{"list":"other","total":62,"rows":[{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"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":"1609.09106","title":"HyperNetworks","created":"2016-09-27","cited_by_count":1027},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"2112.08654","title":"Learning to Prompt for Continual Learning","created":"2021-12-16","cited_by_count":944},{"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":"1810.04650","title":"Multi-Task Learning as Multi-Objective Optimization","created":"2018-10-10","cited_by_count":821},{"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":"1812.03443","title":"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search","created":"2018-12-09","cited_by_count":485},{"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":"1812.09926","title":"SNAS: Stochastic Neural Architecture Search","created":"2018-12-24","cited_by_count":289},{"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":"1912.12854","title":"Pareto Multi-Task Learning","created":"2019-12-30","cited_by_count":224},{"id":"1708.05344","title":"SMASH: One-Shot Model Architecture Search through HyperNetworks","created":"2017-08-17","cited_by_count":202},{"id":"2107.00651","title":"AutoFormer: Searching Transformers for Visual Recognition","created":"2021-07-01","cited_by_count":188},{"id":"2006.05078","title":"Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimization","created":"2020-06-09","cited_by_count":179},{"id":"1804.09081","title":"Efficient Multi-objective Neural Architecture Search via Lamarckian Evolution","created":"2018-04-24","cited_by_count":153},{"id":"2011.01821","title":"Minimax Pareto Fairness: A Multi Objective Perspective","created":"2020-11-03","cited_by_count":153},{"id":"2004.05565","title":"FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions","created":"2020-04-12","cited_by_count":152},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139},{"id":"2005.14187","title":"HAT: Hardware-Aware Transformers for Efficient Natural Language Processing","created":"2020-05-28","cited_by_count":136},{"id":"2010.04104","title":"Learning the Pareto Front with Hypernetworks","created":"2020-10-08","cited_by_count":125},{"id":"2007.08668","title":"BRP-NAS: Prediction-based NAS using GCNs","created":"2020-07-16","cited_by_count":111},{"id":"1805.12168","title":"A Flexible Framework for Multi-Objective Bayesian Optimization using Random Scalarizations","created":"2018-05-30","cited_by_count":99},{"id":"2305.13035","title":"Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design","created":"2023-05-22","cited_by_count":89},{"id":"2109.10964","title":"Multi-Objective Bayesian Optimization over High-Dimensional Search Spaces","created":"2021-09-22","cited_by_count":87},{"id":"2103.10584","title":"HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmark","created":"2021-03-19","cited_by_count":84},{"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":"2011.09011","title":"AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling","created":"2020-11-18","cited_by_count":66},{"id":"2010.06313","title":"Controllable Pareto Multi-Task Learning","created":"2020-10-13","cited_by_count":51},{"id":"2106.10784","title":"iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients","created":"2021-06-21","cited_by_count":51},{"id":"2006.08198","title":"AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks","created":"2020-06-15","cited_by_count":50},{"id":"1907.04472","title":"The stochastic multi-gradient algorithm for multi-objective optimization and its application to supervised machine learning","created":"2019-07-10","cited_by_count":46},{"id":"2103.13392","title":"Scalable Pareto Front Approximation for Deep Multi-Objective Learning","created":"2021-03-24","cited_by_count":45},{"id":"2107.00860","title":"Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets","created":"2021-07-02","cited_by_count":33},{"id":"1606.02492","title":"Convolutional Neural Fabrics","created":"2016-06-08","cited_by_count":32},{"id":"1908.01748","title":"SqueezeNAS: Fast neural architecture search for faster semantic segmentation","created":"2019-08-05","cited_by_count":31},{"id":"2304.08612","title":"Bridging Discrete and Backpropagation: Straight-Through and Beyond","created":"2023-04-17","cited_by_count":31},{"id":"2210.09943","title":"Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition","created":"2022-10-18","cited_by_count":26},{"id":"2006.04492","title":"Speedy Performance Estimation for Neural Architecture Search","created":"2020-06-08","cited_by_count":24},{"id":"1910.11609","title":"Fast Hardware-Aware Neural Architecture Search","created":"2019-10-25","cited_by_count":23},{"id":"2106.12639","title":"Multi-objective Asynchronous Successive Halving","created":"2021-06-23","cited_by_count":23},{"id":"2212.01130","title":"Improving Pareto Front Learning via Multi-Sample Hypernetworks","created":"2022-12-02","cited_by_count":16},{"id":"2101.06658","title":"Trilevel Neural Architecture Search for Efficient Single Image Super-Resolution","created":"2021-01-17","cited_by_count":15},{"id":"2210.07998","title":"$\\Lambda$-DARTS: Mitigating Performance Collapse by Harmonizing Operation Selection among Cells","created":"2022-10-14","cited_by_count":15},{"id":"2206.01934","title":"Stochastic Multiple Target Sampling Gradient Descent","created":"2022-06-04","cited_by_count":14},{"id":"2106.05680","title":"A multi-objective perspective on jointly tuning hardware and hyperparameters","created":"2021-06-10","cited_by_count":12},{"id":"2110.08713","title":"Pareto Navigation Gradient Descent: a First-Order Algorithm for Optimization in Pareto Set","created":"2021-10-17","cited_by_count":12},{"id":"2001.06392","title":"Latency-Aware Differentiable Neural Architecture Search","created":"2020-01-17","cited_by_count":10},{"id":"2009.02009","title":"S3NAS: Fast NPU-aware Neural Architecture Search Methodology","created":"2020-09-04","cited_by_count":5},{"id":"2111.12299","title":"EH-DNAS: End-to-End Hardware-aware Differentiable Neural Architecture Search","created":"2021-11-24","cited_by_count":4},{"id":"2312.10440","title":"Weight-Entanglement Meets Gradient-Based Neural Architecture Search","created":"2023-12-16","cited_by_count":4},{"id":"2310.12145","title":"Fairer and More Accurate Tabular Models Through NAS","created":"2023-10-18","cited_by_count":3}],"next_cursor":null}