{"list":"other","total":64,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1708.00055","title":"SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation","created":"2017-07-31","cited_by_count":1001},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"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":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"1712.00559","title":"Progressive Neural Architecture Search","created":"2017-12-02","cited_by_count":487},{"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":"2001.00326","title":"NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search","created":"2020-01-02","cited_by_count":416},{"id":"1402.1869","title":"On the Number of Linear Regions of Deep Neural Networks","created":"2014-02-08","cited_by_count":381},{"id":"1707.08819","title":"A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets","created":"2017-07-27","cited_by_count":377},{"id":"1902.09635","title":"NAS-Bench-101: Towards Reproducible Neural Architecture Search","created":"2019-02-25","cited_by_count":344},{"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":"2006.02903","title":"A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions","created":"2020-06-01","cited_by_count":254},{"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":"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":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139},{"id":"1911.12126","title":"Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search","created":"2019-11-27","cited_by_count":131},{"id":"2005.00770","title":"Exploring and Predicting Transferability across NLP Tasks","created":"2020-05-02","cited_by_count":128},{"id":"1912.00848","title":"Neural Predictor for Neural Architecture Search","created":"2019-12-02","cited_by_count":118},{"id":"1909.06035","title":"DARTS+: Improved Differentiable Architecture Search with Early Stopping","created":"2019-09-13","cited_by_count":105},{"id":"1312.6098","title":"On the number of response regions of deep feed forward networks with piece-wise linear activations","created":"2013-12-20","cited_by_count":94},{"id":"1909.04977","title":"CARS: Continuous Evolution for Efficient Neural Architecture Search","created":"2019-09-11","cited_by_count":79},{"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":"2205.10793","title":"Knowledge Distillation via the Target-aware Transformer","created":"2022-05-22","cited_by_count":70},{"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":"2001.01233","title":"EcoNAS: Finding Proxies for Economical Neural Architecture Search","created":"2020-01-05","cited_by_count":61},{"id":"2105.11871","title":"TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Search","created":"2021-05-25","cited_by_count":58},{"id":"2301.11300","title":"ZiCo: Zero-shot NAS via Inverse Coefficient of Variation on Gradients","created":"2023-01-26","cited_by_count":58},{"id":"2008.03064","title":"Evaluating Efficient Performance Estimators of Neural Architectures","created":"2020-08-07","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":"2006.00978","title":"On the Number of Linear Regions of Convolutional Neural Networks","created":"2020-06-01","cited_by_count":49},{"id":"2002.10389","title":"Semi-Supervised Neural Architecture Search","created":"2020-02-24","cited_by_count":46},{"id":"2210.03230","title":"NAS-Bench-Suite-Zero: Accelerating Research on Zero Cost Proxies","created":"2022-10-06","cited_by_count":36},{"id":"2103.05471","title":"Contrastive Neural Architecture Search with Neural Architecture Comparators","created":"2021-03-08","cited_by_count":34},{"id":"2203.12217","title":"Training-free Transformer Architecture Search","created":"2022-03-23","cited_by_count":33},{"id":"1906.04113","title":"BlockSwap: Fisher-guided Block Substitution for Network Compression on a Budget","created":"2019-06-10","cited_by_count":26},{"id":"2102.08099","title":"EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search","created":"2021-02-16","cited_by_count":24},{"id":"2203.14577","title":"Demystifying the Neural Tangent Kernel from a Practical Perspective: Can it be trusted for Neural Architecture Search without training?","created":"2022-03-28","cited_by_count":18},{"id":"2205.11656","title":"FlexiBERT: Are Current Transformer Architectures too Homogeneous and Rigid?","created":"2022-05-23","cited_by_count":12},{"id":"1905.07320","title":"EENA: Efficient Evolution of Neural Architecture","created":"2019-05-10","cited_by_count":10},{"id":"1705.10823","title":"Accelerating Neural Architecture Search using Performance Prediction","created":"2017-05-30","cited_by_count":9},{"id":"2306.00288","title":"Training-free Neural Architecture Search for RNNs and Transformers","created":"2023-06-01","cited_by_count":9},{"id":"2012.12540","title":"Evolving Neural Architecture Using One Shot Model","created":"2020-12-23","cited_by_count":8}],"next_cursor":null}