{"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/mixture-of-experts/papers/ran/3","list_of":"/task/mixture-of-experts","task":"Mixture-of-Experts","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","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.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":3,"pages_in_order":3,"rows_per_page":100,"rows":[201,216],"of":216,"counts":{"archive_papers_tagged":1312,"with_a_code_link":516,"where_syntology_ran_a_sample":216,"not_listed_spam_title":0,"listed":1312,"listed_where_code_ran":216,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":184,"every_run_a_failure_of_syntologys_instrument":32,"listed_with_a_run_with_no_instrument_failure":184,"listed_every_run_a_failure_of_syntologys_instrument":32,"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"},"first_page":"/task/mixture-of-experts/papers/ran/1","prev":"/task/mixture-of-experts/papers/ran/2","next":null,"papers":[{"url":"/paper/kdexplainer-a-task-oriented-attention-model","slug":"kdexplainer-a-task-oriented-attention-model","title":"KDExplainer: A Task-oriented Attention Model for Explaining Knowledge Distillation","date":"2021-05-10","arxiv_id":"2105.04181","repositories_listed":1,"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":0,"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/kdexplainer-a-task-oriented-attention-model#ran","syntology_url":"https://syntology.ai/paper/2105.04181","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.04181"}},"official":null}},{"url":"/paper/mice-mixture-of-contrastive-experts-for-1","slug":"mice-mixture-of-contrastive-experts-for-1","title":"MiCE: Mixture of Contrastive Experts for Unsupervised Image Clustering","date":"2021-05-05","arxiv_id":"2105.01899","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"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) · 2 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/mice-mixture-of-contrastive-experts-for-1#ran","syntology_url":"https://syntology.ai/paper/2105.01899","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.01899"}},"official":{"repos":["TsungWeiTsai/MiCE"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/probabilistic-mixture-of-experts-for-1","slug":"probabilistic-mixture-of-experts-for-1","title":"Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement Learning","date":"2021-04-19","arxiv_id":"2104.09122","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/probabilistic-mixture-of-experts-for-1#ran","syntology_url":"https://syntology.ai/paper/2104.09122","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.09122"}},"official":{"repos":["JieRen98/rlkit-pmoe"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/switch-transformers-scaling-to-trillion","slug":"switch-transformers-scaling-to-trillion","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","date":"2021-01-11","arxiv_id":"2101.03961","repositories_listed":8,"syntology":{"n":13,"n_ran":7,"n_constructed":2,"n_ran_checked":3,"n_instrument":4,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"7 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/switch-transformers-scaling-to-trillion#ran","syntology_url":"https://syntology.ai/paper/2101.03961","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.03961"}},"official":{"repos":["tensorflow/mesh"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/federated-learning-using-a-mixture-of-experts","slug":"federated-learning-using-a-mixture-of-experts","title":"Specialized federated learning using a mixture of experts","date":"2020-10-05","arxiv_id":"2010.02056","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/federated-learning-using-a-mixture-of-experts#ran","syntology_url":"https://syntology.ai/paper/2010.02056","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.02056"}},"official":{"repos":["edvinli/federated-learning-mixture"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/making-neural-networks-interpretable-with","slug":"making-neural-networks-interpretable-with","title":"Making Neural Networks Interpretable with Attribution: Application to Implicit Signals Prediction","date":"2020-08-26","arxiv_id":"2008.11406","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/making-neural-networks-interpretable-with#ran","syntology_url":"https://syntology.ai/paper/2008.11406","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.11406"}},"official":{"repos":["deezer/interpretable_nn_attribution"],"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/gshard-scaling-giant-models-with-conditional","slug":"gshard-scaling-giant-models-with-conditional","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","date":"2020-06-30","arxiv_id":"2006.16668","repositories_listed":2,"syntology":{"n":10,"n_ran":9,"n_constructed":2,"n_ran_checked":4,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"9 