{"list":"other","total":86,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1505.05770","title":"Variational Inference with Normalizing Flows","created":"2015-05-21","cited_by_count":2170},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"1811.12359","title":"Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations","created":"2018-11-29","cited_by_count":941},{"id":"1906.01563","title":"Hamiltonian Neural Networks","created":"2019-06-04","cited_by_count":712},{"id":"1606.04934","title":"Improving Variational Inference with Inverse Autoregressive Flow","created":"2016-06-15","cited_by_count":640},{"id":"2007.03898","title":"NVAE: A Deep Hierarchical Variational Autoencoder","created":"2020-07-08","cited_by_count":637},{"id":"1711.09577","title":"Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?","created":"2017-11-27","cited_by_count":551},{"id":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"id":"1612.00222","title":"Interaction Networks for Learning about Objects, Relations and Physics","created":"2016-12-01","cited_by_count":509},{"id":"1502.04681","title":"Unsupervised Learning of Video Representations using LSTMs","created":"2015-02-16","cited_by_count":435},{"id":"1904.11486","title":"Making Convolutional Networks Shift-Invariant Again","created":"2019-04-25","cited_by_count":391},{"id":"1810.09538","title":"Pyro: Deep Universal Probabilistic Programming","created":"2018-10-18","cited_by_count":380},{"id":"1609.02612","title":"Generating Videos with Scene Dynamics","created":"2016-09-08","cited_by_count":376},{"id":"1506.02216","title":"A Recurrent Latent Variable Model for Sequential Data","created":"2015-06-07","cited_by_count":362},{"id":"1905.01164","title":"SinGAN: Learning a Generative Model from a Single Natural Image","created":"2019-05-02","cited_by_count":348},{"id":"1608.06019","title":"Domain Separation Networks","created":"2016-08-22","cited_by_count":320},{"id":"1511.05440","title":"Deep multi-scale video prediction beyond mean square error","created":"2015-11-17","cited_by_count":300},{"id":"1812.02230","title":"Towards a Definition of Disentangled Representations","created":"2018-12-05","cited_by_count":296},{"id":"1312.4314","title":"Learning Factored Representations in a Deep Mixture of Experts","created":"2013-12-16","cited_by_count":278},{"id":"1506.07365","title":"Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images","created":"2015-06-24","cited_by_count":274},{"id":"2002.02886","title":"Weakly-Supervised Disentanglement Without Compromises","created":"2020-02-07","cited_by_count":239},{"id":"1802.03446","title":"Pros and Cons of GAN Evaluation Measures","created":"2018-02-09","cited_by_count":224},{"id":"1511.00830","title":"The Variational Fair Autoencoder","created":"2015-11-03","cited_by_count":223},{"id":"1603.08575","title":"Attend, Infer, Repeat: Fast Scene Understanding with Generative Models","created":"2016-03-28","cited_by_count":209},{"id":"1812.08861","title":"Animating Arbitrary Objects via Deep Motion Transfer","created":"2018-12-20","cited_by_count":208},{"id":"1611.06624","title":"Temporal Generative Adversarial Nets with Singular Value Clipping","created":"2016-11-21","cited_by_count":198},{"id":"1906.02589","title":"Flexibly Fair Representation Learning by Disentanglement","created":"2019-06-06","cited_by_count":196},{"id":"1903.05789","title":"Diagnosing and Enhancing VAE Models","created":"2019-03-14","cited_by_count":193},{"id":"1906.02634","title":"Scaling Autoregressive Video Models","created":"2019-06-06","cited_by_count":190},{"id":"1609.09869","title":"Structured Inference Networks for Nonlinear State Space Models","created":"2016-09-30","cited_by_count":182},{"id":"1511.05121","title":"Deep Kalman Filters","created":"2015-11-16","cited_by_count":166},{"id":"1905.13662","title":"On the Fairness of Disentangled Representations","created":"2019-05-31","cited_by_count":144},{"id":"1705.10915","title":"Unsupervised Learning of Disentangled Representations from Video","created":"2017-05-31","cited_by_count":139},{"id":"1909.13789","title":"Hamiltonian Generative Networks","created":"2019-09-30","cited_by_count":137},{"id":"1806.01794","title":"Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects","created":"2018-06-05","cited_by_count":128},{"id":"1806.04166","title":"Learning to Decompose and Disentangle Representations for Video Prediction","created":"2018-06-11","cited_by_count":121},{"id":"1803.02991","title":"Disentangled Sequential Autoencoder","created":"2018-03-08","cited_by_count":120},{"id":"1605.07571","title":"Sequential Neural Models with Stochastic Layers","created":"2016-05-24","cited_by_count":115},{"id":"1905.10427","title":"DIVA: Domain Invariant Variational Autoencoders","created":"2019-05-24","cited_by_count":115},{"id":"1805.09458","title":"Invariant