{"list":"other","total":70,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"2012.07436","title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","created":"2020-12-14","cited_by_count":2169},{"id":"2211.14730","title":"A Time Series is Worth 64 Words: Long-term Forecasting with Transformers","created":"2022-11-27","cited_by_count":2039},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"2106.13008","title":"Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting","created":"2021-06-24","cited_by_count":1676},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"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":"1908.09791","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","created":"2019-08-26","cited_by_count":787},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"id":"1712.00559","title":"Progressive Neural Architecture Search","created":"2017-12-02","cited_by_count":487},{"id":"1812.03443","title":"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search","created":"2018-12-09","cited_by_count":485},{"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":"1904.00420","title":"Single Path One-Shot Neural Architecture Search with Uniform Sampling","created":"2019-03-31","cited_by_count":414},{"id":"1902.09635","title":"NAS-Bench-101: Towards Reproducible Neural Architecture Search","created":"2019-02-25","cited_by_count":344},{"id":"1907.05737","title":"PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search","created":"2019-07-12","cited_by_count":265},{"id":"2006.04647","title":"Neural Architecture Search without Training","created":"2020-06-08","cited_by_count":244},{"id":"2101.08134","title":"Zero-Cost Proxies for Lightweight NAS","created":"2021-01-20","cited_by_count":199},{"id":"2006.05078","title":"Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimization","created":"2020-06-09","cited_by_count":179},{"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":"1804.09081","title":"Efficient Multi-objective Neural Architecture Search via Lamarckian Evolution","created":"2018-04-24","cited_by_count":153},{"id":"1605.07079","title":"Fast Bayesian Optimization of Machine Learning Hyperparameters on Large Datasets","created":"2016-05-23","cited_by_count":132},{"id":"1911.12126","title":"Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search","created":"2019-11-27","cited_by_count":131},{"id":"1902.08142","title":"Evaluating the Search Phase of Neural Architecture Search","created":"2019-02-21","cited_by_count":120},{"id":"2105.08195","title":"Parallel Bayesian Optimization of Multiple Noisy Objectives with Expected Hypervolume Improvement","created":"2021-05-17","cited_by_count":118},{"id":"1801.05787","title":"Faster gaze prediction with dense networks and Fisher pruning","created":"2018-01-17","cited_by_count":94},{"id":"2002.05786","title":"Deep Learning for Financial Applications : A Survey","created":"2020-02-09","cited_by_count":91},{"id":"2007.00708","title":"Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search","created":"2020-07-01","cited_by_count":89},{"id":"2103.10584","title":"HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmark","created":"2021-03-19","cited_by_count":84},{"id":"1812.08934","title":"ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation","created":"2018-12-21","cited_by_count":76},{"id":"2007.10396","title":"NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search","created":"2020-07-20","cited_by_count":76},{"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":"1905.04919","title":"BayesNAS: A Bayesian Approach for Neural Architecture Search","created":"2019-05-13","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":"1810.10408","title":"Multi-Agent Reinforcement Learning Based Resource Allocation for UAV Networks","created":"2018-10-24","cited_by_count":56},{"id":"2105.14444","title":"NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search","created":"2021-05-30","cited_by_count":56},{"id":"2006.06863","title":"Few-shot Neural Architecture Search","created":"2020-06-11","cited_by_count":50},{"id":"1806.08198","title":"DPP-Net: Device-aware Progressive Search for Pareto-optimal Neural Architectures","created":"2018-06-21","cited_by_count":40},{"id":"1912.10952","title":"Progressive DARTS: Bridging the Optimization Gap for NAS in the Wild","created":"2019-12-23","cited_by_count":40},{"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":"2111.13293","title":"KNAS: Green Neural Architecture Search","created":"2021-11-26","cited_by_count":33},{"id":"2203.15207","title":"Generalizing Few-Shot NAS with Gradient Matching","created":"2022-03-29","cited_by_count":25},{"id":"2102.08099","title":"EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search","created":"2021-02-16","cited_by_count":24},{"id":"1906.06832","title":"Sample-Efficient Neural Architecture Search by Learning Action Space","created":"2019-06-17","cited_by_count":23},{"id":"2106.06442","title":"K-shot NAS: Learnable Weight-Sharing for NAS with K-shot Supernets","created":"2021-06-11","cited_by_count":22},{"id":"2307.01998","title":"Zero-Shot Neural Architecture Search: Challenges, Solutions, and Opportunities","created":"2023-07-05","cited_by_count":21},{"id":"2110.08616","title":"GradSign: Model Performance Inference with Theoretical Insights","created":"2021-10-16","cited_by_count":19},{"id":"1703.04221","title":"A Hierarchical Framework of Cloud Resource Allocation and Power Management Using Deep Reinforcement Learning","created":"2017-03-13","cited_by_count":16},{"id":"2111.13336","title":"MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection","created":"2021-11-26","cited_by_count":16},{"id":"1903.06478","title":"Multimodal Deep Learning for Finance: Integrating and Forecasting International Stock Markets","created":"2019-03-15","cited_by_count":15},{"id":"2202.11921","title":"Auto-scaling Vision Transformers without Training","created":"2022-02-24","cited_by_count":15},{"id":"2009.02186","title":"Dynamic Scheduling for Stochastic Edge-Cloud Computing Environments using A3C learning and Residual Recurrent Neural Networks","created":"2020-09-01","cited_by_count":14},{"id":"2403.12900","title":"Toward Sustainable GenAI using Generation Directives for Carbon-Friendly Large Language Model Inference","created":"2024-03-19","cited_by_count":13},{"id":"2106.08872","title":"Enabling Sustainable Clouds: The Case for Virtualizing the Energy System","created":"2021-06-16","cited_by_count":12},{"id":"1903.11728","title":"AutoSlim: Towards One-Shot Architecture Search for Channel Numbers","created":"2019-03-27","cited_by_count":10},{"id":"2211.12759","title":"NAS-LID: Efficient Neural Architecture Search with Local Intrinsic Dimension","created":"2022-11-23","cited_by_count":5},{"id":"2112.13354","title":"Large-scale Machine Learning Cluster Scheduling via Multi-agent Graph Reinforcement Learning","created":"2021-12-26","cited_by_count":2},{"id":"2307.04131","title":"Carbon-Efficient Neural Architecture Search","created":"2023-07-09","cited_by_count":2}],"next_cursor":null}