{"url":"/task/architecture-search","name":"Neural Architecture Search","slug":"architecture-search","description_markdown":"**Neural architecture search (NAS)** is a technique for automating the design of artificial neural networks (ANN), a widely used model in the field of machine learning. NAS essentially takes the process of a human manually tweaking a neural network and learning what works well, and automates this task to discover more complex architectures.\r\n\r\nImage Credit : [NAS with Reinforcement Learning](https://arxiv.org/abs/1611.01578)","categories":[{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":1915,"papers_with_code":859,"benchmarks":26,"benchmark_tables_in_archive":26,"benchmark_tables_shown":26,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":27,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/neural-architecture-search-on-imagenet","slug":"neural-architecture-search-on-imagenet","dataset":"ImageNet","dataset_url":"/dataset/imagenet","rows_in_archive":135,"metrics":["Top-1 Error Rate","Accuracy","Params","MACs","FLOPs"],"first_row_in_archive_order":{"model":"DeepMAD-50M","paper_title":"DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network","paper_url":"/paper/deepmad-mathematical-architecture-design-for","paper_date":"2023-03-05","arxiv_id":"2303.02165","code_links":[{"title":"alibaba/lightweight-neural-architecture-search","url":"https://github.com/alibaba/lightweight-neural-architecture-search"}],"syntology":null}},{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-201","slug":"neural-architecture-search-on-nas-bench-201","dataset":"NAS-Bench-201, ImageNet-16-120","dataset_url":"/dataset/nas-bench-201","rows_in_archive":49,"metrics":["Accuracy (Test)","Accuracy (Val)","Search time (s)"],"first_row_in_archive_order":{"model":"CR-LSO","paper_title":"CR-LSO: Convex Neural Architecture Optimization in the Latent Space of Graph Variational Autoencoder with Input Convex Neural Networks","paper_url":"/paper/cr-lso-convex-neural-architecture","paper_date":"2022-11-11","arxiv_id":"2211.05950","code_links":[{"title":"raoxuan-1998/cr-lso","url":"https://github.com/raoxuan-1998/cr-lso"}],"syntology":null}},{"leaderboard":"/sota/neural-architecture-search-on-cifar-10","slug":"neural-architecture-search-on-cifar-10","dataset":"CIFAR-10","dataset_url":"/dataset/cifar-10","rows_in_archive":41,"metrics":["Top-1 Error Rate","Parameters","FLOPS","Search Time (GPU days)","Accuracy (% )"],"first_row_in_archive_order":{"model":"NAT-M4","paper_title":"Neural Architecture Transfer","paper_url":"/paper/neural-architecture-transfer","paper_date":"2020-05-12","arxiv_id":"2005.05859","code_links":[{"title":"human-analysis/neural-architecture-transfer","url":"https://github.com/human-analysis/neural-architecture-transfer"},{"title":"awesomelemon/encas","url":"https://github.com/awesomelemon/encas"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}}},{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-201-2","slug":"neural-architecture-search-on-nas-bench-201-2","dataset":"NAS-Bench-201, CIFAR-100","dataset_url":"/dataset/nas-bench-201","rows_in_archive":40,"metrics":["Accuracy (Test)","Accuracy (Val)","Search time (s)"],"first_row_in_archive_order":{"model":"DiNAS","paper_title":"Multi-conditioned Graph Diffusion for Neural Architecture