For Faster Transformers","created":"2021-09-10","cited_by_count":177},{"id":"2204.00408","title":"Structured Pruning Learns Compact and Accurate Models","created":"2022-04-01","cited_by_count":170},{"id":"1808.07233","title":"Neural Architecture Optimization","created":"2018-08-22","cited_by_count":167},{"id":"2402.03898","title":"DistiLLM: Towards Streamlined Distillation for Large Language Models","created":"2024-02-06","cited_by_count":163},{"id":"1909.08174","title":"Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networks","created":"2019-09-18","cited_by_count":118},{"id":"2005.07093","title":"Bayesian Bits: Unifying Quantization and Pruning","created":"2020-05-14","cited_by_count":94},{"id":"2007.03260","title":"ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgetting","created":"2020-07-07","cited_by_count":85},{"id":"2007.02491","title":"EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning","created":"2020-07-06","cited_by_count":80},{"id":"2003.05643","title":"Highly Efficient Salient Object Detection with 100K Parameters","created":"2020-03-12","cited_by_count":79},{"id":"2003.08935","title":"Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression","created":"2020-03-19","cited_by_count":72},{"id":"2107.07467","title":"Only Train Once: A One-Shot Neural Network Training And Pruning Framework","created":"2021-07-15","cited_by_count":70},{"id":"1908.09979","title":"DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measures","created":"2019-08-27","cited_by_count":56},{"id":"2009.14410","title":"Pruning Filter in Filter","created":"2020-09-30","cited_by_count":47},{"id":"2310.18356","title":"LoRAShear: Efficient Large Language Model Structured Pruning and Knowledge Recovery","created":"2023-10-24","cited_by_count":38},{"id":"1910.14488","title":"NAT: Neural Architecture Transformer for Accurate and Compact Architectures","created":"2019-10-31","cited_by_count":33},{"id":"2303.06862","title":"OTOV2: Automatic, Generic, User-Friendly","created":"2023-03-13","cited_by_count":32},{"id":"1812.00353","title":"Accelerate CNN via Recursive Bayesian Pruning","created":"2018-12-02","cited_by_count":27},{"id":"2312.00678","title":"The Efficiency Spectrum of Large Language Models: An Algorithmic Survey","created":"2023-12-01","cited_by_count":26},{"id":"2004.03639","title":"Orthant Based Proximal Stochastic Gradient Method for $\\ell_1$-Regularized Optimization","created":"2020-04-07","cited_by_count":20},{"id":"2403.14729","title":"Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch","created":"2024-03-21","cited_by_count":20},{"id":"2102.03869","title":"Structured Sparsity Inducing Adaptive Optimizers for Deep Learning","created":"2021-02-07","cited_by_count":17},{"id":"2011.04868","title":"Neural Network Compression Via Sparse Optimization","created":"2020-11-10","cited_by_count":13},{"id":"1907.11845","title":"Generative Adversarial Network for Handwritten Text","created":"2019-07-27","cited_by_count":12},{"id":"2312.00210","title":"DREAM: Diffusion Rectification and Estimation-Adaptive Models","created":"2023-11-30","cited_by_count":12},{"id":"2311.15510","title":"CaesarNeRF: Calibrated Semantic Representation for Few-shot Generalizable Neural Rendering","created":"2023-11-27","cited_by_count":10},{"id":"2403.18955","title":"Structurally Prune Anything: Any Architecture, Any Framework, Any Time","created":"2024-03-03","cited_by_count":8},{"id":"1602.07018","title":"A Reduced-Space Algorithm for Minimizing $\\ell_1$-Regularized Convex Functions","created":"2016-02-23","cited_by_count":7},{"id":"2009.12078","title":"Half-Space Proximal Stochastic Gradient Method for Group-Sparsity Regularized Problem","created":"2020-09-25","cited_by_count":7},{"id":"2310.10054","title":"NASH: A Simple Unified Framework of Structured Pruning for Accelerating Encoder-Decoder Language Models","created":"2023-10-16","cited_by_count":7},{"id":"2312.09411","title":"OTOv3: Automatic Architecture-Agnostic Neural Network Training and Compression from Structured Pruning to Erasing Operators","created":"2023-12-15","cited_by_count":6},{"id":"2009.08169","title":"Holistic Filter Pruning for Efficient Deep Neural Networks","created":"2020-09-17","cited_by_count":4},{"id":"2404.08016","title":"ONNXPruner: ONNX-Based General Model Pruning Adapter","created":"2024-04-10","cited_by_count":3}],"next_cursor":null}