{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/network-pruning","name":"Network Pruning","slug":"network-pruning","description_markdown":"**Network Pruning** is a popular approach to reduce a heavy network to obtain a light-weight form by removing redundancy in the heavy network. In this approach, a complex over-parameterized network is first trained, then pruned based on come criterions, and finally fine-tuned to achieve comparable performance with reduced parameters.\n\n\n<span class=\"description-source\">Source: [Ensemble Knowledge Distillation for Learning Improved and Efficient Networks ](https://arxiv.org/abs/1909.08097)</span>","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":534,"papers_with_code":239,"benchmarks":5,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"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":5,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/network-pruning-on-imagenet","slug":"network-pruning-on-imagenet","dataset":"ImageNet","dataset_url":"/dataset/imagenet","rows_in_archive":16,"metrics":["Accuracy","GFLOPs","MParams"],"first_row_in_archive_order":{"model":"ResNet50-2.3 GFLOPs","paper_title":"Pruning Filters for Efficient ConvNets","paper_url":"/paper/pruning-filters-for-efficient-convnets","paper_date":"2016-08-31","arxiv_id":"1608.08710","code_links":[{"title":"PaddlePaddle/PaddleOCR","url":"https://github.com/PaddlePaddle/PaddleOCR"},{"title":"VainF/Torch-Pruning","url":"https://github.com/VainF/Torch-Pruning"},{"title":"he-y/filter-pruning-geometric-median","url":"https://github.com/he-y/filter-pruning-geometric-median"},{"title":"midasklr/yolov5prune","url":"https://github.com/midasklr/yolov5prune"},{"title":"oandrienko/fast-semantic-segmentation","url":"https://github.com/oandrienko/fast-semantic-segmentation"},{"title":"marcoancona/TorchPruner","url":"https://github.com/marcoancona/TorchPruner"},{"title":"mingsun-tse/regularization-pruning","url":"https://github.com/mingsun-tse/regularization-pruning"},{"title":"Adlik/model_optimizer","url":"https://github.com/Adlik/model_optimizer"},{"title":"guoxiaolu/model_compression","url":"https://github.com/guoxiaolu/model_compression"},{"title":"matthew-mcateer/Keras_pruning","url":"https://github.com/matthew-mcateer/Keras_pruning"},{"title":"AlumLuther/PruningFilters","url":"https://github.com/AlumLuther/PruningFilters"},{"title":"EstherBear/implementation-of-pruning-filters","url":"https://github.com/EstherBear/implementation-of-pruning-filters"},{"title":"arturjordao/PruningNeuralNetworks","url":"https://github.com/arturjordao/PruningNeuralNetworks"},{"title":"lehduong/ginp","url":"https://github.com/lehduong/ginp"},{"title":"lehduong/kesi","url":"https://github.com/lehduong/kesi"},{"title":"siyuan0/pytorch_model_prune","url":"https://github.com/siyuan0/pytorch_model_prune"},{"title":"mvpzhangqiu/yolov5prune","url":"https://github.com/mvpzhangqiu/yolov5prune"},{"title":"cailinhang/2018-Graduation-Project","url":"https://github.com/cailinhang/2018-Graduation-Project"},{"title":"AnishDelft/ModelCompression","url":"https://github.com/AnishDelft/ModelCompression"},{"title":"mattangus/fast-semantic-segmentation","url":"https://github.com/mattangus/fast-semantic-segmentation"},{"title":"prerakmody/CS4180-DL","url":"https://github.com/prerakmody/CS4180-DL"}],"syntology":{"n":36,"n_ran":23,"n_constructed":4,"n_ran_checked":9,"n_instrument":14,"n_unverified":13,"n_honours":1,"n_violates":1,"n_no_contract":7,"n_pointer_only":22,"phrase":"23 ran (of which 4 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 1 violated, 7 with no contract checked; 14 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/pruning-filters-for-efficient-convnets#ran","syntology_url":"https://syntology.ai/paper/1608.08710","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1608.08710"}},"official":null}}},{"leaderboard":"/sota/network-pruning-on-imagenet-resnet-50-90","slug":"network-pruning-on-imagenet-resnet-50-90","dataset":"ImageNet - ResNet 50 - 90% sparsity","dataset_url":null,"rows_in_archive":9,"metrics":["Top-1 Accuracy"],"first_row_in_archive_order":{"model":"Feather","paper_title":"Feather: An Elegant Solution to Effective DNN Sparsification","paper_url":"/paper/feather-an-elegant-solution-to-effective-dnn","paper_date":"2023-10-03","arxiv_id":"2310.02448","code_links":[{"title":"athglentis/feather","url":"https://github.com/athglentis/feather"}],"syntology":null}},{"leaderboard":"/sota/network-pruning-on-cifar-100","slug":"network-pruning-on-cifar-100","dataset":"CIFAR-100","dataset_url":"/dataset/cifar-100","rows_in_archive":5,"metrics":["Accuracy","GFLOPs","Inference Time (ms)"],"first_row_in_archive_order":{"model":"Dense","paper_title":"AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks","paper_url":"/paper/ac-dc-alternating-compressed-decompressed","paper_date":"2021-06-23","arxiv_id":"2106.12379","code_links":[{"title":"IST-DASLab/ACDC","url":"https://github.com/IST-DASLab/ACDC"},{"title":"IST-DASLab/sparseprop","url":"https://github.com/IST-DASLab/sparseprop"}],"syntology":{"n":5,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/ac-dc-alternating-compressed-decompressed#ran","syntology_url":"https://syntology.ai/paper/2106.12379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.12379"}},"official":{"repos":["IST-DASLab/ACDC"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}}},{"leaderboard":"/sota/network-pruning-on-cifar-10","slug":"network-pruning-on-cifar-10","dataset":"CIFAR-10","dataset_url":"/dataset/cifar-10","rows_in_archive":4,"metrics":["Accuracy","GFLOPs","Inference Time (ms)"],"first_row_in_archive_order":{"model":"TAS-pruned ResNet-110","paper_title":"Network Pruning via Transformable Architecture Search","paper_url":"/paper/network-pruning-via-transformable","paper_date":"2019-05-23","arxiv_id":"1905.09717","code_links":[{"title":"D-X-Y/GDAS","url":"https://github.com/D-X-Y/GDAS"},{"title":"D-X-Y/NAS-Projects","url":"https://github.com/D-X-Y/NAS-Projects"},{"title":"D-X-Y/AutoDL-Projects","url":"https://github.com/D-X-Y/AutoDL-Projects"},{"title":"xxlya/COS598D_Assignment1","url":"https://github.com/xxlya/COS598D_Assignment1"}],"syntology":null}},{"leaderboard":"/sota/network-pruning-on-mnist","slug":"network-pruning-on-mnist","dataset":"MNIST","dataset_url":"/dataset/mnist","rows_in_archive":1,"metrics":["Avg #Steps"],"first_row_in_archive_order":{"model":"FFN-ShapleyPruned","paper_title":"Analysing Neural Network Topologies: a Game Theoretic Approach","paper_url":"/paper/analysing-neural-network-topologies-a-game","paper_date":"2019-04-17","arxiv_id":"1904.08166","code_links":[],"syntology":null}}],"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/netzschleuder","name":"Netzschleuder","full_name":"network catalogue, repository and centrifuge","num_papers_in_archive":5}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":6,"rows_per_page":100,"shown":100,"of":534,"of_with_code":239,"tagged_in_all":534,"counts":{"archive_papers_tagged":534,"with_a_code_link":239,"where_syntology_ran_a_sample":83,"not_listed_spam_title":0,"listed":534,"listed_where_code_ran":83,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":65,"every_run_a_failure_of_syntologys_instrument":18,"listed_with_a_run_with_no_instrument_failure":65,"listed_every_run_a_failure_of_syntologys_instrument":18,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/squeezenet-alexnet-level-accuracy-with-50x","slug":"squeezenet-alexnet-level-accuracy-with-50x","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","date":"2016-02-24","arxiv_id":"1602.07360","repositories_listed":59,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/squeezenet-alexnet-level-accuracy-with-50x#ran","syntology_url":"https://syntology.ai/paper/1602.07360","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1602.07360"}},"official":{"repos":["DT42/squeezenet_demo","DeepScale/SqueezeNet","Element-Research/dpnn","ejlb/squeezenet-chainer","haria/SqueezeNet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/the-lottery-ticket-hypothesis-finding-sparse","slug":"the-lottery-ticket-hypothesis-finding-sparse","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","date":"2018-03-09","arxiv_id":"1803.03635","repositories_listed":24,"syntology":{"n":25,"n_ran":12,"n_constructed":2,"n_ran_checked":10,"n_instrument":2,"n_unverified":13,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":6,"phrase":"12 ran (of which 2 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/the-lottery-ticket-hypothesis-finding-sparse#ran","syntology_url":"https://syntology.ai/paper/1803.03635","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.03635"}},"official":null}},{"url":"/paper/pruning-filters-for-efficient-convnets","slug":"pruning-filters-for-efficient-convnets","title":"Pruning Filters for Efficient ConvNets","date":"2016-08-31","arxiv_id":"1608.08710","repositories_listed":21,"syntology":{"n":36,"n_ran":23,"n_constructed":4,"n_ran_checked":9,"n_instrument":14,"n_unverified":13,"n_honours":1,"n_violates":1,"n_no_contract":7,"n_pointer_only":22,"phrase":"23 ran (of which 4 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 1 violated, 7 with no contract checked; 14 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/pruning-filters-for-efficient-convnets#ran","syntology_url":"https://syntology.ai/paper/1608.08710","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1608.08710"}},"official":null}},{"url":"/paper/deep-compression-compressing-deep-neural","slug":"deep-compression-compressing-deep-neural","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","date":"2015-10-01","arxiv_id":"1510.00149","repositories_listed":15,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/deep-compression-compressing-deep-neural#ran","syntology_url":"https://syntology.ai/paper/1510.00149","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1510.00149"}},"official":null}},{"url":"/paper/snip-single-shot-network-pruning-based-on","slug":"snip-single-shot-network-pruning-based-on","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","date":"2018-10-04","arxiv_id":"1810.02340","repositories_listed":8,"syntology":{"n":12,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/snip-single-shot-network-pruning-based-on#ran","syntology_url":"https://syntology.ai/paper/1810.02340","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.02340"}},"official":{"repos":["namhoonlee/snip-public"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/a-simple-and-effective-pruning-approach-for","slug":"a-simple-and-effective-pruning-approach-for","title":"A Simple and Effective Pruning Approach for Large Language Models","date":"2023-06-20","arxiv_id":"2306.11695","repositories_listed":7,"syntology":{"n":22,"n_ran":9,"n_constructed":5,"n_ran_checked":6,"n_instrument":3,"n_unverified":13,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":9,"phrase":"9 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/a-simple-and-effective-pruning-approach-for#ran","syntology_url":"https://syntology.ai/paper/2306.11695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.11695"}},"official":{"repos":["locuslab/wanda"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/manifold-regularized-dynamic-network-pruning","slug":"manifold-regularized-dynamic-network-pruning","title":"Manifold Regularized Dynamic Network Pruning","date":"2021-03-10","arxiv_id":"2103.05861","repositories_listed":7,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/manifold-regularized-dynamic-network-pruning#ran","syntology_url":"https://syntology.ai/paper/2103.05861","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.05861"}},"official":null}},{"url":"/paper/scop-scientific-control-for-reliable-neural","slug":"scop-scientific-control-for-reliable-neural","title":"SCOP: Scientific Control for Reliable Neural Network Pruning","date":"2020-10-21","arxiv_id":"2010.10732","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scop-scientific-control-for-reliable-neural#ran","syntology_url":"https://syntology.ai/paper/2010.10732","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.10732"}},"official":{"repos":["huawei-noah/Pruning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/movement-pruning-adaptive-sparsity-by-fine","slug":"movement-pruning-adaptive-sparsity-by-fine","title":"Movement Pruning: Adaptive Sparsity by