{"list":"other","total":63,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"1706.02690","title":"Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks","created":"2017-06-08","cited_by_count":1328},{"id":"1702.05464","title":"Adversarial Discriminative Domain Adaptation","created":"2017-02-17","cited_by_count":1311},{"id":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"id":"2003.00688","title":"Out-of-Distribution Generalization via Risk Extrapolation (REx)","created":"2020-03-02","cited_by_count":742},{"id":"2108.08810","title":"Do Vision Transformers See Like Convolutional Neural Networks?","created":"2021-08-19","cited_by_count":675},{"id":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644},{"id":"2201.02177","title":"Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets","created":"2022-01-06","cited_by_count":629},{"id":"1301.2115","title":"Domain Generalization via Invariant Feature Representation","created":"2013-01-10","cited_by_count":623},{"id":"2105.10497","title":"Intriguing Properties of Vision Transformers","created":"2021-05-21","cited_by_count":446},{"id":"2105.08050","title":"Pay Attention to MLPs","created":"2021-05-17","cited_by_count":368},{"id":"2105.03824","title":"FNet: Mixing Tokens with Fourier Transforms","created":"2021-05-09","cited_by_count":347},{"id":"1909.03683","title":"Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases","created":"2019-09-09","cited_by_count":280},{"id":"2006.04315","title":"Counterfactual VQA: A Cause-Effect Look at Language Bias","created":"2020-06-08","cited_by_count":266},{"id":"2010.05761","title":"The Risks of Invariant Risk Minimization","created":"2020-10-12","cited_by_count":262},{"id":"1812.10352","title":"Learning Not to Learn: Training Deep Neural Networks with Biased Data","created":"2018-12-26","cited_by_count":255},{"id":"1703.07326","title":"One-Shot Imitation Learning","created":"2017-03-21","cited_by_count":233},{"id":"1909.10893","title":"Recurrent Independent Mechanisms","created":"2019-09-24","cited_by_count":219},{"id":"2105.07581","title":"Vision Transformers are Robust Learners","created":"2021-05-17","cited_by_count":207},{"id":"2201.09792","title":"Patches Are All You Need?","created":"2022-01-24","cited_by_count":201},{"id":"2111.05464","title":"Are Transformers More Robust Than CNNs?","created":"2021-11-10","cited_by_count":187},{"id":"2006.04439","title":"Liquid Time-constant Networks","created":"2020-06-08","cited_by_count":161},{"id":"2209.12951","title":"Liquid Structural State-Space Models","created":"2022-09-26","cited_by_count":136},{"id":"1611.01353","title":"Information Dropout: Learning Optimal Representations Through Noisy Computation","created":"2016-11-04","cited_by_count":132},{"id":"1903.06256","title":"Learning Robust Representations by Projecting Superficial Statistics Out","created":"2019-03-02","cited_by_count":123},{"id":"1901.09387","title":"Imitation Learning from Imperfect Demonstration","created":"2019-01-27","cited_by_count":114},{"id":"2103.03493","title":"Causal Attention for Vision-Language Tasks","created":"2021-03-05","cited_by_count":111},{"id":"2103.00887","title":"Counterfactual Zero-Shot and Open-Set Visual Recognition","created":"2021-03-01","cited_by_count":95},{"id":"1803.00590","title":"Hierarchical Imitation and Reinforcement Learning","created":"2018-03-01","cited_by_count":88},{"id":"2006.04418","title":"Learning Long-Term Dependencies in Irregularly-Sampled Time Series","created":"2020-06-08","cited_by_count":83},{"id":"2111.12083","title":"VISTA 2.0: An Open, Data-driven Simulator for Multimodal Sensing and Policy Learning for Autonomous Vehicles","created":"2021-11-23","cited_by_count":81},{"id":"2108.08782","title":"Causal Attention for Unbiased Visual Recognition","created":"2021-08-19","cited_by_count":80},{"id":"2110.10819","title":"Shaking the foundations: delusions in sequence models for interaction and control","created":"2021-10-20","cited_by_count":62},{"id":"2203.08392","title":"Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?","created":"2022-03-16","cited_by_count":49},{"id":"2105.08710","title":"Fast and Slow Learning of Recurrent Independent Mechanisms","created":"2021-05-18","cited_by_count":36},{"id":"1810.11043","title":"One-Shot Hierarchical Imitation Learning of Compound Visuomotor Tasks","created":"2018-10-25","cited_by_count":33},{"id":"2103.04909","title":"Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing","created":"2021-03-08","cited_by_count":26},{"id":"2106.08314","title":"Causal Navigation by Continuous-time Neural Networks","created":"2021-06-15","cited_by_count":23},{"id":"2103.08187","title":"Adversarial Training is Not Ready for Robot Learning","created":"2021-03-15","cited_by_count":20},{"id":"1905.12310","title":"Adversarial Imitation Learning from Incomplete Demonstrations","created":"2019-05-29","cited_by_count":16},{"id":"2111.11277","title":"BarrierNet: A Safety-Guaranteed Layer for Neural Networks","created":"2021-11-22","cited_by_count":12},{"id":"1809.03864","title":"Response Characterization for Auditing Cell Dynamics in Long Short-term Memory Networks","created":"2018-09-11","cited_by_count":10},{"id":"2203.02401","title":"Differentiable Control Barrier Functions for Vision-based End-to-End Autonomous Driving","created":"2022-03-04","cited_by_count":10},{"id":"2206.01261","title":"Entangled Residual Mappings","created":"2022-06-02","cited_by_count":4}],"next_cursor":null}