{"list":"other","total":93,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"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":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"1601.06759","title":"Pixel Recurrent Neural Networks","created":"2016-01-25","cited_by_count":816},{"id":"1703.00443","title":"OptNet: Differentiable Optimization as a Layer in Neural Networks","created":"2017-03-01","cited_by_count":599},{"id":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"1812.03443","title":"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search","created":"2018-12-09","cited_by_count":485},{"id":"1910.05453","title":"vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations","created":"2019-10-12","cited_by_count":340},{"id":"1503.00075","title":"Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks","created":"2015-02-28","cited_by_count":306},{"id":"1812.09926","title":"SNAS: Stochastic Neural Architecture Search","created":"2018-12-24","cited_by_count":289},{"id":"1906.10652","title":"Monte Carlo Gradient Estimation in Machine Learning","created":"2019-06-25","cited_by_count":283},{"id":"1703.04908","title":"Emergence of Grounded Compositional Language in Multi-Agent Populations","created":"2017-03-15","cited_by_count":263},{"id":"1802.07814","title":"Learning to Explain: An Information-Theoretic Perspective on Model Interpretation","created":"2018-02-21","cited_by_count":248},{"id":"1705.07832","title":"Concrete Dropout","created":"2017-05-22","cited_by_count":227},{"id":"1903.06059","title":"Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement","created":"2019-03-14","cited_by_count":211},{"id":"1802.08665","title":"Learning Latent Permutations with Gumbel-Sinkhorn Networks","created":"2018-02-23","cited_by_count":175},{"id":"2010.00577","title":"Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking","created":"2020-10-01","cited_by_count":153},{"id":"2004.05565","title":"FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions","created":"2020-04-12","cited_by_count":152},{"id":"1411.0030","title":"A* Sampling","created":"2014-10-31","cited_by_count":151},{"id":"1904.03375","title":"Modeling Point Clouds with Self-Attention and Gumbel Subset Sampling","created":"2019-04-06","cited_by_count":151},{"id":"1711.11503","title":"Convolutional Networks with Adaptive Inference Graphs","created":"2017-11-30","cited_by_count":148},{"id":"1812.03299","title":"Learning to Assemble Neural Module Tree Networks for Visual Grounding","created":"2018-12-08","cited_by_count":140},{"id":"1705.11192","title":"Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols","created":"2017-05-31","cited_by_count":125},{"id":"1402.0030","title":"Neural Variational Inference and Learning in Belief Networks","created":"2014-01-31","cited_by_count":117},{"id":"1905.05824","title":"Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models","created":"2019-05-14","cited_by_count":117},{"id":"2006.01895","title":"Learning to Branch for Multi-Task Learning","created":"2020-06-02","cited_by_count":115},{"id":"1903.08850","title":"Stochastic Optimization of Sorting Networks via Continuous Relaxations","created":"2019-03-21","cited_by_count":111},{"id":"1711.00123","title":"Backpropagation through the Void: Optimizing control variates for black-box gradient estimation","created":"2017-10-31","cited_by_count":106},{"id":"1703.10660","title":"Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images","created":"2017-03-30","cited_by_count":101},{"id":"1912.03203","title":"Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference","created":"2019-12-06","cited_by_count":91},{"id":"1901.09346","title":"Concrete Autoencoders for Differentiable Feature Selection and Reconstruction","created":"2019-01-27","cited_by_count":90},{"id":"1602.06725","title":"Variational inference for Monte Carlo objectives","created":"2016-02-22","cited_by_count":84},{"id":"1804.00104","title":"Learning