{"list":"other","total":62,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"id":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"id":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"1802.01548","title":"Regularized Evolution for Image Classifier Architecture Search","created":"2018-02-05","cited_by_count":909},{"id":"1802.03268","title":"Efficient Neural Architecture Search via Parameter Sharing","created":"2018-02-09","cited_by_count":837},{"id":"1603.06560","title":"Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization","created":"2016-03-21","cited_by_count":699},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"id":"1905.03197","title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","created":"2019-05-08","cited_by_count":670},{"id":"1712.00559","title":"Progressive Neural Architecture Search","created":"2017-12-02","cited_by_count":487},{"id":"1807.01774","title":"BOHB: Robust and Efficient Hyperparameter Optimization at Scale","created":"2018-07-04","cited_by_count":470},{"id":"2001.00326","title":"NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search","created":"2020-01-02","cited_by_count":416},{"id":"1703.01041","title":"Large-Scale Evolution of Image Classifiers","created":"2017-03-03","cited_by_count":348},{"id":"1902.09635","title":"NAS-Bench-101: Towards Reproducible Neural Architecture Search","created":"2019-02-25","cited_by_count":344},{"id":"1812.09926","title":"SNAS: Stochastic Neural Architecture Search","created":"2018-12-24","cited_by_count":289},{"id":"1502.05700","title":"Scalable Bayesian Optimization Using Deep Neural Networks","created":"2015-02-19","cited_by_count":284},{"id":"1611.02167","title":"Designing Neural Network Architectures using Reinforcement Learning","created":"2016-11-07","cited_by_count":279},{"id":"1910.04465","title":"Searching for A Robust Neural Architecture in Four GPU Hours","created":"2019-10-10","cited_by_count":260},{"id":"1902.07638","title":"Random Search and Reproducibility for Neural Architecture Search","created":"2019-02-20","cited_by_count":254},{"id":"1802.07191","title":"Neural Architecture Search with Bayesian Optimisation and Optimal Transport","created":"2018-02-11","cited_by_count":195},{"id":"1711.00436","title":"Hierarchical Representations for Efficient Architecture Search","created":"2017-11-01","cited_by_count":191},{"id":"1910.11858","title":"BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search","created":"2019-10-25","cited_by_count":179},{"id":"1909.09656","title":"Understanding and Robustifying Differentiable Architecture Search","created":"2019-09-20","cited_by_count":178},{"id":"1808.07233","title":"Neural Architecture Optimization","created":"2018-08-22","cited_by_count":167},{"id":"1907.01845","title":"FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search","created":"2019-07-03","cited_by_count":130},{"id":"1912.00848","title":"Neural Predictor for Neural Architecture Search","created":"2019-12-02","cited_by_count":118},{"id":"1904.01569","title":"Exploring Randomly Wired Neural Networks for Image Recognition","created":"2019-04-02","cited_by_count":103},{"id":"2002.05283","title":"Stabilizing Differentiable Architecture Search via Perturbation-based Regularization","created":"2020-02-12","cited_by_count":102},{"id":"1904.11088","title":"D-VAE: A Variational Autoencoder for Directed Acyclic Graphs","created":"2019-04-24","cited_by_count":98},{"id":"2007.10396","title":"NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search","created":"2020-07-20","cited_by_count":76},{"id":"2003.11236","title":"GreedyNAS: Towards Fast One-Shot NAS with Greedy Supernet","created":"2020-03-25","cited_by_count":69},{"id":"1905.04919","title":"BayesNAS: A Bayesian Approach for Neural Architecture Search","created":"2019-05-13","cited_by_count":68},{"id":"2007.06559","title":"Graph Structure of Neural Networks","created":"2020-07-13","cited_by_count":68},{"id":"2008.06120","title":"Can weight sharing outperform random architecture search? An investigation with TuNAS","created":"2020-08-13","cited_by_count":68},{"id":"2006.06936","title":"Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?","created":"2020-06-12","cited_by_count":59},{"id":"2004.01899","title":"A Generic Graph-based Neural Architecture Encoding Scheme for Predictor-based NAS","created":"2020-04-04","cited_by_count":55},{"id":"2008.01475","title":"Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap","created":"2020-08-04","cited_by_count":50},{"id":"2002.10389","title":"Semi-Supervised Neural Architecture Search","created":"2020-02-24","cited_by_count":46},{"id":"2007.04965","title":"A Study on Encodings for Neural Architecture Search","created":"2020-07-09","cited_by_count":38},{"id":"2010.15821","title":"Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search","created":"2020-10-29","cited_by_count":38},{"id":"1903.11059","title":"AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree Search","created":"2019-03-26","cited_by_count":33},{"id":"2004.01395","title":"Neural Architecture Generator Optimization","created":"2020-04-03","cited_by_count":30},{"id":"1704.08792","title":"DeepArchitect: Automatically Designing and Training Deep Architectures","created":"2017-04-28","cited_by_count":28},{"id":"2005.06821","title":"A Semi-Supervised Assessor of Neural Architectures","created":"2020-05-14","cited_by_count":28},{"id":"1908.06756","title":"BOAH: A Tool Suite for Multi-Fidelity Bayesian Optimization & Analysis of Hyperparameters","created":"2019-08-16","cited_by_count":25},{"id":"1906.06832","title":"Sample-Efficient Neural Architecture Search by Learning Action Space","created":"2019-06-17","cited_by_count":23},{"id":"2004.08996","title":"Local Search is a Remarkably Strong Baseline for Neural Architecture Search","created":"2020-04-20","cited_by_count":15},{"id":"2010.04683","title":"Smooth Variational Graph Embeddings for Efficient Neural Architecture Search","created":"2020-10-09","cited_by_count":12},{"id":"2011.00186","title":"Self-supervised Representation Learning for Evolutionary Neural Architecture Search","created":"2020-10-31","cited_by_count":9},{"id":"1909.00122","title":"HM-NAS: Efficient Neural Architecture Search via Hierarchical Masking","created":"2019-08-31","cited_by_count":5},{"id":"2010.10261","title":"AutoBSS: An Efficient Algorithm for Block Stacking Style Search","created":"2020-10-20","cited_by_count":4},{"id":"2102.04208","title":"Contrastive Embeddings for Neural Architectures","created":"2021-02-08","cited_by_count":3}],"next_cursor":null}