{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"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":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"1611.08097","title":"Geometric deep learning: going beyond Euclidean data","created":"2016-11-24","cited_by_count":1048},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1410.5401","title":"Neural Turing Machines","created":"2014-10-20","cited_by_count":644},{"id":"1603.00831","title":"MOT16: A Benchmark for Multi-Object Tracking","created":"2016-03-02","cited_by_count":532},{"id":"1612.00222","title":"Interaction Networks for Learning about Objects, Relations and Physics","created":"2016-12-01","cited_by_count":509},{"id":"1901.11390","title":"MONet: Unsupervised Scene Decomposition and Representation","created":"2019-01-22","cited_by_count":392},{"id":"1511.02799","title":"Neural Module Networks","created":"2015-11-09","cited_by_count":376},{"id":"1701.08734","title":"PathNet: Evolution Channels Gradient Descent in Super Neural Networks","created":"2017-01-30","cited_by_count":364},{"id":"1903.00450","title":"Multi-Object Representation Learning with Iterative Variational Inference","created":"2019-03-01","cited_by_count":360},{"id":"1802.04687","title":"Neural Relational Inference for Interacting Systems","created":"2018-02-13","cited_by_count":339},{"id":"2003.13350","title":"Agent57: Outperforming the Atari Human Benchmark","created":"2020-03-30","cited_by_count":303},{"id":"2011.15091","title":"Inductive Biases for Deep Learning of Higher-Level Cognition","created":"2020-11-30","cited_by_count":275},{"id":"1907.13052","title":"GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations","created":"2019-07-30","cited_by_count":227},{"id":"1909.10893","title":"Recurrent Independent Mechanisms","created":"2019-09-24","cited_by_count":219},{"id":"1603.08575","title":"Attend, Infer, Repeat: Fast Scene Understanding with Generative Models","created":"2016-03-28","cited_by_count":209},{"id":"1911.12247","title":"Contrastive Learning of Structured World Models","created":"2019-11-27","cited_by_count":209},{"id":"1806.01794","title":"Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects","created":"2018-06-05","cited_by_count":128},{"id":"1711.01239","title":"Routing Networks: Adaptive Selection of Non-linear Functions for Multi-Task Learning","created":"2017-11-03","cited_by_count":126},{"id":"1910.12827","title":"Entity Abstraction in Visual Model-Based Reinforcement Learning","created":"2019-10-28","cited_by_count":110},{"id":"2010.04296","title":"CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning","created":"2020-10-08","cited_by_count":109},{"id":"1709.08568","title":"The Consciousness Prior","created":"2017-09-25","cited_by_count":107},{"id":"1511.06279","title":"Neural Programmer-Interpreters","created":"2015-11-19","cited_by_count":101},{"id":"1802.10353","title":"Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions","created":"2018-02-28","cited_by_count":100},{"id":"1706.01433","title":"Visual Interaction Networks","created":"2017-06-05","cited_by_count":95},{"id":"1805.04276","title":"Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis","created":"2018-05-11","cited_by_count":84},{"id":"1901.10902","title":"InfoBot: Transfer and Exploration via the Information Bottleneck","created":"2019-01-30","cited_by_count":78},{"id":"1710.01813","title":"Neural Task Programming: Learning to Generalize Across Hierarchical Tasks","created":"2017-10-04","cited_by_count":76},{"id":"1808.00508","title":"Neural Arithmetic Logic Units","created":"2018-08-01","cited_by_count":70},{"id":"1606.06724","title":"Tagger: Deep Unsupervised Perceptual Grouping","created":"2016-06-21","cited_by_count":69},{"id":"1811.05249","title":"Modular Networks: Learning to Decompose Neural Computation","created":"2018-11-13","cited_by_count":62},{"id":"1804.08018","title":"ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stacking","created":"2018-04-21","cited_by_count":55},{"id":"1904.12774","title":"Routing Networks and the Challenges of Modular and Compositional Computation","created":"2019-04-29","cited_by_count":50},{"id":"2006.16225","title":"Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems","created":"2020-06-29","cited_by_count":48},{"id":"2008.02265","title":"Learning Long-term Visual Dynamics with Region Proposal Interaction Networks","created":"2020-08-05","cited_by_count":44},{"id":"2010.14274","title":"Behavior Priors for Efficient Reinforcement Learning","created":"2020-10-27","cited_by_count":41},{"id":"1704.06611","title":"Making Neural Programming Architectures Generalize via Recursion","created":"2017-04-21","cited_by_count":35},{"id":"1511.04834","title":"Neural Programmer: Inducing Latent Programs with Gradient Descent","created":"2015-11-16","cited_by_count":34},{"id":"1910.02227","title":"Making sense of sensory input","created":"2019-10-05","cited_by_count":29},{"id":"2007.12348","title":"Unsupervised Discovery of 3D Physical Objects from Video","created":"2020-07-24","cited_by_count":27},{"id":"1809.03137","title":"Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackers","created":"2018-09-10","cited_by_count":22},{"id":"1809.11044","title":"Relational Forward Models for Multi-Agent Learning","created":"2018-09-28","cited_by_count":21},{"id":"1702.05068","title":"Discovering objects and their relations from entangled scene representations","created":"2017-02-16","cited_by_count":12},{"id":"2006.14727","title":"Unsupervised Video Decomposition using Spatio-temporal Iterative Inference","created":"2020-06-25","cited_by_count":12},{"id":"2007.03629","title":"Strong Generalization and Efficiency in Neural Programs","created":"2020-07-07","cited_by_count":12},{"id":"2007.06533","title":"S2RMs: Spatially Structured Recurrent Modules","created":"2020-07-13","cited_by_count":10},{"id":"2010.08012","title":"Neural Function Modules with Sparse Arguments: A Dynamic Approach to Integrating Information across Layers","created":"2020-10-15","cited_by_count":3}],"next_cursor":null}