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/gshard-scaling-giant-models-with-conditional#ran","syntology_url":"https://syntology.ai/paper/2006.16668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.16668"}},"official":null}},{"url":"/paper/variational-mixture-of-experts-autoencoders","slug":"variational-mixture-of-experts-autoencoders","title":"Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models","date":"2019-11-08","arxiv_id":"1911.03393","repositories_listed":3,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/variational-mixture-of-experts-autoencoders#ran","syntology_url":"https://syntology.ai/paper/1911.03393","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.03393"}},"official":{"repos":["iffsid/mmvae"],"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":["listed","official"]}}},{"url":"/paper/hierarchical-mixtures-of-generators-for","slug":"hierarchical-mixtures-of-generators-for","title":"Hierarchical Mixtures of Generators for Adversarial Learning","date":"2019-11-05","arxiv_id":"1911.02069","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"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) · 2 unverified","sample_list":"/paper/hierarchical-mixtures-of-generators-for#ran","syntology_url":"https://syntology.ai/paper/1911.02069","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.02069"}},"official":{"repos":["alper111/hmog"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/mixture-of-experts-variational-autoencoder","slug":"mixture-of-experts-variational-autoencoder","title":"Mixture-of-Experts Variational Autoencoder for Clustering and Generating from Similarity-Based Representations on Single Cell Data","date":"2019-10-17","arxiv_id":"1910.07763","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mixture-of-experts-variational-autoencoder#ran","syntology_url":"https://syntology.ai/paper/1910.07763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.07763"}},"official":{"repos":["andkopf/MoESimVAE"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/expert-sample-consensus-applied-to-camera-re","slug":"expert-sample-consensus-applied-to-camera-re","title":"Expert Sample Consensus Applied to Camera Re-Localization","date":"2019-08-07","arxiv_id":"1908.02484","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/expert-sample-consensus-applied-to-camera-re#ran","syntology_url":"https://syntology.ai/paper/1908.02484","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.02484"}},"official":{"repos":["vislearn/esac"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-source-domain-adaptation-with-mixture","slug":"multi-source-domain-adaptation-with-mixture","title":"Multi-Source Domain Adaptation with Mixture of Experts","date":"2018-09-07","arxiv_id":"1809.02256","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-source-domain-adaptation-with-mixture#ran","syntology_url":"https://syntology.ai/paper/1809.02256","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.02256"}},"official":{"repos":["jiangfeng1124/transfer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tafe-net-task-aware-feature-embeddings-for","slug":"tafe-net-task-aware-feature-embeddings-for","title":"Deep Mixture of Experts via Shallow Embedding","date":"2018-06-05","arxiv_id":"1806.01531","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"8 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tafe-net-task-aware-feature-embeddings-for#ran","syntology_url":"https://syntology.ai/paper/1806.01531","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.01531"}},"official":null}},{"url":"/paper/gated-multimodal-units-for-information-fusion","slug":"gated-multimodal-units-for-information-fusion","title":"Gated Multimodal Units for Information Fusion","date":"2017-02-07","arxiv_id":"1702.01992","repositories_listed":9,"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":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) · 0 unverified","sample_list":"/paper/gated-multimodal-units-for-information-fusion#ran","syntology_url":"https://syntology.ai/paper/1702.01992","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1702.01992"}},"official":{"repos":["johnarevalo/gmu-mmimdb"],"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/outrageously-large-neural-networks-the","slug":"outrageously-large-neural-networks-the","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","date":"2017-01-23","arxiv_id":"1701.06538","repositories_listed":4,"syntology":{"n":6,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"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) · 2 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/outrageously-large-neural-networks-the#ran","syntology_url":"https://syntology.ai/paper/1701.06538","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1701.06538"}},"official":null}},{"url":"/paper/distilling-the-knowledge-in-a-neural-network","slug":"distilling-the-knowledge-in-a-neural-network","title":"Distilling the Knowledge in a Neural Network","date":"2015-03-09","arxiv_id":"1503.02531","repositories_listed":64,"syntology":{"n":37,"n_ran":23,"n_constructed":0,"n_ran_checked":14,"n_instrument":9,"n_unverified":14,"n_honours":6,"n_violates":0,"n_no_contract":8,"n_pointer_only":11,"phrase":"23 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 6 honoured, 0 violated, 8 with no contract checked; 9 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/distilling-the-knowledge-in-a-neural-network#ran","syntology_url":"https://syntology.ai/paper/1503.02531","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1503.02531"}},"official":null}}],"record_sha256":"5aad5e3da0edf149221344d005291b4e0836012a10efff4c93c6cd412e3b8da0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}