Search","paper_url":"/paper/multi-conditioned-graph-diffusion-for-neural","paper_date":"2024-03-09","arxiv_id":"2403.06020","code_links":[{"title":"rohanasthana/dinas","url":"https://github.com/rohanasthana/dinas"}],"syntology":{"n":7,"n_ran":4,"n_unverified":3,"n_pointer_only":0}}},{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-201-1","slug":"neural-architecture-search-on-nas-bench-201-1","dataset":"NAS-Bench-201, CIFAR-10","dataset_url":"/dataset/nas-bench-201","rows_in_archive":37,"metrics":["Accuracy (Test)","Accuracy (Val)","Search time (s)"],"first_row_in_archive_order":{"model":"DiNAS","paper_title":"Multi-conditioned Graph Diffusion for Neural Architecture Search","paper_url":"/paper/multi-conditioned-graph-diffusion-for-neural","paper_date":"2024-03-09","arxiv_id":"2403.06020","code_links":[{"title":"rohanasthana/dinas","url":"https://github.com/rohanasthana/dinas"}],"syntology":{"n":7,"n_ran":4,"n_unverified":3,"n_pointer_only":0}}},{"leaderboard":"/sota/architecture-search-on-cifar-10-image","slug":"architecture-search-on-cifar-10-image","dataset":"CIFAR-10 Image Classification","dataset_url":"/dataset/cifar-10","rows_in_archive":19,"metrics":["Percentage error","Params","FLOPS","Search Time (GPU days)"],"first_row_in_archive_order":{"model":"NAT-M4","paper_title":"Neural Architecture Transfer","paper_url":"/paper/neural-architecture-transfer","paper_date":"2020-05-12","arxiv_id":"2005.05859","code_links":[{"title":"human-analysis/neural-architecture-transfer","url":"https://github.com/human-analysis/neural-architecture-transfer"},{"title":"awesomelemon/encas","url":"https://github.com/awesomelemon/encas"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}}},{"leaderboard":"/sota/neural-architecture-search-on-cifar-100-1","slug":"neural-architecture-search-on-cifar-100-1","dataset":"CIFAR-100","dataset_url":"/dataset/cifar-100","rows_in_archive":13,"metrics":["Percentage Error","FLOPS","PARAMS","Search Time (GPU days)","Accuracy (% )"],"first_row_in_archive_order":{"model":"DNA-c","paper_title":"Blockwisely Supervised Neural Architecture Search with Knowledge Distillation","paper_url":"/paper/blockwisely-supervised-neural-architecture","paper_date":"2019-11-29","arxiv_id":"1911.13053","code_links":[{"title":"changlin31/DNA","url":"https://github.com/changlin31/DNA"}],"syntology":null}},{"leaderboard":"/sota/neural-architecture-search-on-nats-bench","slug":"neural-architecture-search-on-nats-bench","dataset":"NATS-Bench Topology, ImageNet16-120","dataset_url":"/dataset/nats-bench","rows_in_archive":11,"metrics":["Test Accuracy","Kendall's Tau","Spearman's Rho"],"first_row_in_archive_order":{"model":"LayerNAS","paper_title":"LayerNAS: Neural Architecture Search in Polynomial Complexity","paper_url":"/paper/layernas-neural-architecture-search-in","paper_date":"2023-04-23","arxiv_id":"2304.11517","code_links":[],"syntology":null}},{"leaderboard":"/sota/neural-architecture-search-on-nats-bench-1","slug":"neural-architecture-search-on-nats-bench-1","dataset":"NATS-Bench Topology, CIFAR-10","dataset_url":"/dataset/nats-bench","rows_in_archive":11,"metrics":["Test Accuracy","Kendall's Tau","Spearman's Rho"],"first_row_in_archive_order":{"model":"LayerNAS","paper_title":"LayerNAS: Neural Architecture Search in Polynomial Complexity","paper_url":"/paper/layernas-neural-architecture-search-in","paper_date":"2023-04-23","arxiv_id":"2304.11517","code_links":[],"syntology":null}},{"leaderboard":"/sota/neural-architecture-search-on-nats-bench-2","slug":"neural-architecture-search-on-nats-bench-2","dataset":"NATS-Bench Topology, CIFAR-100","dataset_url":"/dataset/nats-bench","rows_in_archive":11,"metrics":["Test Accuracy","Kendall's Tau","Spearman's Rho"],"first_row_in_archive_order":{"model":"LayerNAS","paper_title":"LayerNAS: Neural Architecture Search in Polynomial Complexity","paper_url":"/paper/layernas-neural-architecture-search-in","paper_date":"2023-04-23","arxiv_id":"2304.11517","code_links":[],"syntology":null}},{"leaderboard":"/sota/neural-architecture-search-on-food-101","slug":"neural-architecture-search-on-food-101","dataset":"Food-101","dataset_url":"/dataset/food-101","rows_in_archive":5,"metrics":["Accuracy (%)","FLOPS","PARAMS","Accuracy (% )"],"first_row_in_archive_order":{"model":"NAT-M4","paper_title":"Neural Architecture Transfer","paper_url":"/paper/neural-architecture-transfer","paper_date":"2020-05-12","arxiv_id":"2005.05859","code_links":[{"title":"human-analysis/neural-architecture-transfer","url":"https://github.com/human-analysis/neural-architecture-transfer"},{"title":"awesomelemon/encas","url":"https://github.com/awesomelemon/encas"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}}},{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-101","slug":"neural-architecture-search-on-nas-bench-101","dataset":"NAS-Bench-101","dataset_url":"/dataset/nas-bench-101","rows_in_archive":5,"metrics":["Accuracy (%)","Spearman Correlation"],"first_row_in_archive_order":{"model":"DiNAS","paper_title":"Multi-conditioned Graph Diffusion for Neural Architecture Search","paper_url":"/paper/multi-conditioned-graph-diffusion-for-neural","paper_date":"2024-03-09","arxiv_id":"2403.06020","code_links":[{"title":"rohanasthana/dinas","url":"https://github.com/rohanasthana/dinas"}],"syntology":{"n":7,"n_ran":4,"n_unverified":3,"n_pointer_only":0}}},{"leaderboard":"/sota/neural-architecture-search-on-nats-bench-size-1","slug":"neural-architecture-search-on-nats-bench-size-1","dataset":"NATS-Bench Size, CIFAR-10","dataset_url":"/dataset/cifar-10","rows_in_archive":5,"metrics":["Kendall's Tau","Spearman's Rho","Pearson R","Acc. (test)","Test Accuracy","Validation Accuracy"],"first_row_in_archive_order":{"model":"GreenMachine-3","paper_title":"GreenMachine: Automatic Design of Zero-Cost Proxies for Energy-Efficient NAS","paper_url":"/paper/greenmachine-automatic-design-of-zero-cost","paper_date":"2024-11-22","arxiv_id":"2411.15290","code_links":[{"title":"RodriguesGabriel/greenmachine","url":"https://github.com/RodriguesGabriel/greenmachine"}],"syntology":null}},{"leaderboard":"/sota/neural-architecture-search-on-nats-bench-size-2","slug":"neural-architecture-search-on-nats-bench-size-2","dataset":"NATS-Bench Size, CIFAR-100","dataset_url":"/dataset/nats-bench","rows_in_archive":5,"metrics":["Kendall's Tau","Spearman's Rho","Pearson R","Acc. (test)","Test Accuracy","Validation Accuracy"],"first_row_in_archive_order":{"model":"GreenMachine-2","paper_title":"GreenMachine: Automatic Design of Zero-Cost Proxies for Energy-Efficient NAS","paper_url":"/paper/greenmachine-automatic-design-of-zero-cost","paper_date":"2024-11-22","arxiv_id":"2411.15290","code_links":[{"title":"RodriguesGabriel/greenmachine","url":"https://github.com/RodriguesGabriel/greenmachine"}],"syntology":null}},{"leaderboard":"/sota/neural-architecture-search-on-cinic-10","slug":"neural-architecture-search-on-cinic-10","dataset":"CINIC-10","dataset_url":"/dataset/cinic-10","rows_in_archive":4,"metrics":["Accuracy (%)","FLOPS","PARAMS"],"first_row_in_archive_order":{"model":"NAT-M4","paper_title":"Neural Architecture