{"list":"other","total":93,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"1703.06114","title":"Deep Sets","created":"2017-03-10","cited_by_count":1421},{"id":"1704.04368","title":"Get To The Point: Summarization with Pointer-Generator Networks","created":"2017-04-14","cited_by_count":1292},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"1506.03134","title":"Pointer Networks","created":"2015-06-09","cited_by_count":895},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1806.08804","title":"Hierarchical Graph Representation Learning with Differentiable Pooling","created":"2018-06-22","cited_by_count":787},{"id":"1709.00103","title":"Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning","created":"2017-08-31","cited_by_count":687},{"id":"1803.08475","title":"Attention, Learn to Solve Routing Problems!","created":"2018-03-22","cited_by_count":656},{"id":"1807.03819","title":"Universal Transformers","created":"2018-07-10","cited_by_count":647},{"id":"1410.5401","title":"Neural Turing Machines","created":"2014-10-20","cited_by_count":644},{"id":"1811.06128","title":"Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizon","created":"2018-11-15","cited_by_count":623},{"id":"1611.09940","title":"Neural Combinatorial Optimization with Reinforcement Learning","created":"2016-11-29","cited_by_count":608},{"id":"1704.01665","title":"Learning Combinatorial Optimization Algorithms over Graphs","created":"2017-04-05","cited_by_count":561},{"id":"1807.05511","title":"Object Detection with Deep Learning: A Review","created":"2018-07-15","cited_by_count":528},{"id":"1603.08983","title":"Adaptive Computation Time for Recurrent Neural Networks","created":"2016-03-29","cited_by_count":506},{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408},{"id":"1805.11973","title":"MolGAN: An implicit generative model for small molecular graphs","created":"2018-05-30","cited_by_count":393},{"id":"1410.3916","title":"Memory Networks","created":"2014-10-15","cited_by_count":363},{"id":"1802.04240","title":"Reinforcement Learning for Solving the Vehicle Routing Problem","created":"2018-02-12","cited_by_count":333},{"id":"1605.05273","title":"Learning Convolutional Neural Networks for Graphs","created":"2016-05-17","cited_by_count":314},{"id":"1906.06755","title":"Theoretical Limitations of Self-Attention in Neural Sequence Models","created":"2019-06-16","cited_by_count":288},{"id":"1810.02912","title":"Actor-Attention-Critic for Multi-Agent Reinforcement Learning","created":"2018-10-05","cited_by_count":261},{"id":"1511.06391","title":"Order Matters: Sequence to sequence for sets","created":"2015-11-19","cited_by_count":237},{"id":"2002.08871","title":"Fast Differentiable Sorting and Ranking","created":"2020-02-20","cited_by_count":197},{"id":"1404.4661","title":"Learning Fine-grained Image Similarity with Deep Ranking","created":"2014-04-17","cited_by_count":190},{"id":"1901.08149","title":"TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents","created":"2019-01-23","cited_by_count":188},{"id":"1802.08665","title":"Learning Latent Permutations with Gumbel-Sinkhorn Networks","created":"2018-02-23","cited_by_count":175},{"id":"1601.06733","title":"Long Short-Term Memory-Networks for Machine Reading","created":"2016-01-25","cited_by_count":161},{"id":"1607.07086","title":"An Actor-Critic Algorithm for Sequence Prediction","created":"2016-07-24","cited_by_count":159},{"id":"2003.07064","title":"On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location","created":"2020-03-16","cited_by_count":142},{"id":"1606.02960","title":"Sequence-to-Sequence Learning as Beam-Search Optimization","created":"2016-06-09","cited_by_count":127},{"id":"1904.02874","title":"An Attentive Survey of Attention Models","created":"2019-04-05","cited_by_count":124},{"id":"1711.09224","title":"CondenseNet: An Efficient DenseNet using Learned Group Convolutions","created":"2017-11-25","cited_by_count":122},{"id":"1606.02185","title":"Towards a Neural Statistician","created":"2016-06-07","cited_by_count":121},{"id":"2010.02650","title":"If beam search is the answer, what was the question?","created":"2020-10-06","cited_by_count":116},{"id":"1905.11885","title":"Differentiable Ranks and Sorting using Optimal Transport","created":"2019-05-28","cited_by_count":113},{"id":"1903.08850","title":"Stochastic Optimization of Sorting Networks via Continuous Relaxations","created":"2019-03-21","cited_by_count":111},{"id":"1809.00582","title":"Data-to-Text Generation with Content Selection and Planning","created":"2018-09-03","cited_by_count":106},{"id":"1811.01900","title":"Janossy Pooling: Learning Deep Permutation-Invariant Functions for Variable-Size Inputs","created":"2018-11-05","cited_by_count":98},{"id":"1611.03199","title":"Low Data Drug Discovery with One-shot