Disentangled Joint Continuous and Discrete Representations","created":"2018-03-31","cited_by_count":83},{"id":"2006.04240","title":"Improving Inference for Neural Image Compression","created":"2020-06-07","cited_by_count":83},{"id":"2002.08676","title":"Learning with Differentiable Perturbed Optimizers","created":"2020-02-20","cited_by_count":81},{"id":"1905.09717","title":"Network Pruning via Transformable Architecture Search","created":"2019-05-23","cited_by_count":80},{"id":"1703.07370","title":"REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models","created":"2017-03-21","cited_by_count":79},{"id":"1909.04866","title":"Deep Declarative Networks: A New Hope","created":"2019-09-11","cited_by_count":78},{"id":"2007.03938","title":"Operation-Aware Soft Channel Pruning using Differentiable Masks","created":"2020-07-08","cited_by_count":74},{"id":"1901.10517","title":"Reparameterizable Subset Sampling via Continuous Relaxations","created":"2019-01-29","cited_by_count":70},{"id":"1705.10257","title":"Boltzmann Exploration Done Right","created":"2017-05-29","cited_by_count":69},{"id":"2006.08063","title":"Gradient Estimation with Stochastic Softmax Tricks","created":"2020-06-15","cited_by_count":67},{"id":"1802.04223","title":"SparseMAP: Differentiable Sparse Structured Inference","created":"2018-02-12","cited_by_count":62},{"id":"1705.00154","title":"Classical Planning in Deep Latent Space: Bridging the Subsymbolic-Symbolic Boundary","created":"2017-04-29","cited_by_count":58},{"id":"1611.04051","title":"GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution","created":"2016-11-12","cited_by_count":48},{"id":"1707.02786","title":"Learning to Compose Task-Specific Tree Structures","created":"2017-07-10","cited_by_count":48},{"id":"1907.06627","title":"Batch-Shaping for Learning Conditional Channel Gated Networks","created":"2019-07-15","cited_by_count":42},{"id":"1908.09597","title":"Stochastic Filter Groups for Multi-Task CNNs: Learning Specialist and Generalist Convolution Kernels","created":"2019-08-26","cited_by_count":42},{"id":"1805.12316","title":"Greedy Attack and Gumbel Attack: Generating Adversarial Examples for Discrete Data","created":"2018-05-31","cited_by_count":38},{"id":"2010.04838","title":"Rao-Blackwellizing the Straight-Through Gumbel-Softmax Gradient Estimator","created":"2020-10-09","cited_by_count":37},{"id":"1711.01068","title":"Compressing Word Embeddings via Deep Compositional Code Learning","created":"2017-11-03","cited_by_count":35},{"id":"2007.08513","title":"RetrieveGAN: Image Synthesis via Differentiable Patch Retrieval","created":"2020-07-16","cited_by_count":35},{"id":"1812.02664","title":"Recursive Visual Attention in Visual Dialog","created":"2018-12-06","cited_by_count":34},{"id":"2002.06043","title":"Estimating Gradients for Discrete Random Variables by Sampling without Replacement","created":"2020-02-14","cited_by_count":31},{"id":"2001.01941","title":"Paraphrase Generation with Latent Bag of Words","created":"2020-01-07","cited_by_count":27},{"id":"1801.09251","title":"Multi-Pointer Co-Attention Networks for Recommendation","created":"2018-01-28","cited_by_count":25},{"id":"2002.09067","title":"Incremental Sampling Without Replacement for Sequence Models","created":"2020-02-21","cited_by_count":23},{"id":"1706.01554","title":"Best of Both Worlds: Transferring Knowledge from Discriminative Learning to a Generative Visual Dialog Model","created":"2017-06-05","cited_by_count":19},{"id":"1803.01785","title":"Differentiable Submodular Maximization","created":"2018-03-05","cited_by_count":19},{"id":"1807.09875","title":"Differentiable Perturb-and-Parse: Semi-Supervised Parsing with a Structured Variational Autoencoder","created":"2018-07-25","cited_by_count":19},{"id":"1912.09588","title":"Invertible Gaussian Reparameterization: Revisiting the Gumbel-Softmax","created":"2019-12-19","cited_by_count":18},{"id":"1812.11482","title":"A