Transfer","paper_url":"/paper/neural-architecture-transfer","paper_date":"2020-05-12","arxiv_id":"2005.05859","code_links":[{"title":"human-analysis/neural-architecture-transfer","url":"https://github.com/human-analysis/neural-architecture-transfer"},{"title":"awesomelemon/encas","url":"https://github.com/awesomelemon/encas"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}}},{"leaderboard":"/sota/neural-architecture-search-on-dtd","slug":"neural-architecture-search-on-dtd","dataset":"DTD","dataset_url":"/dataset/dtd","rows_in_archive":4,"metrics":["Accuracy (%)","FLOPS","PARAMS"],"first_row_in_archive_order":{"model":"NAT-M4","paper_title":"Neural Architecture Transfer","paper_url":"/paper/neural-architecture-transfer","paper_date":"2020-05-12","arxiv_id":"2005.05859","code_links":[{"title":"human-analysis/neural-architecture-transfer","url":"https://github.com/human-analysis/neural-architecture-transfer"},{"title":"awesomelemon/encas","url":"https://github.com/awesomelemon/encas"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}}},{"leaderboard":"/sota/neural-architecture-search-on-fgvc-aircraft","slug":"neural-architecture-search-on-fgvc-aircraft","dataset":"FGVC Aircraft","dataset_url":"/dataset/fgvc-aircraft-1","rows_in_archive":4,"metrics":["Accuracy (%)","FLOPS","PARAMS"],"first_row_in_archive_order":{"model":"NAT-M4","paper_title":"Neural Architecture Transfer","paper_url":"/paper/neural-architecture-transfer","paper_date":"2020-05-12","arxiv_id":"2005.05859","code_links":[{"title":"human-analysis/neural-architecture-transfer","url":"https://github.com/human-analysis/neural-architecture-transfer"},{"title":"awesomelemon/encas","url":"https://github.com/awesomelemon/encas"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}}},{"leaderboard":"/sota/neural-architecture-search-on-nats-bench-size-3","slug":"neural-architecture-search-on-nats-bench-size-3","dataset":"NATS-Bench Size, ImageNet16-120","dataset_url":"/dataset/nats-bench","rows_in_archive":4,"metrics":["Kendall's Tau","Spearman's Rho","Test Accuracy","Validation Accuracy"],"first_row_in_archive_order":{"model":"GreenMachine-2","paper_title":"GreenMachine: Automatic Design of Zero-Cost Proxies for Energy-Efficient NAS","paper_url":"/paper/greenmachine-automatic-design-of-zero-cost","paper_date":"2024-11-22","arxiv_id":"2411.15290","code_links":[{"title":"RodriguesGabriel/greenmachine","url":"https://github.com/RodriguesGabriel/greenmachine"}],"syntology":null}},{"leaderboard":"/sota/neural-architecture-search-on-oxford-102","slug":"neural-architecture-search-on-oxford-102","dataset":"Oxford 102 Flowers","dataset_url":"/dataset/oxford-102-flower","rows_in_archive":4,"metrics":["Accuracy (%)","FLOPS","PARAMS"],"first_row_in_archive_order":{"model":"NAT-M4","paper_title":"Neural Architecture Transfer","paper_url":"/paper/neural-architecture-transfer","paper_date":"2020-05-12","arxiv_id":"2005.05859","code_links":[{"title":"human-analysis/neural-architecture-transfer","url":"https://github.com/human-analysis/neural-architecture-transfer"},{"title":"awesomelemon/encas","url":"https://github.com/awesomelemon/encas"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}}},{"leaderboard":"/sota/neural-architecture-search-on-oxford-iiit","slug":"neural-architecture-search-on-oxford-iiit","dataset":"Oxford-IIIT Pet Dataset","dataset_url":"/dataset/oxford-iiit-pets","rows_in_archive":4,"metrics":["Accuracy (%)","FLOPS","PARAMS"],"first_row_in_archive_order":{"model":"NAT-M4","paper_title":"Neural Architecture