Fine-Tuning","date":"2020-05-15","arxiv_id":"2005.07683","repositories_listed":4,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/movement-pruning-adaptive-sparsity-by-fine#ran","syntology_url":"https://syntology.ai/paper/2005.07683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.07683"}},"official":{"repos":["huggingface/transformers"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/similarity-of-neural-networks-with-gradients","slug":"similarity-of-neural-networks-with-gradients","title":"Similarity of Neural Networks with Gradients","date":"2020-03-25","arxiv_id":"2003.11498","repositories_listed":4,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/similarity-of-neural-networks-with-gradients#ran","syntology_url":"https://syntology.ai/paper/2003.11498","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.11498"}},"official":{"repos":["amzn/xfer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/on-pruning-adversarially-robust-neural","slug":"on-pruning-adversarially-robust-neural","title":"HYDRA: Pruning Adversarially Robust Neural Networks","date":"2020-02-24","arxiv_id":"2002.10509","repositories_listed":4,"syntology":{"n":19,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":15,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":17,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 15 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/on-pruning-adversarially-robust-neural#ran","syntology_url":"https://syntology.ai/paper/2002.10509","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.10509"}},"official":{"repos":["inspire-group/compactness-robustness"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/190600586","slug":"190600586","title":"Discovering Neural Wirings","date":"2019-06-03","arxiv_id":"1906.00586","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/190600586#ran","syntology_url":"https://syntology.ai/paper/1906.00586","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.00586"}},"official":{"repos":["allenai/dnw"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/network-pruning-via-transformable","slug":"network-pruning-via-transformable","title":"Network Pruning via Transformable Architecture Search","date":"2019-05-23","arxiv_id":"1905.09717","repositories_listed":4,"syntology":null},{"url":"/paper/a-systematic-dnn-weight-pruning-framework","slug":"a-systematic-dnn-weight-pruning-framework","title":"A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers","date":"2018-04-10","arxiv_id":"1804.03294","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-systematic-dnn-weight-pruning-framework#ran","syntology_url":"https://syntology.ai/paper/1804.03294","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.03294"}},"official":{"repos":["KaiqiZhang/admm-pruning"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/packnet-adding-multiple-tasks-to-a-single","slug":"packnet-adding-multiple-tasks-to-a-single","title":"PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning","date":"2017-11-15","arxiv_id":"1711.05769","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/packnet-adding-multiple-tasks-to-a-single#ran","syntology_url":"https://syntology.ai/paper/1711.05769","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.05769"}},"official":{"repos":["arunmallya/packnet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/picking-winning-tickets-before-training-by-1","slug":"picking-winning-tickets-before-training-by-1","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","date":"2020-02-18","arxiv_id":"2002.07376","repositories_listed":3,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/picking-winning-tickets-before-training-by-1#ran","syntology_url":"https://syntology.ai/paper/2002.07376","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.07376"}},"official":{"repos":["alecwangcq/GraSP"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/importance-estimation-for-neural-network-1","slug":"importance-estimation-for-neural-network-1","title":"Importance Estimation for Neural Network Pruning","date":"2019-06-25","arxiv_id":"1906.10771","repositories_listed":3,"syntology":null},{"url":"/paper/adversarial-fine-tuning-of-compressed-neural","slug":"adversarial-fine-tuning-of-compressed-neural","title":"Adversarial Fine-tuning of Compressed Neural Networks for Joint Improvement of Robustness and Efficiency","date":"2024-03-14","arxiv_id":"2403.09441","repositories_listed":2,"syntology":null},{"url":"/paper/falcon-flop-aware-combinatorial-optimization","slug":"falcon-flop-aware-combinatorial-optimization","title":"FALCON: FLOP-Aware Combinatorial Optimization for Neural Network Pruning","date":"2024-03-11","arxiv_id":"2403.07094","repositories_listed":2,"syntology":null},{"url":"/paper/do-localization-methods-actually-localize","slug":"do-localization-methods-actually-localize","title":"Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two Benchmarks","date":"2023-11-15","arxiv_id":"2311.09060","repositories_listed":2,"syntology":{"n":15,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/do-localization-methods-actually-localize#ran","syntology_url":"https://syntology.ai/paper/2311.09060","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09060"}},"official":{"repos":["terarachang/memdata","terarachang/mempi"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/beyond-size-how-gradients-shape-pruning","slug":"beyond-size-how-gradients-shape-pruning","title":"Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models","date":"2023-11-08","arxiv_id":"2311.04902","repositories_listed":2,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/beyond-size-how-gradients-shape-pruning#ran","syntology_url":"https://syntology.ai/paper/2311.04902","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.04902"}},"official":{"repos":["rocktimjyotidas/gblm-pruner","vila-lab/gblm-pruner"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-the-transferability-of-adversarial-5","slug":"improving-the-transferability-of-adversarial-5","title":"Improving the Transferability of Adversarial Examples via Direction