{"list":"other","total":61,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"1807.03039","title":"Glow: Generative Flow with Invertible 1x1 Convolutions","created":"2018-07-09","cited_by_count":1545},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135},{"id":"1410.8516","title":"NICE: Non-linear Independent Components Estimation","created":"2014-10-30","cited_by_count":1058},{"id":"1611.08097","title":"Geometric deep learning: going beyond Euclidean data","created":"2016-11-24","cited_by_count":1048},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"2011.04006","title":"Long Range Arena: A Benchmark for Efficient Transformers","created":"2020-11-08","cited_by_count":700},{"id":"2204.01697","title":"MaxViT: Multi-Axis Vision Transformer","created":"2022-04-04","cited_by_count":476},{"id":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471},{"id":"2105.08050","title":"Pay Attention to MLPs","created":"2021-05-17","cited_by_count":368},{"id":"1902.00275","title":"Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design","created":"2019-02-01","cited_by_count":262},{"id":"2204.07143","title":"Neighborhood Attention Transformer","created":"2022-04-14","cited_by_count":239},{"id":"1707.04585","title":"The Reversible Residual Network: Backpropagation Without Storing Activations","created":"2017-07-14","cited_by_count":217},{"id":"1703.02719","title":"Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network","created":"2017-03-08","cited_by_count":208},{"id":"2005.00743","title":"Synthesizer: Rethinking Self-Attention in Transformer Models","created":"2020-05-02","cited_by_count":205},{"id":"1909.00015","title":"Adaptively Sparse Transformers","created":"2019-08-30","cited_by_count":155},{"id":"2207.03620","title":"More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity","created":"2022-07-07","cited_by_count":142},{"id":"2006.10901","title":"Sparse GPU Kernels for Deep Learning","created":"2020-06-18","cited_by_count":141},{"id":"1802.07088","title":"i-RevNet: Deep Invertible Networks","created":"2018-02-20","cited_by_count":137},{"id":"2110.15343","title":"Scatterbrain: Unifying Sparse and Low-rank Attention Approximation","created":"2021-10-28","cited_by_count":130},{"id":"1804.06028","title":"ListOps: A Diagnostic Dataset for Latent Tree Learning","created":"2018-04-17","cited_by_count":129},{"id":"2106.02689","title":"RegionViT: Regional-to-Local Attention for Vision Transformers","created":"2021-06-04","cited_by_count":127},{"id":"2107.10224","title":"CycleMLP: A MLP-like Architecture for Dense Prediction","created":"2021-07-21","cited_by_count":126},{"id":"2204.00595","title":"Monarch: Expressive Structured Matrices for Efficient and Accurate Training","created":"2022-04-01","cited_by_count":106},{"id":"2106.12368","title":"Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition","created":"2021-06-23","cited_by_count":103},{"id":"2107.08391","title":"AS-MLP: An Axial Shifted MLP Architecture for Vision","created":"2021-07-18","cited_by_count":101},{"id":"1805.08315","title":"Learning long-range spatial dependencies with horizontal gated-recurrent units","created":"2018-05-21","cited_by_count":98},{"id":"2006.11469","title":"Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators","created":"2020-06-20","cited_by_count":85},{"id":"1903.05895","title":"Learning Fast Algorithms for Linear Transforms Using Butterfly Factorizations","created":"2019-03-14","cited_by_count":76},{"id":"2112.00029","title":"Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models","created":"2021-11-30","cited_by_count":76},{"id":"2108.13341","title":"Hire-MLP: Vision MLP via Hierarchical Rearrangement","created":"2021-08-30","cited_by_count":66},{"id":"2111.04060","title":"Are we ready for a new paradigm shift? A Survey on Visual Deep MLP","created":"2021-11-07","cited_by_count":63},{"id":"2111.12294","title":"An Image Patch is a Wave: Phase-Aware Vision MLP","created":"2021-11-24","cited_by_count":61},{"id":"2302.04869","title":"Reversible Vision Transformers","created":"2023-02-09","cited_by_count":33},{"id":"2209.09570","title":"Adaptable Butterfly Accelerator for Attention-based NNs via Hardware and Algorithm Co-design","created":"2022-09-20","cited_by_count":31},{"id":"2201.12083","title":"DynaMixer: A Vision MLP Architecture with Dynamic Mixing","created":"2022-01-28","cited_by_count":28},{"id":"2108.01072","title":"S$^2$-MLPv2: Improved Spatial-Shift MLP Architecture for Vision","created":"2021-08-02","cited_by_count":24},{"id":"1906.02256","title":"Butterfly Transform: An Efficient FFT Based Neural Architecture Design","created":"2019-06-05","cited_by_count":16},{"id":"2106.03959","title":"Generative Flows with Invertible Attentions","created":"2021-06-07","cited_by_count":13},{"id":"2203.13556","title":"Deformable Butterfly: A Highly Structured and Sparse Linear Transform","created":"2022-03-25","cited_by_count":8},{"id":"2202.06510","title":"Mixing and Shifting: Exploiting Global and Local Dependencies in Vision MLPs","created":"2022-02-14","cited_by_count":6},{"id":"2203.02358","title":"ViT-P: Rethinking Data-efficient Vision Transformers from Locality","created":"2022-03-04","cited_by_count":4},{"id":"2306.01470","title":"Understanding MLP-Mixer as a Wide and Sparse MLP","created":"2023-06-02","cited_by_count":3}],"next_cursor":null}