Transfer","paper_url":"/paper/neural-architecture-transfer","paper_date":"2020-05-12","arxiv_id":"2005.05859","code_links":[{"title":"human-analysis/neural-architecture-transfer","url":"https://github.com/human-analysis/neural-architecture-transfer"},{"title":"awesomelemon/encas","url":"https://github.com/awesomelemon/encas"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}}},{"leaderboard":"/sota/neural-architecture-search-on-stanford-cars","slug":"neural-architecture-search-on-stanford-cars","dataset":"Stanford Cars","dataset_url":"/dataset/stanford-cars","rows_in_archive":4,"metrics":["Accuracy (%)","FLOPS","PARAMS"],"first_row_in_archive_order":{"model":"NAT-M4","paper_title":"Neural Architecture Transfer","paper_url":"/paper/neural-architecture-transfer","paper_date":"2020-05-12","arxiv_id":"2005.05859","code_links":[{"title":"human-analysis/neural-architecture-transfer","url":"https://github.com/human-analysis/neural-architecture-transfer"},{"title":"awesomelemon/encas","url":"https://github.com/awesomelemon/encas"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}}},{"leaderboard":"/sota/neural-architecture-search-on-stl-10","slug":"neural-architecture-search-on-stl-10","dataset":"STL-10","dataset_url":"/dataset/stl-10","rows_in_archive":4,"metrics":["Accuracy (%)","FLOPS","PARAMS"],"first_row_in_archive_order":{"model":"NAT-M4","paper_title":"Neural Architecture Transfer","paper_url":"/paper/neural-architecture-transfer","paper_date":"2020-05-12","arxiv_id":"2005.05859","code_links":[{"title":"human-analysis/neural-architecture-transfer","url":"https://github.com/human-analysis/neural-architecture-transfer"},{"title":"awesomelemon/encas","url":"https://github.com/awesomelemon/encas"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}}},{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-201-3","slug":"neural-architecture-search-on-nas-bench-201-3","dataset":"NAS-Bench-201","dataset_url":"/dataset/nas-bench-201","rows_in_archive":2,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"Improved FireFly Algorithme","paper_title":"Improving Neural Architecture Search by Mixing a FireFly algorithm with a Training Free Evaluation","paper_url":"/paper/improving-neural-architecture-search-by","paper_date":"2022-07-18","arxiv_id":null,"code_links":[{"title":"nassimmokhtari/Improved-FireFly-Algorithm","url":"https://github.com/nassimmokhtari/Improved-FireFly-Algorithm"}],"syntology":null}},{"leaderboard":"/sota/neural-architecture-search-on-lidc-idri","slug":"neural-architecture-search-on-lidc-idri","dataset":"LIDC-IDRI","dataset_url":"/dataset/lidc-idri","rows_in_archive":1,"metrics":["F1 score","Specificity (VEB+)"],"first_row_in_archive_order":{"model":"NASLung (ours)","paper_title":"Learning Efficient, Explainable and Discriminative Representations for Pulmonary Nodules Classification","paper_url":"/paper/learning-efficient-explainable-and","paper_date":"2021-01-19","arxiv_id":"2101.07429","code_links":[{"title":"fei-hdu/NAS-Lung","url":"https://github.com/fei-hdu/NAS-Lung"}],"syntology":null}},{"leaderboard":"/sota/neural-architecture-search-on-mnist","slug":"neural-architecture-search-on-mnist","dataset":"MNIST","dataset_url":"/dataset/mnist","rows_in_archive":1,"metrics":["R2"],"first_row_in_archive_order":{"model":"Sparse Neural Network","paper_title":"Structural Analysis of Sparse Neural Networks","paper_url":"/paper/structural-analysis-of-sparse-neural-networks","paper_date":"2019-10-16","arxiv_id":"1910.07225","code_links":[],"syntology":null}},{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-301","slug":"neural-architecture-search-on-nas-bench-301","dataset":"NAS-Bench-301","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy (Val)"],"first_row_in_archive_order":{"model":"DiNAS","paper_title":"Multi-conditioned Graph