Tuning","date":"2023-03-27","arxiv_id":"2303.15109","repositories_listed":2,"syntology":null},{"url":"/paper/iterative-soft-shrinkage-learning-for","slug":"iterative-soft-shrinkage-learning-for","title":"Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution","date":"2023-03-16","arxiv_id":"2303.09650","repositories_listed":2,"syntology":null},{"url":"/paper/upop-unified-and-progressive-pruning-for","slug":"upop-unified-and-progressive-pruning-for","title":"UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers","date":"2023-01-31","arxiv_id":"2301.13741","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/upop-unified-and-progressive-pruning-for#ran","syntology_url":"https://syntology.ai/paper/2301.13741","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.13741"}},"official":{"repos":["sdc17/upop"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/why-is-the-state-of-neural-network-pruning-so","slug":"why-is-the-state-of-neural-network-pruning-so","title":"Why is the State of Neural Network Pruning so Confusing? On the Fairness, Comparison Setup, and Trainability in Network Pruning","date":"2023-01-12","arxiv_id":"2301.05219","repositories_listed":2,"syntology":null},{"url":"/paper/training-deep-neural-networks-with-joint","slug":"training-deep-neural-networks-with-joint","title":"Training Deep Neural Networks with Joint Quantization and Pruning of Weights and Activations","date":"2021-10-15","arxiv_id":"2110.08271","repositories_listed":2,"syntology":null},{"url":"/paper/group-fisher-pruning-for-practical-network","slug":"group-fisher-pruning-for-practical-network","title":"Group Fisher Pruning for Practical Network Compression","date":"2021-08-02","arxiv_id":"2108.00708","repositories_listed":2,"syntology":null},{"url":"/paper/manipulating-identical-filter-redundancy-for","slug":"manipulating-identical-filter-redundancy-for","title":"Manipulating Identical Filter Redundancy for Efficient Pruning on Deep and Complicated CNN","date":"2021-07-30","arxiv_id":"2107.14444","repositories_listed":2,"syntology":null},{"url":"/paper/efficient-matrix-free-approximations-of","slug":"efficient-matrix-free-approximations-of","title":"M-FAC: Efficient Matrix-Free Approximations of Second-Order Information","date":"2021-07-07","arxiv_id":"2107.03356","repositories_listed":2,"syntology":{"n":14,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":7,"n_honours":4,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 4 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/efficient-matrix-free-approximations-of#ran","syntology_url":"https://syntology.ai/paper/2107.03356","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.03356"}},"official":{"repos":["IST-DASLab/M-FAC"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/ac-dc-alternating-compressed-decompressed","slug":"ac-dc-alternating-compressed-decompressed","title":"AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks","date":"2021-06-23","arxiv_id":"2106.12379","repositories_listed":2,"syntology":{"n":5,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/ac-dc-alternating-compressed-decompressed#ran","syntology_url":"https://syntology.ai/paper/2106.12379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.12379"}},"official":{"repos":["IST-DASLab/ACDC"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/sparse-training-via-boosting-pruning","slug":"sparse-training-via-boosting-pruning","title":"Sparse Training via Boosting Pruning Plasticity with Neuroregeneration","date":"2021-06-19","arxiv_id":"2106.10404","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/sparse-training-via-boosting-pruning#ran","syntology_url":"https://syntology.ai/paper/2106.10404","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.10404"}},"official":{"repos":["Shiweiliuiiiiiii/GraNet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/lottery-jackpots-exist-in-pre-trained-models","slug":"lottery-jackpots-exist-in-pre-trained-models","title":"Lottery Jackpots Exist in Pre-trained Models","date":"2021-04-18","arxiv_id":"2104.08700","repositories_listed":2,"syntology":null},{"url":"/paper/emerging-paradigms-of-neural-network-pruning","slug":"emerging-paradigms-of-neural-network-pruning","title":"Recent Advances on Neural Network Pruning at Initialization","date":"2021-03-11","arxiv_id":"2103.06460","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/emerging-paradigms-of-neural-network-pruning#ran","syntology_url":"https://syntology.ai/paper/2103.06460","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.06460"}},"official":{"repos":["mingsun-tse/awesome-pruning-at-initialization","mingsun-tse/smile-pruning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dhp-differentiable-meta-pruning-via","slug":"dhp-differentiable-meta-pruning-via","title":"DHP: Differentiable Meta Pruning via HyperNetworks","date":"2020-03-30","arxiv_id":"2003.13683","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dhp-differentiable-meta-pruning-via#ran","syntology_url":"https://syntology.ai/paper/2003.13683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13683"}},"official":{"repos":["ofsoundof/dhp"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/comparing-rewinding-and-fine-tuning-in-neural","slug":"comparing-rewinding-and-fine-tuning-in-neural","title":"Comparing Rewinding and Fine-tuning in Neural Network Pruning","date":"2020-03-05","arxiv_id":"2003.02389","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/comparing-rewinding-and-fine-tuning-in-neural#ran","syntology_url":"https://syntology.ai/paper/2003.02389","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.02389"}},"official":{"repos":["lottery-ticket/rewinding-iclr20-public"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hrank-filter-pruning-using-high-rank-feature","slug":"hrank-filter-pruning-using-high-rank-feature","title":"HRank: Filter Pruning using High-Rank Feature Map","date":"2020-02-24","arxiv_id":"2002.10179","repositories_listed":2,"syntology":null},{"url":"/paper/dreaming-to-distill-data-free-knowledge","slug":"dreaming-to-distill-data-free-knowledge","title":"Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion","date":"2019-12-18","arxiv_id":"1912.08795","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dreaming-to-distill-data-free-knowledge#ran","syntology_url":"https://syntology.ai/paper/1912.08795","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.08795"}},"official":{"repos":["NVlabs/DeepInversion"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/winning-the-lottery-with-continuous-1","slug":"winning-the-lottery-with-continuous-1","title":"Winning