{"list":"other","total":74,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"1904.08405","title":"Event-based Vision: A Survey","created":"2019-04-17","cited_by_count":1016},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1506.03099","title":"Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks","created":"2015-06-09","cited_by_count":803},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"1611.01704","title":"End-to-end Optimized Image Compression","created":"2016-11-05","cited_by_count":696},{"id":"1904.02882","title":"LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech","created":"2019-04-05","cited_by_count":649},{"id":"1511.06349","title":"Generating Sentences from a Continuous Space","created":"2015-11-19","cited_by_count":612},{"id":"2005.00341","title":"Jukebox: A Generative Model for Music","created":"2020-04-30","cited_by_count":542},{"id":"1603.08983","title":"Adaptive Computation Time for Recurrent Neural Networks","created":"2016-03-29","cited_by_count":506},{"id":"1912.07875","title":"Libri-Light: A Benchmark for ASR with Limited or No Supervision","created":"2019-12-17","cited_by_count":467},{"id":"1807.06653","title":"Invariant Information Clustering for Unsupervised Image Classification and Segmentation","created":"2018-07-17","cited_by_count":455},{"id":"1912.08193","title":"PointRend: Image Segmentation as Rendering","created":"2019-12-17","cited_by_count":440},{"id":"1901.11390","title":"MONet: Unsupervised Scene Decomposition and Representation","created":"2019-01-22","cited_by_count":392},{"id":"1903.00450","title":"Multi-Object Representation Learning with Iterative Variational Inference","created":"2019-03-01","cited_by_count":360},{"id":"1910.05453","title":"vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations","created":"2019-10-12","cited_by_count":340},{"id":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","cited_by_count":340},{"id":"2006.03677","title":"Visual Transformers: Token-based Image Representation and Processing for Computer Vision","created":"2020-06-05","cited_by_count":334},{"id":"1703.00395","title":"Lossy Image Compression with Compressive Autoencoders","created":"2017-03-01","cited_by_count":294},{"id":"1910.06764","title":"Stabilizing Transformers for Reinforcement Learning","created":"2019-10-13","cited_by_count":270},{"id":"2103.03841","title":"Generating Images with Sparse Representations","created":"2021-03-05","cited_by_count":266},{"id":"1809.10853","title":"Adaptive Input Representations for Neural Language Modeling","created":"2018-09-28","cited_by_count":226},{"id":"1603.08575","title":"Attend, Infer, Repeat: Fast Scene Understanding with Generative Models","created":"2016-03-28","cited_by_count":209},{"id":"1611.02731","title":"Variational Lossy Autoencoder","created":"2016-11-08","cited_by_count":176},{"id":"1609.02200","title":"Discrete Variational Autoencoders","created":"2016-09-07","cited_by_count":125},{"id":"2007.10930","title":"Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding","created":"2020-07-21","cited_by_count":122},{"id":"1612.02297","title":"Spatially Adaptive Computation Time for Residual Networks","created":"2016-12-07","cited_by_count":118},{"id":"1712.00636","title":"Compressed Video Action Recognition","created":"2017-12-02","cited_by_count":106},{"id":"1511.06984","title":"End-to-end Learning of Action Detection from Frame Glimpses in Videos","created":"2015-11-22","cited_by_count":101},{"id":"1610.09513","title":"Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences","created":"2016-10-29","cited_by_count":99},{"id":"1901.08810","title":"Unsupervised speech representation learning using WaveNet autoencoders","created":"2019-01-25","cited_by_count":90},{"id":"1909.07782","title":"Interpolation-Prediction Networks for Irregularly Sampled Time Series","created":"2019-09-13","cited_by_count":89},{"id":"1901.03416","title":"Preventing Posterior Collapse with delta-VAEs","created":"2019-01-10","cited_by_count":86},{"id":"1810.00597","title":"Taming VAEs","created":"2018-10-01","cited_by_count":85},{"id":"1402.0915","title":"Learning Ordered Representations with Nested Dropout","created":"2014-02-05","cited_by_count":84},{"id":"1812.01608","title":"Generating High Fidelity Images with Subscale Pixel Networks and Multidimensional Upscaling","created":"2018-12-04","cited_by_count":74},{"id":"1808.03715","title":"This Time with Feeling: Learning Expressive Musical Performance","created":"2018-08-10","cited_by_count":68},{"id":"1806.10474","title":"The challenge of realistic music generation: modelling raw audio at scale","created":"2018-06-26","cited_by_count":63},{"id":"1806.02199","title":"SOM-VAE: Interpretable Discrete Representation Learning on Time Series","created":"2018-06-06","cited_by_count":60},{"id":"1708.06834","title":"Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks","created":"2017-08-22","cited_by_count":49},{"id":"1605.06197","title":"Stick-Breaking Variational Autoencoders","created":"2016-05-20","cited_by_count":44},{"id":"2006.07926","title":"UWSpeech: Speech to Speech Translation for Unwritten Languages","created":"2020-06-14","cited_by_count":43},{"id":"1907.07156","title":"Efficient Segmentation: Learning Downsampling Near Semantic Boundaries","created":"2019-07-16","cited_by_count":33},{"id":"1703.04122","title":"Autoregressive Convolutional Neural Networks for Asynchronous Time Series","created":"2017-03-12","cited_by_count":31},{"id":"1710.04110","title":"Discrete Event, Continuous Time RNNs","created":"2017-10-11","cited_by_count":31},{"id":"1808.00300","title":"Learning Visual Question Answering by Bootstrapping Hard Attention","created":"2018-08-01","cited_by_count":24},{"id":"2005.05525","title":"DiscreTalk: Text-to-Speech as a Machine Translation Problem","created":"2020-05-12","cited_by_count":21},{"id":"2006.02547","title":"A Convolutional Deep Markov Model for Unsupervised Speech Representation Learning","created":"2020-06-03","cited_by_count":18},{"id":"2102.09660","title":"Generative Speech Coding with Predictive Variance Regularization","created":"2021-02-18","cited_by_count":18},{"id":"1903.04933","title":"Hierarchical Autoregressive Image Models with Auxiliary Decoders","created":"2019-03-06","cited_by_count":17},{"id":"1810.05246","title":"Piano Genie","created":"2018-10-11","cited_by_count":11},{"id":"2004.10120","title":"Vector Quantized Contrastive Predictive Coding for Template-based Music Generation","created":"2020-04-21","cited_by_count":10},{"id":"1608.00508","title":"Blind phoneme segmentation with temporal prediction errors","created":"2016-08-01","cited_by_count":9},{"id":"1502.02476","title":"An Infinite Restricted Boltzmann Machine","created":"2015-02-09","cited_by_count":4},{"id":"2006.01659","title":"Surprisal-Triggered Conditional Computation with Neural Networks","created":"2020-06-02","cited_by_count":4},{"id":"2006.13105","title":"Differentiable Segmentation of Sequences","created":"2020-06-23","cited_by_count":3},{"id":"1706.06699","title":"Representation Learning using Event-based STDP","created":"2017-06-20","cited_by_count":2}],"next_cursor":null}