{"list":"other","total":56,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1907.10902","title":"Optuna: A Next-generation Hyperparameter Optimization Framework","created":"2019-07-25","cited_by_count":2501},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"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":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"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":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"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":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633},{"id":"2006.05467","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","created":"2020-06-09","cited_by_count":479},{"id":"2002.07376","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","created":"2020-02-18","cited_by_count":471},{"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":"1904.00420","title":"Single Path One-Shot Neural Architecture Search with Uniform Sampling","created":"2019-03-31","cited_by_count":414},{"id":"1905.03696","title":"HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision","created":"2019-04-29","cited_by_count":402},{"id":"1902.09635","title":"NAS-Bench-101: Towards Reproducible Neural Architecture Search","created":"2019-02-25","cited_by_count":344},{"id":"1502.05336","title":"Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks","created":"2015-02-18","cited_by_count":295},{"id":"1911.03852","title":"HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks","created":"2019-11-10","cited_by_count":261},{"id":"1910.04465","title":"Searching for A Robust Neural Architecture in Four GPU Hours","created":"2019-10-10","cited_by_count":260},{"id":"2006.04647","title":"Neural Architecture Search without Training","created":"2020-06-08","cited_by_count":244},{"id":"1904.12760","title":"Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation","created":"2019-04-29","cited_by_count":230},{"id":"2101.08134","title":"Zero-Cost Proxies for Lightweight NAS","created":"2021-01-20","cited_by_count":199},{"id":"1802.07191","title":"Neural Architecture Search with Bayesian Optimisation and Optimal Transport","created":"2018-02-11","cited_by_count":195},{"id":"2107.00651","title":"AutoFormer: Searching Transformers for Visual Recognition","created":"2021-07-01","cited_by_count":188},{"id":"2102.11535","title":"Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective","created":"2021-02-23","cited_by_count":169},{"id":"1808.07233","title":"Neural Architecture Optimization","created":"2018-08-22","cited_by_count":167},{"id":"2003.03384","title":"AutoML-Zero: Evolving Machine Learning Algorithms From Scratch","created":"2020-03-06","cited_by_count":143},{"id":"1912.00848","title":"Neural Predictor for Neural Architecture Search","created":"2019-12-02","cited_by_count":118},{"id":"2102.01063","title":"Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition","created":"2021-02-01","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":"1905.13214","title":"On Network Design Spaces for Visual Recognition","created":"2019-05-30","cited_by_count":68},{"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":"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":"2008.03064","title":"Evaluating Efficient Performance Estimators of Neural Architectures","created":"2020-08-07","cited_by_count":55},{"id":"2109.07865","title":"OMPQ: Orthogonal Mixed Precision Quantization","created":"2021-09-16","cited_by_count":39},{"id":"1910.01523","title":"ReNAS:Relativistic Evaluation of Neural Architecture Search","created":"2019-09-30","cited_by_count":37},{"id":"2103.05471","title":"Contrastive Neural Architecture Search with Neural Architecture Comparators","created":"2021-03-08","cited_by_count":34},{"id":"2111.13293","title":"KNAS: Green Neural Architecture Search","created":"2021-11-26","cited_by_count":33},{"id":"2203.12217","title":"Training-free Transformer Architecture Search","created":"2022-03-23","cited_by_count":33},{"id":"2106.13700","title":"ViTAS: Vision Transformer Architecture Search","created":"2021-06-25","cited_by_count":31},{"id":"2303.15678","title":"DisWOT: Student Architecture Search for Distillation WithOut Training","created":"2023-03-28","cited_by_count":29},{"id":"2109.00817","title":"NASI: Label- and Data-agnostic Neural Architecture Search at Initialization","created":"2021-09-02","cited_by_count":28},{"id":"2307.10554","title":"EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization","created":"2023-07-20","cited_by_count":22},{"id":"2110.08616","title":"GradSign: Model Performance Inference with Theoretical Insights","created":"2021-10-16","cited_by_count":19},{"id":"2201.09785","title":"Unifying and Boosting Gradient-Based Training-Free Neural Architecture Search","created":"2022-01-24","cited_by_count":17},{"id":"2209.07413","title":"EZNAS: Evolving Zero Cost Proxies For Neural Architecture Scoring","created":"2022-09-15","cited_by_count":15},{"id":"2304.14636","title":"PreNAS: Preferred One-Shot Learning Towards Efficient Neural Architecture Search","created":"2023-04-28","cited_by_count":11},{"id":"2207.05135","title":"FreeREA: Training-Free Evolution-based Architecture Search","created":"2022-06-17","cited_by_count":10},{"id":"2311.13169","title":"SiGeo: Sub-One-Shot NAS via Information Theory and Geometry of Loss Landscape","created":"2023-11-22","cited_by_count":1}],"next_cursor":null}