the Lottery with Continuous Sparsification","date":"2019-12-10","arxiv_id":"1912.04427","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/winning-the-lottery-with-continuous-1#ran","syntology_url":"https://syntology.ai/paper/1912.04427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.04427"}},"official":{"repos":["lolemacs/continuous-sparsification"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/selective-brain-damage-measuring-the","slug":"selective-brain-damage-measuring-the","title":"What Do Compressed Deep Neural Networks Forget?","date":"2019-11-13","arxiv_id":"1911.05248","repositories_listed":2,"syntology":null},{"url":"/paper/learning-sparse-networks-using-targeted","slug":"learning-sparse-networks-using-targeted","title":"Learning Sparse Networks Using Targeted Dropout","date":"2019-05-31","arxiv_id":"1905.13678","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-sparse-networks-using-targeted#ran","syntology_url":"https://syntology.ai/paper/1905.13678","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.13678"}},"official":null}},{"url":"/paper/towards-learning-of-filter-level","slug":"towards-learning-of-filter-level","title":"Towards Learning of Filter-Level Heterogeneous Compression of Convolutional Neural Networks","date":"2019-04-22","arxiv_id":"1904.09872","repositories_listed":2,"syntology":null},{"url":"/paper/gasl-guided-attention-for-sparsity-learning","slug":"gasl-guided-attention-for-sparsity-learning","title":"GASL: Guided Attention for Sparsity Learning in Deep Neural Networks","date":"2019-01-07","arxiv_id":"1901.01939","repositories_listed":2,"syntology":null},{"url":"/paper/dynamic-channel-pruning-feature-boosting-and","slug":"dynamic-channel-pruning-feature-boosting-and","title":"Dynamic Channel Pruning: Feature Boosting and Suppression","date":"2018-10-12","arxiv_id":"1810.05331","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dynamic-channel-pruning-feature-boosting-and#ran","syntology_url":"https://syntology.ai/paper/1810.05331","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.05331"}},"official":{"repos":["deep-fry/mayo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/rethinking-the-value-of-network-pruning","slug":"rethinking-the-value-of-network-pruning","title":"Rethinking the Value of Network Pruning","date":"2018-10-11","arxiv_id":"1810.05270","repositories_listed":2,"syntology":null},{"url":"/paper/pruning-neural-networks-is-it-time-to-nip-it","slug":"pruning-neural-networks-is-it-time-to-nip-it","title":"A Closer Look at Structured Pruning for Neural Network Compression","date":"2018-10-10","arxiv_id":"1810.04622","repositories_listed":2,"syntology":null},{"url":"/paper/building-efficient-convnets-using-redundant","slug":"building-efficient-convnets-using-redundant","title":"Building Efficient ConvNets using Redundant Feature Pruning","date":"2018-02-21","arxiv_id":"1802.07653","repositories_listed":2,"syntology":null},{"url":"/paper/hierarchical-safety-realignment-lightweight","slug":"hierarchical-safety-realignment-lightweight","title":"Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models","date":"2025-05-22","arxiv_id":"2505.16104","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-pruning-of-deep-neural-networks-for","slug":"adaptive-pruning-of-deep-neural-networks-for","title":"Adaptive Pruning of Deep Neural Networks for Resource-Aware Embedded Intrusion Detection on the Edge","date":"2025-05-20","arxiv_id":"2505.14592","repositories_listed":1,"syntology":null},{"url":"/paper/guiding-evolutionary-autoencoder-training","slug":"guiding-evolutionary-autoencoder-training","title":"Guiding Evolutionary AutoEncoder Training with Activation-Based Pruning Operators","date":"2025-05-08","arxiv_id":"2505.05138","repositories_listed":1,"syntology":null},{"url":"/paper/replaceme-network-simplification-via-layer","slug":"replaceme-network-simplification-via-layer","title":"ReplaceMe: Network Simplification via Layer Pruning and Linear Transformations","date":"2025-05-05","arxiv_id":"2505.02819","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/replaceme-network-simplification-via-layer#ran","syntology_url":"https://syntology.ai/paper/2505.02819","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.02819"}},"official":{"repos":["mts-ai/replaceme"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/boosting-large-language-models-with-mask-fine","slug":"boosting-large-language-models-with-mask-fine","title":"Boosting Large Language Models with Mask Fine-Tuning","date":"2025-03-27","arxiv_id":"2503.22764","repositories_listed":1,"syntology":null},{"url":"/paper/compact-bayesian-neural-networks-via-pruned","slug":"compact-bayesian-neural-networks-via-pruned","title":"Compact Bayesian Neural Networks via pruned MCMC sampling","date":"2025-01-12","arxiv_id":"2501.06962","repositories_listed":1,"syntology":null},{"url":"/paper/neural-architecture-codesign-for-fast-physics","slug":"neural-architecture-codesign-for-fast-physics","title":"Neural Architecture Codesign for Fast Physics Applications","date":"2025-01-09","arxiv_id":"2501.05515","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-glu-expansion-ratios-a-study-of","slug":"exploring-glu-expansion-ratios-a-study-of","title":"Exploring GLU Expansion Ratios: A Study of Structured Pruning in LLaMA-3.2 Models","date":"2024-12-26","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/zeroth-order-adaptive-neuron-alignment-based","slug":"zeroth-order-adaptive-neuron-alignment-based","title":"Zeroth-Order Adaptive Neuron Alignment Based Pruning without Re-Training","date":"2024-11-11","arxiv_id":"2411.07066","repositories_listed":1,"syntology":null},{"url":"/paper/llm-rank-a-graph-theoretical-approach-to","slug":"llm-rank-a-graph-theoretical-approach-to","title":"LLM-Rank: A Graph Theoretical Approach to Pruning Large Language Models","date":"2024-10-17","arxiv_id":"2410.13299","repositories_listed":1,"syntology":null},{"url":"/paper/is-c4-dataset-optimal-for-pruning-an","slug":"is-c4-dataset-optimal-for-pruning-an","title":"Is C4 Dataset Optimal for Pruning? An Investigation of Calibration