Diffusion for Neural Architecture Search","paper_url":"/paper/multi-conditioned-graph-diffusion-for-neural","paper_date":"2024-03-09","arxiv_id":"2403.06020","code_links":[{"title":"rohanasthana/dinas","url":"https://github.com/rohanasthana/dinas"}],"syntology":{"n":7,"n_ran":4,"n_unverified":3,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/cifar-10","name":"CIFAR-10","full_name":"CIFAR-10","num_papers_in_archive":16145},{"url":"/dataset/imagenet","name":"ImageNet","full_name":"","num_papers_in_archive":15430},{"url":"/dataset/cifar-100","name":"CIFAR-100","full_name":"","num_papers_in_archive":9045},{"url":"/dataset/mnist","name":"MNIST","full_name":"","num_papers_in_archive":7651},{"url":"/dataset/oxford-102-flower","name":"Oxford 102 Flower","full_name":"102 Category Flower Dataset","num_papers_in_archive":1307},{"url":"/dataset/stl-10","name":"STL-10","full_name":"Self-Taught Learning 10","num_papers_in_archive":1092},{"url":"/dataset/dtd","name":"DTD","full_name":"Describable Textures Dataset","num_papers_in_archive":870},{"url":"/dataset/food-101","name":"Food-101","full_name":"","num_papers_in_archive":805},{"url":"/dataset/stanford-cars","name":"Stanford Cars","full_name":"","num_papers_in_archive":790},{"url":"/dataset/fgvc-aircraft-1","name":"FGVC-Aircraft","full_name":"","num_papers_in_archive":520},{"url":"/dataset/nas-bench-201","name":"NAS-Bench-201","full_name":"","num_papers_in_archive":260},{"url":"/dataset/lidc-idri","name":"LIDC-IDRI","full_name":"LIDC-IDRI","num_papers_in_archive":240},{"url":"/dataset/cinic-10","name":"CINIC-10","full_name":"CINIC-10","num_papers_in_archive":197},{"url":"/dataset/nas-bench-101","name":"NAS-Bench-101","full_name":"","num_papers_in_archive":152},{"url":"/dataset/oxford-iiit-pets","name":"Oxford-IIIT Pet Dataset","full_name":"Oxford-IIIT Pet Dataset","num_papers_in_archive":90},{"url":"/dataset/oxford-iiit-pets-1","name":"Oxford-IIIT Pets","full_name":"","num_papers_in_archive":59},{"url":"/dataset/nats-bench","name":"NATS-Bench","full_name":"","num_papers_in_archive":43},{"url":"/dataset/visual-wake-words","name":"Visual Wake Words","full_name":"","num_papers_in_archive":40},{"url":"/dataset/nas-bench-1shot1","name":"NAS-Bench-1Shot1","full_name":"","num_papers_in_archive":24},{"url":"/dataset/mir-1k","name":"MIR-1K","full_name":"","num_papers_in_archive":21},{"url":"/dataset/transnas-bench-101","name":"TransNAS-Bench-101","full_name":"","num_papers_in_archive":14},{"url":"/dataset/codebrim","name":"CODEBRIM","full_name":"COncrete DEfect BRidge IMage Dataset","num_papers_in_archive":9},{"url":"/dataset/freiburg-groceries","name":"Freiburg Groceries","full_name":"Freiburg Groceries","num_papers_in_archive":7},{"url":"/dataset/farsbase-kbp","name":"FarsBase-KBP","full_name":"","num_papers_in_archive":2},{"url":"/dataset/ea-has-bench","name":"EA-HAS-Bench","full_name":"Energy-Aware Hyperparameter and Architecture Search Benchmark","num_papers_in_archive":1},{"url":"/dataset/hw-nas-bench","name":"HW-NAS-Bench","full_name":"","num_papers_in_archive":1},{"url":"/dataset/jhu-costar-block-stacking-dataset","name":"JHU CoSTAR Block Stacking Dataset","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/activation-function-synthesis","name":"Activation Function Synthesis"}],"parent_tasks":[{"url":"/task/automl","name":"AutoML"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":859,"tagged_in_all":1915,"items":[{"url":"/paper/proximal-policy-optimization-algorithms","title":"Proximal Policy Optimization