{"list":"other","total":66,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"2007.01434","title":"In Search of Lost Domain Generalization","created":"2020-07-02","cited_by_count":1054},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"1803.00567","title":"Computational Optimal Transport","created":"2018-03-01","cited_by_count":780},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"1710.01878","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","created":"2017-10-05","cited_by_count":603},{"id":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"2003.03033","title":"What is the State of Neural Network Pruning?","created":"2020-03-06","cited_by_count":583},{"id":"1712.00409","title":"Deep Learning Scaling is Predictable, Empirically","created":"2017-12-01","cited_by_count":582},{"id":"1902.09574","title":"The State of Sparsity in Deep Neural Networks","created":"2019-02-25","cited_by_count":476},{"id":"1805.11604","title":"How Does Batch Normalization Help Optimization?","created":"2018-05-29","cited_by_count":357},{"id":"2111.00364","title":"Sustainable AI: Environmental Implications, Challenges and Opportunities","created":"2021-10-30","cited_by_count":242},{"id":"1903.04064","title":"Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation","created":"2019-03-10","cited_by_count":235},{"id":"2105.02375","title":"A Geometric Analysis of Neural Collapse with Unconstrained Features","created":"2021-05-06","cited_by_count":227},{"id":"2403.17887","title":"The Unreasonable Ineffectiveness of the Deeper Layers","created":"2024-03-26","cited_by_count":226},{"id":"1811.05381","title":"Sorting out Lipschitz function approximation","created":"2018-11-13","cited_by_count":213},{"id":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203},{"id":"2308.06767","title":"A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations","created":"2023-08-13","cited_by_count":202},{"id":"1506.05439","title":"Learning with a Wasserstein Loss","created":"2015-06-17","cited_by_count":196},{"id":"1802.07191","title":"Neural Architecture Search with Bayesian Optimisation and Optimal Transport","created":"2018-02-11","cited_by_count":195},{"id":"1702.08811","title":"Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning","created":"2017-02-28","cited_by_count":192},{"id":"2402.11187","title":"LaCo: Large Language Model Pruning via Layer Collapse","created":"2024-02-17","cited_by_count":126},{"id":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","cited_by_count":122},{"id":"1904.05877","title":"Max-Sliced Wasserstein Distance and its use for GANs","created":"2019-04-11","cited_by_count":119},{"id":"1911.00937","title":"Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks","created":"2019-11-03","cited_by_count":87},{"id":"2003.05783","title":"Statistical and Topological Properties of Sliced Probability Divergences","created":"2020-03-12","cited_by_count":85},{"id":"1610.04161","title":"Why Deep Neural Networks for Function Approximation?","created":"2016-10-13","cited_by_count":82},{"id":"1905.10124","title":"Sliced Gromov-Wasserstein","created":"2019-05-24","cited_by_count":66},{"id":"2310.16228","title":"On the Foundations of Shortcut Learning","created":"2023-10-24","cited_by_count":65},{"id":"2012.08674","title":"Wasserstein Contrastive Representation Distillation","created":"2020-12-15","cited_by_count":64},{"id":"2103.03014","title":"Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy","created":"2021-03-04","cited_by_count":62},{"id":"1904.05408","title":"Sliced Wasserstein Generative Models","created":"2019-04-10","cited_by_count":61},{"id":"2001.01050","title":"Discrimination-aware Network Pruning for Deep Model Compression","created":"2020-01-04","cited_by_count":51},{"id":"2106.15427","title":"Fast Approximation of the Sliced-Wasserstein Distance Using Concentration of Random Projections","created":"2021-06-29","cited_by_count":33},{"id":"2104.05097","title":"Pay attention to your loss: understanding misconceptions about 1-Lipschitz neural networks","created":"2021-04-11","cited_by_count":30},{"id":"2006.07593","title":"Optimal Transport Kernels for Sequential and Parallel Neural Architecture Search","created":"2020-06-13","cited_by_count":29},{"id":"2103.07208","title":"In the light of feature distributions: moment matching for Neural Style Transfer","created":"2021-03-12","cited_by_count":26},{"id":"2108.07686","title":"Scaling Laws for Deep Learning","created":"2021-08-17","cited_by_count":26},{"id":"2302.05601","title":"Pruning Deep Neural Networks from a Sparsity Perspective","created":"2023-02-11","cited_by_count":25},{"id":"2308.06619","title":"Can Unstructured Pruning Reduce the Depth in Deep Neural Networks?","created":"2023-08-12","cited_by_count":20},{"id":"2011.09905","title":"LOss-Based SensiTivity rEgulaRization: towards deep sparse neural networks","created":"2020-11-16","cited_by_count":19},{"id":"2203.13417","title":"Amortized Projection Optimization for Sliced Wasserstein Generative Models","created":"2022-03-25","cited_by_count":17},{"id":"2106.09309","title":"Layer Folding: Neural Network Depth Reduction using Activation Linearization","created":"2021-06-17","cited_by_count":14},{"id":"2112.00423","title":"Controlling Wasserstein Distances by Kernel Norms with Application to Compressive Statistical Learning","created":"2021-12-01","cited_by_count":14},{"id":"2102.03773","title":"SeReNe: Sensitivity based Regularization of Neurons for Structured Sparsity in Neural Networks","created":"2021-02-07","cited_by_count":12},{"id":"2307.10352","title":"Properties of Discrete Sliced Wasserstein Losses","created":"2023-07-19","cited_by_count":12},{"id":"2009.08372","title":"A Principle of Least Action for the Training of Neural Networks","created":"2020-09-17","cited_by_count":8},{"id":"2012.03907","title":"Model Compression Using Optimal Transport","created":"2020-12-07","cited_by_count":8},{"id":"2102.09235","title":"Deep Residual Networks Learn the Geodesic Curve in the Wasserstein Space","created":"2021-02-18","cited_by_count":8},{"id":"2303.01213","title":"DSD$^2$: Can We Dodge Sparse Double Descent and Compress the Neural Network Worry-Free?","created":"2023-03-02","cited_by_count":6},{"id":"2211.17180","title":"Nonlinear Advantage: Trained Networks Might Not Be As Complex as You Think","created":"2022-11-30","cited_by_count":4},{"id":"2309.17357","title":"Module-wise Training of Neural Networks via the Minimizing Movement Scheme","created":"2023-09-29","cited_by_count":4},{"id":"2404.16890","title":"Layer Collapse Can be Induced by Unstructured Pruning","created":"2024-04-24","cited_by_count":4},{"id":"2404.18949","title":"The Simpler The Better: An Entropy-Based Importance Metric To Reduce Neural Networks' Depth","created":"2024-04-27","cited_by_count":3}],"next_cursor":null}