Data for LLM Pruning","date":"2024-10-09","arxiv_id":"2410.07461","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/is-c4-dataset-optimal-for-pruning-an#ran","syntology_url":"https://syntology.ai/paper/2410.07461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07461"}},"official":{"repos":["abx393/llm-pruning-calibration-data"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/investigating-the-effect-of-network-pruning","slug":"investigating-the-effect-of-network-pruning","title":"Investigating the Effect of Network Pruning on Performance and Interpretability","date":"2024-09-29","arxiv_id":"2409.19727","repositories_listed":1,"syntology":null},{"url":"/paper/maskllm-learnable-semi-structured-sparsity","slug":"maskllm-learnable-semi-structured-sparsity","title":"MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models","date":"2024-09-26","arxiv_id":"2409.17481","repositories_listed":1,"syntology":{"n":16,"n_ran":5,"n_constructed":1,"n_ran_checked":5,"n_instrument":0,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":16,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/maskllm-learnable-semi-structured-sparsity#ran","syntology_url":"https://syntology.ai/paper/2409.17481","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.17481"}},"official":{"repos":["nvlabs/maskllm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":5,"n_unverified":11,"ran_from_kinds":["official"]}}},{"url":"/paper/cfsp-an-efficient-structured-pruning","slug":"cfsp-an-efficient-structured-pruning","title":"CFSP: An Efficient Structured Pruning Framework for LLMs with Coarse-to-Fine Activation Information","date":"2024-09-20","arxiv_id":"2409.13199","repositories_listed":1,"syntology":null},{"url":"/paper/oats-outlier-aware-pruning-through-sparse-and","slug":"oats-outlier-aware-pruning-through-sparse-and","title":"OATS: Outlier-Aware Pruning Through Sparse and Low Rank Decomposition","date":"2024-09-20","arxiv_id":"2409.13652","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/oats-outlier-aware-pruning-through-sparse-and#ran","syntology_url":"https://syntology.ai/paper/2409.13652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.13652"}},"official":{"repos":["stephenqz/oats"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/adversarial-pruning-a-survey-and-benchmark-of","slug":"adversarial-pruning-a-survey-and-benchmark-of","title":"Adversarial Pruning: A Survey and Benchmark of Pruning Methods for Adversarial Robustness","date":"2024-09-02","arxiv_id":"2409.01249","repositories_listed":1,"syntology":null},{"url":"/paper/3d-point-cloud-network-pruning-when-some","slug":"3d-point-cloud-network-pruning-when-some","title":"3D Point Cloud Network Pruning: When Some Weights Do not Matter","date":"2024-08-26","arxiv_id":"2408.14601","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-sparsity-in-recurrent-neural","slug":"investigating-sparsity-in-recurrent-neural","title":"Investigating Sparsity in Recurrent Neural Networks","date":"2024-07-30","arxiv_id":"2407.20601","repositories_listed":1,"syntology":null},{"url":"/paper/finding-lottery-tickets-in-vision-models-via","slug":"finding-lottery-tickets-in-vision-models-via","title":"Finding Lottery Tickets in Vision Models via Data-driven Spectral Foresight Pruning","date":"2024-06-03","arxiv_id":"2406.01820","repositories_listed":1,"syntology":null},{"url":"/paper/aggressive-or-imperceptible-or-both-network","slug":"aggressive-or-imperceptible-or-both-network","title":"Aggressive or Imperceptible, or Both: Network Pruning Assisted Hybrid Byzantines in Federated Learning","date":"2024-04-09","arxiv_id":"2404.06230","repositories_listed":1,"syntology":null},{"url":"/paper/auto-train-once-controller-network-guided","slug":"auto-train-once-controller-network-guided","title":"Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch","date":"2024-03-21","arxiv_id":"2403.14729","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":1,"n_ran_checked":5,"n_instrument":7,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":14,"phrase":"12 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/auto-train-once-controller-network-guided#ran","syntology_url":"https://syntology.ai/paper/2403.14729","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.14729"}},"official":{"repos":["xidongwu/autotrainonce"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":1,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/not-all-tickets-are-equal-and-we-know-it","slug":"not-all-tickets-are-equal-and-we-know-it","title":"Pruning neural network models for gene regulatory dynamics using data and domain knowledge","date":"2024-03-05","arxiv_id":"2403.04805","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/not-all-tickets-are-equal-and-we-know-it#ran","syntology_url":"https://syntology.ai/paper/2403.04805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04805"}},"official":{"repos":["quackenbushlab/dash"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/what-to-do-when-your-discrete-optimization-is","slug":"what-to-do-when-your-discrete-optimization-is","title":"What to Do When Your Discrete Optimization Is the Size of a Neural Network?","date":"2024-02-15","arxiv_id":"2402.10339","repositories_listed":1,"syntology":null},{"url":"/paper/less-is-ken-a-universal-and-simple-non","slug":"less-is-ken-a-universal-and-simple-non","title":"Less is KEN: a Universal and Simple Non-Parametric Pruning Algorithm for Large Language Models","date":"2024-02-05","arxiv_id":"2402.03142","repositories_listed":1,"syntology":null},{"url":"/paper/device-wise-federated-network-pruning","slug":"device-wise-federated-network-pruning","title":"Device-Wise Federated Network Pruning","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/fluctuation-based-adaptive-structured-pruning","slug":"fluctuation-based-adaptive-structured-pruning","title":"Fluctuation-based Adaptive Structured Pruning for Large Language Models","date":"2023-12-19","arxiv_id":"2312.11983","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/fluctuation-based-adaptive-structured-pruning#ran","syntology_url":"https://syntology.ai/paper/2312.11983","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11983"}},"official":{"repos":["casia-iva-lab/flap"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-higher-ranks-via-adversarial-weight-1","slug":"towards-higher-ranks-via-adversarial-weight-1","title":"Towards