Representations without Adversarial Training","created":"2018-05-24","cited_by_count":112},{"id":"1610.00527","title":"Video Pixel Networks","created":"2016-10-03","cited_by_count":108},{"id":"1710.05741","title":"A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning","created":"2017-10-16","cited_by_count":107},{"id":"2006.10704","title":"Latent Video Transformer","created":"2020-06-18","cited_by_count":106},{"id":"1712.00961","title":"Learning Independent Causal Mechanisms","created":"2017-12-04","cited_by_count":105},{"id":"2010.00654","title":"VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models","created":"2020-10-01","cited_by_count":104},{"id":"1705.08841","title":"Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observations","created":"2017-05-24","cited_by_count":100},{"id":"1709.07902","title":"Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data","created":"2017-09-22","cited_by_count":93},{"id":"1910.09772","title":"Weakly Supervised Disentanglement with Guarantees","created":"2019-10-22","cited_by_count":82},{"id":"1706.00400","title":"Learning Disentangled Representations with Semi-Supervised Deep Generative Models","created":"2017-06-01","cited_by_count":72},{"id":"2005.11437","title":"S3VAE: Self-Supervised Sequential VAE for Representation Disentanglement and Data Generation","created":"2020-05-23","cited_by_count":63},{"id":"1411.7610","title":"Learning Stochastic Recurrent Networks","created":"2014-11-27","cited_by_count":60},{"id":"1809.09087","title":"Implicit Maximum Likelihood Estimation","created":"2018-09-24","cited_by_count":52},{"id":"1711.05411","title":"Z-Forcing: Training Stochastic Recurrent Networks","created":"2017-11-15","cited_by_count":51},{"id":"1812.03253","title":"Counterfactuals uncover the modular structure of deep generative models","created":"2018-12-08","cited_by_count":51},{"id":"1806.03107","title":"Temporal Difference Variational Auto-Encoder","created":"2018-06-08","cited_by_count":49},{"id":"1910.02425","title":"Structured Object-Aware Physics Prediction for Video Modeling and Planning","created":"2019-10-06","cited_by_count":43},{"id":"1912.12773","title":"Learning Predictive Models From Observation and Interaction","created":"2019-12-30","cited_by_count":41},{"id":"1810.02419","title":"Towards High Resolution Video Generation with Progressive Growing of Sliced Wasserstein GANs","created":"2018-10-04","cited_by_count":36},{"id":"1906.11796","title":"Demystifying Inter-Class Disentanglement","created":"2019-06-27","cited_by_count":31},{"id":"1806.09655","title":"Learning what you can do before doing anything","created":"2018-06-25","cited_by_count":26},{"id":"1902.06568","title":"STCN: Stochastic Temporal Convolutional Networks","created":"2019-02-18","cited_by_count":26},{"id":"1803.08085","title":"Probabilistic Video Generation using Holistic Attribute Control","created":"2018-03-21","cited_by_count":24},{"id":"1612.05299","title":"A Survey of Inductive Biases for Factorial Representation-Learning","created":"2016-12-15","cited_by_count":23},{"id":"1906.01044","title":"Weakly Supervised Disentanglement by Pairwise Similarities","created":"2019-06-03","cited_by_count":22},{"id":"1901.08651","title":"Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based robotics","created":"2019-01-24","cited_by_count":21},{"id":"1808.10002","title":"Interpretable Intuitive Physics Model","created":"2018-08-29","cited_by_count":19},{"id":"1905.12434","title":"Switching Linear Dynamics for Variational Bayes Filtering","created":"2019-05-29","cited_by_count":17},{"id":"2001.05017","title":"Emerging Disentanglement in Auto-Encoder Based Unsupervised Image Content Transfer","created":"2020-01-14","cited_by_count":15},{"id":"1906.03255","title":"Disentangled State Space Representations","created":"2019-06-07","cited_by_count":14},{"id":"1908.03918","title":"DynaNet: Neural Kalman Dynamical Model for Motion Estimation and Prediction","created":"2019-08-11","cited_by_count":13},{"id":"2002.11576","title":"NestedVAE: Isolating Common Factors via Weak Supervision","created":"2020-02-26","cited_by_count":13},{"id":"2010.03172","title":"Improving Sequential Latent Variable Models with Autoregressive Flows","created":"2020-10-07","cited_by_count":8},{"id":"1911.06443","title":"Gated Variational AutoEncoders: Incorporating Weak Supervision to Encourage Disentanglement","created":"2019-11-15","cited_by_count":6},{"id":"1612.04440","title":"Disentangling Space and Time in Video with Hierarchical Variational Auto-encoders","created":"2016-12-14","cited_by_count":4},{"id":"1910.06205","title":"Variational Tracking and Prediction with Generative Disentangled State-Space Models","created":"2019-10-14","cited_by_count":2}],"next_cursor":null}