Learning","created":"2016-11-10","cited_by_count":91},{"id":"1901.09006","title":"On the Limitations of Representing Functions on Sets","created":"2019-01-25","cited_by_count":90},{"id":"1906.06565","title":"Deep Set Prediction Networks","created":"2019-06-15","cited_by_count":71},{"id":"1509.06664","title":"Reasoning about Entailment with Neural Attention","created":"2015-09-22","cited_by_count":69},{"id":"1804.05936","title":"Learning a Deep Listwise Context Model for Ranking Refinement","created":"2018-04-16","cited_by_count":62},{"id":"1912.03500","title":"Optimizing Rank-based Metrics with Blackbox Differentiation","created":"2019-12-07","cited_by_count":58},{"id":"1902.03477","title":"The Omniglot challenge: a 3-year progress report","created":"2019-02-09","cited_by_count":54},{"id":"1906.02795","title":"FSPool: Learning Set Representations with Featurewise Sort Pooling","created":"2019-06-06","cited_by_count":53},{"id":"1902.06285","title":"Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank","created":"2019-02-17","cited_by_count":52},{"id":"1912.05891","title":"SetRank: Learning a Permutation-Invariant Ranking Model for Information Retrieval","created":"2019-12-12","cited_by_count":48},{"id":"1808.00758","title":"Robust Attentional Aggregation of Deep Feature Sets for Multi-view 3D Reconstruction","created":"2018-08-02","cited_by_count":44},{"id":"1810.02019","title":"Seq2Slate: Re-ranking and Slate Optimization with RNNs","created":"2018-10-04","cited_by_count":39},{"id":"1803.02400","title":"Natural Language to Structured Query Generation via Meta-Learning","created":"2018-03-02","cited_by_count":33},{"id":"1507.01053","title":"Describing Multimedia Content using Attention-based Encoder--Decoder Networks","created":"2015-07-04","cited_by_count":32},{"id":"1811.05544","title":"An Introductory Survey on Attention Mechanisms in NLP Problems","created":"2018-11-12","cited_by_count":32},{"id":"2006.16841","title":"Conditional Set Generation with Transformers","created":"2020-06-26","cited_by_count":32},{"id":"1904.04272","title":"SoDeep: a Sorting Deep net to learn ranking loss surrogates","created":"2019-04-08","cited_by_count":28},{"id":"1805.07010","title":"Learning Permutations with Sinkhorn Policy Gradient","created":"2018-05-18","cited_by_count":26},{"id":"1604.06720","title":"Learning rotation invariant convolutional filters for texture classification","created":"2016-04-22","cited_by_count":24},{"id":"1904.01962","title":"Rep the Set: Neural Networks for Learning Set Representations","created":"2019-04-03","cited_by_count":22},{"id":"2001.00056","title":"Deep Attentive Ranking Networks for Learning to Order Sentences","created":"2019-12-31","cited_by_count":22},{"id":"1905.07689","title":"DivGraphPointer: A Graph Pointer Network for Extracting Diverse Keyphrases","created":"2019-05-19","cited_by_count":16},{"id":"2002.08772","title":"Set2Graph: Learning Graphs From Sets","created":"2020-02-20","cited_by_count":16},{"id":"1812.03928","title":"Learning Representations of Sets through Optimized Permutations","created":"2018-12-10","cited_by_count":15},{"id":"1809.10083","title":"Unsupervised Adversarial Invariance","created":"2018-09-26","cited_by_count":14},{"id":"2007.01409","title":"A (Slightly) Improved Approximation Algorithm for Metric TSP","created":"2020-07-02","cited_by_count":13},{"id":"1808.07503","title":"Second-order Democratic Aggregation","created":"2018-08-22","cited_by_count":12},{"id":"1710.09508","title":"Reparameterizing the Birkhoff Polytope for Variational Permutation Inference","created":"2017-10-26","cited_by_count":10},{"id":"2006.14673","title":"Fully Convolutional Open Set Segmentation","created":"2020-06-25","cited_by_count":8},{"id":"2011.05435","title":"Don't Read Too Much into It: Adaptive Computation for Open-Domain Question Answering","created":"2020-11-10","cited_by_count":7},{"id":"1612.06152","title":"Few-Shot Object Recognition from Machine-Labeled Web Images","created":"2016-12-19","cited_by_count":6},{"id":"1906.04547","title":"Learning robust visual representations using data augmentation invariance","created":"2019-06-11","cited_by_count":5},{"id":"1803.05796","title":"Deep Architectures for Learning Context-dependent Ranking Functions","created":"2018-03-15","cited_by_count":3},{"id":"2003.09443","title":"Deep Sets for Generalization in RL","created":"2020-03-20","cited_by_count":3},{"id":"1710.02745","title":"Multi-Document Summarization using Distributed Bag-of-Words Model","created":"2017-10-07","cited_by_count":2},{"id":"1910.09972","title":"Exchangeable deep neural networks for set-to-set matching and learning","created":"2019-10-22","cited_by_count":2},{"id":"1807.00425","title":"Dynamic Prediction Length for Time Series with Sequence to Sequence Networks","created":"2018-07-02","cited_by_count":1}],"next_cursor":null}