{"list":"other","total":54,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800},{"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":"1707.06168","title":"Channel Pruning for Accelerating Very Deep Neural Networks","created":"2017-07-19","cited_by_count":702},{"id":"2305.11627","title":"LLM-Pruner: On the Structural Pruning of Large Language Models","created":"2023-05-19","cited_by_count":650},{"id":"2111.09832","title":"Merging Models with Fisher-Weighted Averaging","created":"2021-11-18","cited_by_count":621},{"id":"1608.03665","title":"Learning Structured Sparsity in Deep Neural Networks","created":"2016-08-12","cited_by_count":541},{"id":"1707.06342","title":"ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression","created":"2017-07-20","cited_by_count":442},{"id":"1912.08795","title":"Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion","created":"2019-12-18","cited_by_count":423},{"id":"2212.09849","title":"Dataless Knowledge Fusion by Merging Weights of Language Models","created":"2022-12-19","cited_by_count":387},{"id":"2401.15024","title":"SliceGPT: Compress Large Language Models by Deleting Rows and Columns","created":"2024-01-26","cited_by_count":385},{"id":"2403.03853","title":"ShortGPT: Layers in Large Language Models are More Redundant Than You Expect","created":"2024-03-06","cited_by_count":383},{"id":"1502.02551","title":"Deep Learning with Limited Numerical Precision","created":"2015-02-09","cited_by_count":376},{"id":"1705.09280","title":"Implicit Regularization in Matrix Factorization","created":"2017-05-25","cited_by_count":322},{"id":"2208.11580","title":"Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning","created":"2022-08-24","cited_by_count":322},{"id":"2110.06296","title":"The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks","created":"2021-10-12","cited_by_count":291},{"id":"1607.03250","title":"Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures","created":"2016-07-12","cited_by_count":221},{"id":"1511.07543","title":"Convergent Learning: Do different neural networks learn the same representations?","created":"2015-11-24","cited_by_count":220},{"id":"1910.05653","title":"Model Fusion via Optimal Transport","created":"2019-10-12","cited_by_count":219},{"id":"1702.03044","title":"Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights","created":"2017-02-10","cited_by_count":217},{"id":"1605.04711","title":"Ternary Weight Networks","created":"2016-05-16","cited_by_count":204},{"id":"1904.01186","title":"Data-Free Learning of Student Networks","created":"2019-04-02","cited_by_count":204},{"id":"1412.6553","title":"Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition","created":"2014-12-19","cited_by_count":203},{"id":"2305.03053","title":"ZipIt! Merging Models from Different Tasks without Training","created":"2023-05-04","cited_by_count":179},{"id":"1511.06530","title":"Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications","created":"2015-11-20","cited_by_count":162},{"id":"1905.09768","title":"Zero-shot Knowledge Transfer via Adversarial Belief Matching","created":"2019-05-23","cited_by_count":129},{"id":"2211.08403","title":"REPAIR: REnormalizing Permuted Activations for Interpolation Repair","created":"2022-11-15","cited_by_count":120},{"id":"2312.11983","title":"Fluctuation-based Adaptive Structured Pruning for Large Language Models","created":"2023-12-19","cited_by_count":111},{"id":"1912.11006","title":"Data-Free Adversarial Distillation","created":"2019-12-23","cited_by_count":90},{"id":"1805.09791","title":"Multi-Task Zipping via Layer-wise Neuron Sharing","created":"2018-05-24","cited_by_count":20},{"id":"2310.06756","title":"Going Beyond Neural Network Feature Similarity: The Network Feature Complexity and Its Interpretation Using Category Theory","created":"2023-10-10","cited_by_count":12},{"id":"1512.07548","title":"k-Means Clustering Is Matrix Factorization","created":"2015-12-23","cited_by_count":11},{"id":"2306.14152","title":"Low-Rank Prune-And-Factorize for Language Model Compression","created":"2023-06-25","cited_by_count":11},{"id":"2308.14929","title":"Maestro: Uncovering Low-Rank Structures via Trainable Decomposition","created":"2023-08-28","cited_by_count":8},{"id":"2402.07839","title":"Towards Meta-Pruning via Optimal Transport","created":"2024-02-12","cited_by_count":8},{"id":"1909.10364","title":"Class-dependent Compression of Deep Neural Networks","created":"2019-09-23","cited_by_count":7},{"id":"2202.04595","title":"Exploring Structural Sparsity in Neural Image Compression","created":"2022-02-09","cited_by_count":4},{"id":"2311.13349","title":"REDS: Resource-Efficient Deep Subnetworks for Dynamic Resource Constraints","created":"2023-11-22","cited_by_count":2},{"id":"2305.18953","title":"Sit Back and Relax: Learning to Drive Incrementally in All Weather Conditions","created":"2023-05-30","cited_by_count":1}],"next_cursor":null}