General Deep Learning Framework for Network Reconstruction and Dynamics Learning","created":"2018-12-30","cited_by_count":16},{"id":"1908.05764","title":"Learning Sub-Sampling and Signal Recovery with Applications in Ultrasound Imaging","created":"2019-08-15","cited_by_count":13},{"id":"1810.13107","title":"End-to-End Feedback Loss in Speech Chain Framework via Straight-Through Estimator","created":"2018-10-31","cited_by_count":11},{"id":"1910.08031","title":"Deep clustering with concrete k-means","created":"2019-10-17","cited_by_count":11},{"id":"1710.09508","title":"Reparameterizing the Birkhoff Polytope for Variational Permutation Inference","created":"2017-10-26","cited_by_count":10},{"id":"1810.12406","title":"Learning to Screen for Fast Softmax Inference on Large Vocabulary Neural Networks","created":"2018-10-29","cited_by_count":10},{"id":"1905.01413","title":"ARSM: Augment-REINFORCE-Swap-Merge Estimator for Gradient Backpropagation Through Categorical Variables","created":"2019-05-04","cited_by_count":10},{"id":"2002.09928","title":"Predictive Sampling with Forecasting Autoregressive Models","created":"2020-02-23","cited_by_count":10},{"id":"1905.13125","title":"Seeker: Real-Time Interactive Search","created":"2019-05-17","cited_by_count":9},{"id":"2004.10536","title":"Learning Sampling and Model-Based Signal Recovery for Compressed Sensing MRI","created":"2020-04-22","cited_by_count":9},{"id":"1707.03372","title":"Fast Amortized Inference and Learning in Log-linear Models with Randomly Perturbed Nearest Neighbor Search","created":"2017-07-11","cited_by_count":8},{"id":"2010.04361","title":"Event Representation with Sequential, Semi-Supervised Discrete Variables","created":"2020-10-09","cited_by_count":8},{"id":"1309.7598","title":"On Sampling from the Gibbs Distribution with Random Maximum A-Posteriori Perturbations","created":"2013-09-29","cited_by_count":7},{"id":"1712.05087","title":"Learning Binary Residual Representations for Domain-specific Video Streaming","created":"2017-12-14","cited_by_count":7},{"id":"1807.00942","title":"Stochastic Layer-Wise Precision in Deep Neural Networks","created":"2018-07-03","cited_by_count":6},{"id":"1906.10948","title":"Latent Multi-Criteria Ratings for Recommendations","created":"2019-06-26","cited_by_count":6},{"id":"1910.10682","title":"Feature Selection and Extraction for Graph Neural Networks","created":"2019-10-23","cited_by_count":6},{"id":"1706.07518","title":"Neural Machine Translation with Gumbel-Greedy Decoding","created":"2017-06-22","cited_by_count":5},{"id":"2105.12686","title":"Dynamic Probabilistic Pruning: A general framework for hardware-constrained pruning at different granularities","created":"2021-05-26","cited_by_count":5},{"id":"1506.09039","title":"Scalable Discrete Sampling as a Multi-Armed Bandit Problem","created":"2015-06-30","cited_by_count":4},{"id":"2005.02372","title":"Community Detection Clustering via Gumbel Softmax","created":"2020-05-05","cited_by_count":4},{"id":"1708.07590","title":"Hierarchical Multi-scale Attention Networks for Action Recognition","created":"2017-08-25","cited_by_count":3},{"id":"1806.02988","title":"Towards Binary-Valued Gates for Robust LSTM Training","created":"2018-06-08","cited_by_count":3},{"id":"2002.00413","title":"Fast Generating A Large Number of Gumbel-Max Variables","created":"2020-02-02","cited_by_count":3},{"id":"2004.07300","title":"Gumbel-softmax-based Optimization: A Simple General Framework for Optimization Problems on Graphs","created":"2020-04-14","cited_by_count":3},{"id":"2009.01653","title":"Deep Learning Based Antenna Selection for Channel Extrapolation in FDD Massive MIMO","created":"2020-09-03","cited_by_count":3},{"id":"1911.11984","title":"SAG-VAE: End-to-end Joint Inference of Data Representations and Feature Relations","created":"2019-11-27","cited_by_count":2}],"next_cursor":null}