Algorithms","date":"2017-07-20","arxiv_id":"1707.06347","repositories_listed":188,"syntology":{"n":176,"n_ran":99,"n_unverified":77,"n_pointer_only":94}},{"url":"/paper/efficientnet-rethinking-model-scaling-for","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","date":"2019-05-28","arxiv_id":"1905.11946","repositories_listed":144,"syntology":{"n":302,"n_ran":171,"n_unverified":131,"n_pointer_only":112}},{"url":"/paper/searching-for-mobilenetv3","title":"Searching for MobileNetV3","date":"2019-05-06","arxiv_id":"1905.02244","repositories_listed":67,"syntology":{"n":105,"n_ran":58,"n_unverified":47,"n_pointer_only":46}},{"url":"/paper/darts-differentiable-architecture-search","title":"DARTS: Differentiable Architecture Search","date":"2018-06-24","arxiv_id":"1806.09055","repositories_listed":59,"syntology":{"n":156,"n_ran":66,"n_unverified":90,"n_pointer_only":48}},{"url":"/paper/mnasnet-platform-aware-neural-architecture","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","date":"2018-07-31","arxiv_id":"1807.11626","repositories_listed":29,"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":2}},{"url":"/paper/efficient-neural-architecture-search-via-1","title":"Efficient Neural Architecture Search via Parameter Sharing","date":"2018-02-09","arxiv_id":"1802.03268","repositories_listed":28,"syntology":{"n":38,"n_ran":18,"n_unverified":20,"n_pointer_only":25}},{"url":"/paper/efficientnetv2-smaller-models-and-faster","title":"EfficientNetV2: Smaller Models and Faster Training","date":"2021-04-01","arxiv_id":"2104.00298","repositories_listed":26,"syntology":{"n":79,"n_ran":41,"n_unverified":38,"n_pointer_only":10}},{"url":"/paper/proxylessnas-direct-neural-architecture","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","date":"2018-12-02","arxiv_id":"1812.00332","repositories_listed":23,"syntology":{"n":27,"n_ran":5,"n_unverified":22,"n_pointer_only":0}},{"url":"/paper/progressive-neural-architecture-search","title":"Progressive Neural Architecture Search","date":"2017-12-02","arxiv_id":"1712.00559","repositories_listed":18,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/learning-transferable-architectures-for","title":"Learning Transferable Architectures for Scalable Image Recognition","date":"2017-07-21","arxiv_id":"1707.07012","repositories_listed":17,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/spinenet-learning-scale-permuted-backbone-for","title":"SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization","date":"2019-12-10","arxiv_id":"1912.05027","repositories_listed":13,"syntology":null},{"url":"/paper/auto-keras-efficient-neural-architecture","title":"Auto-Keras: An Efficient Neural Architecture Search System","date":"2018-06-27","arxiv_id":"1806.10282","repositories_listed":13,"syntology":{"n":6,"n_ran":3,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/auto-deeplab-hierarchical-neural-architecture","title":"Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation","date":"2019-01-10","arxiv_id":"1901.02985","repositories_listed":12,"syntology":{"n":4,"n_ran":1,"n_unverified":3,"n_pointer_only":1}},{"url":"/paper/amc-automl-for-model-compression-and","title":"AMC: AutoML for Model Compression and Acceleration on Mobile Devices","date":"2018-02-10","arxiv_id":"1802.03494","repositories_listed":12,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/learning-efficient-convolutional-networks","title":"Learning Efficient Convolutional Networks through Network Slimming","date":"2017-08-22","arxiv_id":"1708.06519","repositories_listed":12,"syntology":null},{"url":"/paper/neural-architecture-search-with-reinforcement","title":"Neural