Higher Ranks via Adversarial Weight Pruning","date":"2023-11-29","arxiv_id":"2311.17493","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-higher-ranks-via-adversarial-weight-1#ran","syntology_url":"https://syntology.ai/paper/2311.17493","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17493"}},"official":{"repos":["huawei-noah/Efficient-Computing"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/filter-pruning-of-lightweight-face-detectors","slug":"filter-pruning-of-lightweight-face-detectors","title":"Filter-Pruning of Lightweight Face Detectors Using a Geometric Median Criterion","date":"2023-11-28","arxiv_id":"2311.16613","repositories_listed":1,"syntology":null},{"url":"/paper/lightgaussian-unbounded-3d-gaussian","slug":"lightgaussian-unbounded-3d-gaussian","title":"LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS","date":"2023-11-28","arxiv_id":"2311.17245","repositories_listed":1,"syntology":{"n":22,"n_ran":17,"n_constructed":1,"n_ran_checked":3,"n_instrument":14,"n_unverified":5,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":22,"phrase":"17 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 14 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/lightgaussian-unbounded-3d-gaussian#ran","syntology_url":"https://syntology.ai/paper/2311.17245","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17245"}},"official":{"repos":["VITA-Group/LightGaussian"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/neural-network-pruning-by-gradient-descent","slug":"neural-network-pruning-by-gradient-descent","title":"Neural Network Pruning by Gradient Descent","date":"2023-11-21","arxiv_id":"2311.12526","repositories_listed":1,"syntology":null},{"url":"/paper/a-structured-pruning-algorithm-for-model","slug":"a-structured-pruning-algorithm-for-model","title":"Efficient Model-Based Deep Learning via Network Pruning and Fine-Tuning","date":"2023-11-03","arxiv_id":"2311.02003","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-sparse-no-training-training-free-fine","slug":"dynamic-sparse-no-training-training-free-fine","title":"Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs","date":"2023-10-13","arxiv_id":"2310.08915","repositories_listed":1,"syntology":{"n":15,"n_ran":8,"n_constructed":2,"n_ran_checked":6,"n_instrument":2,"n_unverified":7,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":15,"phrase":"8 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/dynamic-sparse-no-training-training-free-fine#ran","syntology_url":"https://syntology.ai/paper/2310.08915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.08915"}},"official":{"repos":["zyxxmu/dsnot"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":2,"n_ran_no_instrument_failure":6,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/filter-pruning-for-cnn-with-enhanced-linear","slug":"filter-pruning-for-cnn-with-enhanced-linear","title":"Filter Pruning For CNN With Enhanced Linear Representation Redundancy","date":"2023-10-10","arxiv_id":"2310.06344","repositories_listed":1,"syntology":null},{"url":"/paper/outlier-weighed-layerwise-sparsity-owl-a","slug":"outlier-weighed-layerwise-sparsity-owl-a","title":"Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity","date":"2023-10-08","arxiv_id":"2310.05175","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/outlier-weighed-layerwise-sparsity-owl-a#ran","syntology_url":"https://syntology.ai/paper/2310.05175","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05175"}},"official":{"repos":["luuyin/owl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/robust-network-pruning-with-sparse-entropic","slug":"robust-network-pruning-with-sparse-entropic","title":"SWAP: Sparse Entropic Wasserstein Regression for Robust Network Pruning","date":"2023-10-07","arxiv_id":"2310.04918","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/robust-network-pruning-with-sparse-entropic#ran","syntology_url":"https://syntology.ai/paper/2310.04918","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04918"}},"official":{"repos":["youlei202/entropic-wasserstein-pruning"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/feather-an-elegant-solution-to-effective-dnn","slug":"feather-an-elegant-solution-to-effective-dnn","title":"Feather: An Elegant Solution to Effective DNN Sparsification","date":"2023-10-03","arxiv_id":"2310.02448","repositories_listed":1,"syntology":null},{"url":"/paper/edac-efficient-deployment-of-audio","slug":"edac-efficient-deployment-of-audio","title":"EDAC: Efficient Deployment of Audio Classification Models For COVID-19 Detection","date":"2023-09-11","arxiv_id":"2309.05357","repositories_listed":1,"syntology":null},{"url":"/paper/layer-wise-feedback-propagation","slug":"layer-wise-feedback-propagation","title":"Efficient and Flexible Neural Network Training through Layer-wise Feedback Propagation","date":"2023-08-23","arxiv_id":"2308.12053","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-on-deep-neural-network-pruning","slug":"a-survey-on-deep-neural-network-pruning","title":"A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations","date":"2023-08-13","arxiv_id":"2308.06767","repositories_listed":1,"syntology":null},{"url":"/paper/distilled-pruning-using-synthetic-data-to-win","slug":"distilled-pruning-using-synthetic-data-to-win","title":"Distilled Pruning: Using Synthetic Data to Win the Lottery","date":"2023-07-07","arxiv_id":"2307.03364","repositories_listed":1,"syntology":null},{"url":"/paper/pruning-vs-quantization-which-is-better","slug":"pruning-vs-quantization-which-is-better","title":"Pruning vs Quantization: Which is