{"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","name":"Mixture-of-Experts","slug":"mixture-of-experts","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":1312,"papers_with_code":516,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":0,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[],"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":14,"rows_per_page":100,"shown":100,"of":1312,"of_with_code":516,"tagged_in_all":1312,"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":176,"every_run_a_failure_of_syntologys_instrument":40,"listed_with_a_run_with_no_instrument_failure":176,"listed_every_run_a_failure_of_syntologys_instrument":40,"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/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}},{"url":"/paper/modeling-task-relationships-in-multi-task","slug":"modeling-task-relationships-in-multi-task","title":"Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts","date":"2018-07-19","arxiv_id":null,"repositories_listed":11,"syntology":null},{"url":"/paper/no-language-left-behind-scaling-human-1","slug":"no-language-left-behind-scaling-human-1","title":"No Language Left Behind: Scaling Human-Centered Machine Translation","date":"2022-07-11","arxiv_id":"2207.04672","repositories_listed":9,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/no-language-left-behind-scaling-human-1#ran","syntology_url":"https://syntology.ai/paper/2207.04672","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.04672"}},"official":{"repos":["facebookresearch/fairseq","facebookresearch/stopes"],"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/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/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/qwen2-5-technical-report","slug":"qwen2-5-technical-report","title":"Qwen2.5 Technical Report","date":"2024-12-19","arxiv_id":"2412.15115","repositories_listed":6,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/qwen2-5-technical-report#ran","syntology_url":"https://syntology.ai/paper/2412.15115","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.15115"}},"official":{"repos":["qwenlm/qwen2.5"],"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/qwen2-technical-report","slug":"qwen2-technical-report","title":"Qwen2 Technical Report","date":"2024-07-15","arxiv_id":"2407.10671","repositories_listed":6,"syntology":null},{"url":"/paper/mixtral-of-experts","slug":"mixtral-of-experts","title":"Mixtral of Experts","date":"2024-01-08","arxiv_id":"2401.04088","repositories_listed":6,"syntology":{"n":5,"n_ran":5,"n_constructed":5,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 5 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) · 0 unverified; every one of the 5 samples that ran constructed an object rather than computing a result","sample_list":"/paper/mixtral-of-experts#ran","syntology_url":"https://syntology.ai/paper/2401.04088","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.04088"}},"official":null}},{"url":"/paper/deepseek-v2-a-strong-economical-and-efficient","slug":"deepseek-v2-a-strong-economical-and-efficient","title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","date":"2024-05-07","arxiv_id":"2405.04434","repositories_listed":5,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/deepseek-v2-a-strong-economical-and-efficient#ran","syntology_url":"https://syntology.ai/paper/2405.04434","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.04434"}},"official":{"repos":["deepseek-ai/deepseek-v2"],"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/jetmoe-reaching-llama2-performance-with-0-1m","slug":"jetmoe-reaching-llama2-performance-with-0-1m","title":"JetMoE: Reaching Llama2 Performance with 0.1M Dollars","date":"2024-04-11","arxiv_id":"2404.07413","repositories_listed":5,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/jetmoe-reaching-llama2-performance-with-0-1m#ran","syntology_url":"https://syntology.ai/paper/2404.07413","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07413"}},"official":{"repos":["myshell-ai/jetmoe"],"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","unlocated"]}}},{"url":"/paper/comet-fine-grained-computation-communication","slug":"comet-fine-grained-computation-communication","title":"Comet: Fine-grained Computation-communication Overlapping for Mixture-of-Experts","date":"2025-02-27","arxiv_id":"2502.19811","repositories_listed":4,"syntology":{"n":20,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/comet-fine-grained-computation-communication#ran","syntology_url":"https://syntology.ai/paper/2502.19811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.19811"}},"official":{"repos":["bytedance/flux"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":11,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/deepseek-v3-technical-report","slug":"deepseek-v3-technical-report","title":"DeepSeek-V3 Technical Report","date":"2024-12-27","arxiv_id":"2412.19437","repositories_listed":4,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/deepseek-v3-technical-report#ran","syntology_url":"https://syntology.ai/paper/2412.19437","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.19437"}},"official":{"repos":["deepseek-ai/deepseek-v3"],"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":["listed","official"]}}},{"url":"/paper/unity-by-diversity-improved-representation","slug":"unity-by-diversity-improved-representation","title":"Unity by Diversity: Improved Representation Learning in Multimodal VAEs","date":"2024-03-08","arxiv_id":"2403.05300","repositories_listed":4,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unity-by-diversity-improved-representation#ran","syntology_url":"https://syntology.ai/paper/2403.05300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05300"}},"official":{"repos":["thomassutter/mmvampvae","thomassutter/mmvmvae","yangmeng96/mmvmvae-hippocampal","agostini335/mmvmvae-mimic"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["community","found_in_text","official"]}}},{"url":"/paper/fast-feedforward-networks","slug":"fast-feedforward-networks","title":"Fast Feedforward Networks","date":"2023-08-28","arxiv_id":"2308.14711","repositories_listed":4,"syntology":null},{"url":"/paper/long-tailed-visual-recognition-via-self","slug":"long-tailed-visual-recognition-via-self","title":"Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavation","date":"2023-04-03","arxiv_id":"2304.01279","repositories_listed":4,"syntology":{"n":7,"n_ran":5,"n_constructed":4,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/long-tailed-visual-recognition-via-self#ran","syntology_url":"https://syntology.ai/paper/2304.01279","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.01279"}},"official":{"repos":["jinyan-06/shike"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/robust-federated-learning-by-mixture-of","slug":"robust-federated-learning-by-mixture-of","title":"Robust