{"list":"other","total":54,"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":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"2003.01690","title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","created":"2020-03-03","cited_by_count":1451},{"id":"2009.09761","title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","created":"2020-09-21","cited_by_count":1354},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"id":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"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":"1908.09791","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","created":"2019-08-26","cited_by_count":787},{"id":"1805.09501","title":"AutoAugment: Learning Augmentation Policies from Data","created":"2018-05-24","cited_by_count":730},{"id":"2203.17003","title":"Equivariant Diffusion for Molecule Generation in 3D","created":"2022-03-31","cited_by_count":677},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"id":"2209.14734","title":"DiGress: Discrete Denoising diffusion for graph generation","created":"2022-09-29","cited_by_count":520},{"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":"2202.02514","title":"Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations","created":"2022-02-05","cited_by_count":283},{"id":"2003.00638","title":"Permutation Invariant Graph Generation via Score-Based Generative Modeling","created":"2020-03-02","cited_by_count":270},{"id":"1907.05737","title":"PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search","created":"2019-07-12","cited_by_count":265},{"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":"1910.11858","title":"BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search","created":"2019-10-25","cited_by_count":179},{"id":"1808.07233","title":"Neural Architecture Optimization","created":"2018-08-22","cited_by_count":167},{"id":"2104.01409","title":"Diff-TTS: A Denoising Diffusion Model for Text-to-Speech","created":"2021-04-03","cited_by_count":157},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139},{"id":"1912.00848","title":"Neural Predictor for Neural Architecture Search","created":"2019-12-02","cited_by_count":118},{"id":"2007.08668","title":"BRP-NAS: Prediction-based NAS using GCNs","created":"2020-07-16","cited_by_count":111},{"id":"1904.11088","title":"D-VAE: A Variational Autoencoder for Directed Acyclic Graphs","created":"2019-04-24","cited_by_count":98},{"id":"2206.07632","title":"Exploring Chemical Space with Score-based Out-of-distribution Generation","created":"2022-06-06","cited_by_count":95},{"id":"2104.01177","title":"How Powerful are Performance Predictors in Neural Architecture Search?","created":"2021-04-02","cited_by_count":90},{"id":"2103.10584","title":"HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmark","created":"2021-03-19","cited_by_count":84},{"id":"2012.03826","title":"HEBO Pushing The Limits of Sample-Efficient Hyperparameter Optimisation","created":"2020-12-07","cited_by_count":83},{"id":"2007.10396","title":"NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search","created":"2020-07-20","cited_by_count":76},{"id":"2006.10355","title":"DrNAS: Dirichlet Neural Architecture Search","created":"2020-06-18","cited_by_count":73},{"id":"1910.05733","title":"One-Shot Neural Architecture Search via Self-Evaluated Template Network","created":"2019-10-13","cited_by_count":69},{"id":"2008.09777","title":"Surrogate NAS Benchmarks: Going Beyond the Limited Search Spaces of Tabular NAS Benchmarks","created":"2020-08-22","cited_by_count":67},{"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":"2008.03064","title":"Evaluating Efficient Performance Estimators of Neural Architectures","created":"2020-08-07","cited_by_count":55},{"id":"1909.02453","title":"Best Practices for Scientific Research on Neural Architecture Search","created":"2019-09-05","cited_by_count":54},{"id":"2107.00860","title":"Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets","created":"2021-07-02","cited_by_count":33},{"id":"2102.07108","title":"CATE: Computation-aware Neural Architecture Encoding with Transformers","created":"2021-02-14","cited_by_count":21},{"id":"2111.03602","title":"NAS-Bench-x11 and the Power of Learning Curves","created":"2021-11-05","cited_by_count":20}],"next_cursor":null}