Better?","date":"2023-07-06","arxiv_id":"2307.02973","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":10,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pruning-vs-quantization-which-is-better#ran","syntology_url":"https://syntology.ai/paper/2307.02973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.02973"}},"official":{"repos":["Qualcomm-AI-research/pruning-vs-quantization"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/filter-pruning-for-efficient-cnns-via","slug":"filter-pruning-for-efficient-cnns-via","title":"Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Sampler","date":"2023-07-01","arxiv_id":"2307.00198","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/filter-pruning-for-efficient-cnns-via#ran","syntology_url":"https://syntology.ai/paper/2307.00198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.00198"}},"official":{"repos":["osilly/kdfs"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-generalization-in-meta-learning-via","slug":"improving-generalization-in-meta-learning-via","title":"Improving Generalization in Meta-Learning via Meta-Gradient Augmentation","date":"2023-06-14","arxiv_id":"2306.08460","repositories_listed":1,"syntology":null},{"url":"/paper/how-sparse-can-we-prune-a-deep-network-a","slug":"how-sparse-can-we-prune-a-deep-network-a","title":"How Sparse Can We Prune A Deep Network: A Fundamental Limit Viewpoint","date":"2023-06-09","arxiv_id":"2306.05857","repositories_listed":1,"syntology":null},{"url":"/paper/scaling-up-semi-supervised-learning-with","slug":"scaling-up-semi-supervised-learning-with","title":"Scaling Up Semi-supervised Learning with Unconstrained Unlabelled Data","date":"2023-06-02","arxiv_id":"2306.01222","repositories_listed":1,"syntology":null},{"url":"/paper/lottery-tickets-in-evolutionary-optimization","slug":"lottery-tickets-in-evolutionary-optimization","title":"Lottery Tickets in Evolutionary Optimization: On Sparse Backpropagation-Free Trainability","date":"2023-05-31","arxiv_id":"2306.00045","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lottery-tickets-in-evolutionary-optimization#ran","syntology_url":"https://syntology.ai/paper/2306.00045","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00045"}},"official":{"repos":["roberttlange/es-lottery"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-three-regime-model-of-network-pruning","slug":"a-three-regime-model-of-network-pruning","title":"A Three-regime Model of Network Pruning","date":"2023-05-28","arxiv_id":"2305.18383","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-three-regime-model-of-network-pruning#ran","syntology_url":"https://syntology.ai/paper/2305.18383","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18383"}},"official":{"repos":["yefanzhou/threeregimepruning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/pruning-meets-low-rank-parameter-efficient","slug":"pruning-meets-low-rank-parameter-efficient","title":"LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning","date":"2023-05-28","arxiv_id":"2305.18403","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/pruning-meets-low-rank-parameter-efficient#ran","syntology_url":"https://syntology.ai/paper/2305.18403","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18403"}},"official":{"repos":["aim-uofa/loraprune"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/beta-rank-a-robust-convolutional-filter","slug":"beta-rank-a-robust-convolutional-filter","title":"Beta-Rank: A Robust Convolutional Filter Pruning Method For Imbalanced Medical Image Analysis","date":"2023-04-15","arxiv_id":"2304.07461","repositories_listed":1,"syntology":null},{"url":"/paper/ntk-sap-improving-neural-network-pruning-by","slug":"ntk-sap-improving-neural-network-pruning-by","title":"NTK-SAP: Improving neural network pruning by aligning training dynamics","date":"2023-04-06","arxiv_id":"2304.02840","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/ntk-sap-improving-neural-network-pruning-by#ran","syntology_url":"https://syntology.ai/paper/2304.02840","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.02840"}},"official":{"repos":["yitewang/ntk-sap"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/the-other-side-of-compression-measuring-bias","slug":"the-other-side-of-compression-measuring-bias","title":"The Other Side of Compression: Measuring Bias in Pruned Transformers","date":"2023-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/structured-pruning-for-deep-convolutional","slug":"structured-pruning-for-deep-convolutional","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","date":"2023-03-01","arxiv_id":"2303.00566","repositories_listed":1,"syntology":null},{"url":"/paper/st-mfnet-mini-knowledge-distillation-driven","slug":"st-mfnet-mini-knowledge-distillation-driven","title":"ST-MFNet Mini: Knowledge Distillation-Driven Frame Interpolation","date":"2023-02-16","arxiv_id":"2302.08455","repositories_listed":1,"syntology":null},{"url":"/paper/whc-weighted-hybrid-criterion-for-filter","slug":"whc-weighted-hybrid-criterion-for-filter","title":"WHC: Weighted Hybrid Criterion for Filter Pruning on Convolutional Neural Networks","date":"2023-02-16","arxiv_id":"2302.08185","repositories_listed":1,"syntology":null}],"syntology_records":46,"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":3,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/network-pruning-on-imagenet","since_archive":"/sota/network-pruning-on-imagenet#since-judged","papers_judged":2,"placed":0},{"leaderboard":"/sota/network-pruning-on-cifar-10","since_archive":"/sota/network-pruning-on-cifar-10#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":83,"papers_where_code_ran_first_page":"/task/network-pruning/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":6,"url":"/task/network-pruning/papers/2","json":"/task/network-pruning/papers/2.json","rows":100},{"order":"archive","page":3,"of":6,"url":"/task/network-pruning/papers/3","json":"/task/network-pruning/papers/3.json","rows":100},{"order":"archive","page":4,"of":6,"url":"/task/network-pruning/papers/4","json":"/task/network-pruning/papers/4.json","rows":100},{"order":"archive","page":5,"of":6,"url":"/task/network-pruning/papers/5","json":"/task/network-pruning/papers/5.json","rows":100},{"order":"archive","page":6,"of":6,"url":"/task/network-pruning/papers/6","json":"/task/network-pruning/papers/6.json","rows":34},{"order":"ran","page":1,"of":1,"url":"/task/network-pruning/papers/ran/1","json":"/task/network-pruning/papers/ran/1.json","rows":83}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"3bdb8c83080e7b3c873f42b70e766d730de3e02f6e4e0b24475fddf781bcb63f","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}