Architecture Search with Reinforcement Learning","date":"2016-11-05","arxiv_id":"1611.01578","repositories_listed":12,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/once-for-all-train-one-network-and-specialize","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","date":"2019-08-26","arxiv_id":"1908.09791","repositories_listed":10,"syntology":{"n":34,"n_ran":4,"n_unverified":30,"n_pointer_only":0}},{"url":"/paper/network-slimming-by-slimmable-networks","title":"AutoSlim: Towards One-Shot Architecture Search for Channel Numbers","date":"2019-03-27","arxiv_id":"1903.11728","repositories_listed":10,"syntology":null},{"url":"/paper/bam-bottleneck-attention-module","title":"BAM: Bottleneck Attention Module","date":"2018-07-17","arxiv_id":"1807.06514","repositories_listed":10,"syntology":null},{"url":"/paper/isynet-convolutional-neural-networks-design","title":"ISyNet: Convolutional Neural Networks design for AI accelerator","date":"2021-09-04","arxiv_id":"2109.01932","repositories_listed":9,"syntology":null},{"url":"/paper/single-path-nas-designing-hardware-efficient","title":"Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours","date":"2019-04-05","arxiv_id":"1904.02877","repositories_listed":9,"syntology":{"n":16,"n_ran":1,"n_unverified":15,"n_pointer_only":0}},{"url":"/paper/exploring-randomly-wired-neural-networks-for","title":"Exploring Randomly Wired Neural Networks for Image Recognition","date":"2019-04-02","arxiv_id":"1904.01569","repositories_listed":9,"syntology":{"n":31,"n_ran":0,"n_unverified":31,"n_pointer_only":0}},{"url":"/paper/pc-darts-partial-channel-connections-for","title":"PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search","date":"2019-07-12","arxiv_id":"1907.05737","repositories_listed":8,"syntology":{"n":11,"n_ran":1,"n_unverified":10,"n_pointer_only":1}},{"url":"/paper/nas-fpn-learning-scalable-feature-pyramid","title":"NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection","date":"2019-04-16","arxiv_id":"1904.07392","repositories_listed":8,"syntology":null},{"url":"/paper/mobilenetv4-universal-models-for-the-mobile","title":"MobileNetV4 -- Universal Models for the Mobile Ecosystem","date":"2024-04-16","arxiv_id":"2404.10518","repositories_listed":7,"syntology":{"n":13,"n_ran":6,"n_unverified":7,"n_pointer_only":1}},{"url":"/paper/renas-relativistic-evaluation-of-neural","title":"ReNAS: Relativistic Evaluation of Neural Architecture Search","date":"2021-06-19","arxiv_id":null,"repositories_listed":7,"syntology":null},{"url":"/paper/autogluon-tabular-robust-and-accurate-automl","title":"AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data","date":"2020-03-13","arxiv_id":"2003.06505","repositories_listed":7,"syntology":{"n":11,"n_ran":0,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/searching-efficient-3d-architectures-with","title":"Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution","date":"2020-07-31","arxiv_id":"2007.16100","repositories_listed":6,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/sp-nas-serial-to-parallel-backbone-search-for","title":"SP-NAS: Serial-to-Parallel Backbone Search for Object Detection","date":"2020-06-01","arxiv_id":null,"repositories_listed":6,"syntology":null},{"url":"/paper/hournas-extremely-fast-neural-architecture","title":"HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens","date":"2020-05-29","arxiv_id":"2005.14446","repositories_listed":6,"syntology":null}],"syntology_records":21,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}