Federated Learning by Mixture of Experts","date":"2021-04-23","arxiv_id":"2104.11700","repositories_listed":4,"syntology":null},{"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/hunyuan-large-an-open-source-moe-model-with","slug":"hunyuan-large-an-open-source-moe-model-with","title":"Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent","date":"2024-11-04","arxiv_id":"2411.02265","repositories_listed":3,"syntology":null},{"url":"/paper/moh-multi-head-attention-as-mixture-of-head","slug":"moh-multi-head-attention-as-mixture-of-head","title":"MoH: Multi-Head Attention as Mixture-of-Head Attention","date":"2024-10-15","arxiv_id":"2410.11842","repositories_listed":3,"syntology":{"n":18,"n_ran":14,"n_constructed":5,"n_ran_checked":5,"n_instrument":9,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":3,"phrase":"14 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 9 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/moh-multi-head-attention-as-mixture-of-head#ran","syntology_url":"https://syntology.ai/paper/2410.11842","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.11842"}},"official":{"repos":["skyworkai/moh"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/moe-accelerating-mixture-of-experts-methods","slug":"moe-accelerating-mixture-of-experts-methods","title":"MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts","date":"2024-10-09","arxiv_id":"2410.07348","repositories_listed":3,"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/moe-accelerating-mixture-of-experts-methods#ran","syntology_url":"https://syntology.ai/paper/2410.07348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07348"}},"official":{"repos":["skyworkai/moe-plus-plus"],"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":["unlocated"]}}},{"url":"/paper/jamba-a-hybrid-transformer-mamba-language","slug":"jamba-a-hybrid-transformer-mamba-language","title":"Jamba: A Hybrid Transformer-Mamba Language Model","date":"2024-03-28","arxiv_id":"2403.19887","repositories_listed":3,"syntology":null},{"url":"/paper/scattered-mixture-of-experts-implementation","slug":"scattered-mixture-of-experts-implementation","title":"Scattered Mixture-of-Experts Implementation","date":"2024-03-13","arxiv_id":"2403.08245","repositories_listed":3,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/scattered-mixture-of-experts-implementation#ran","syntology_url":"https://syntology.ai/paper/2403.08245","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.08245"}},"official":{"repos":["shawntan/scattermoe"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/rethinking-llm-language-adaptation-a-case","slug":"rethinking-llm-language-adaptation-a-case","title":"Rethinking LLM Language Adaptation: A Case Study on Chinese Mixtral","date":"2024-03-04","arxiv_id":"2403.01851","repositories_listed":3,"syntology":null},{"url":"/paper/moe-llava-mixture-of-experts-for-large-vision","slug":"moe-llava-mixture-of-experts-for-large-vision","title":"MoE-LLaVA: Mixture of Experts for Large Vision-Language Models","date":"2024-01-29","arxiv_id":"2401.15947","repositories_listed":3,"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":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/moe-llava-mixture-of-experts-for-large-vision#ran","syntology_url":"https://syntology.ai/paper/2401.15947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.15947"}},"official":{"repos":["PKU-YuanGroup/MoE-LLaVA"],"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/megablocks-efficient-sparse-training-with","slug":"megablocks-efficient-sparse-training-with","title":"MegaBlocks: Efficient Sparse Training with Mixture-of-Experts","date":"2022-11-29","arxiv_id":"2211.15841","repositories_listed":3,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/megablocks-efficient-sparse-training-with#ran","syntology_url":"https://syntology.ai/paper/2211.15841","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.15841"}},"official":{"repos":["stanford-futuredata/megablocks"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/designing-effective-sparse-expert-models","slug":"designing-effective-sparse-expert-models","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","date":"2022-02-17","arxiv_id":"2202.08906","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/designing-effective-sparse-expert-models#ran","syntology_url":"https://syntology.ai/paper/2202.08906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.08906"}},"official":{"repos":["tensorflow/mesh"],"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/deepspeed-moe-advancing-mixture-of-experts","slug":"deepspeed-moe-advancing-mixture-of-experts","title":"DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale","date":"2022-01-14","arxiv_id":"2201.05596","repositories_listed":3,"syntology":null},{"url":"/paper/dselect-k-differentiable-selection-in-the","slug":"dselect-k-differentiable-selection-in-the","title":"DSelect-k: Differentiable Selection in the Mixture of Experts with Applications to Multi-Task Learning","date":"2021-06-07","arxiv_id":"2106.03760","repositories_listed":3,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dselect-k-differentiable-selection-in-the#ran","syntology_url":"https://syntology.ai/paper/2106.03760","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03760"}},"official":{"repos":["google-research/google-research"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"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/non-normal-mixtures-of-experts","slug":"non-normal-mixtures-of-experts","title":"Non-Normal Mixtures of Experts","date":"2015-06-22","arxiv_id":"1506.06707","repositories_listed":3,"syntology":null},{"url":"/paper/flashdmoe-fast-distributed-moe-in-a-single","slug":"flashdmoe-fast-distributed-moe-in-a-single","title":"FlashDMoE: Fast Distributed MoE in a Single Kernel","date":"2025-06-05","arxiv_id":"2506.04667","repositories_listed":2,"syntology":{"n":7,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 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; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/flashdmoe-fast-distributed-moe-in-a-single#ran","syntology_url":"https://syntology.ai/paper/2506.04667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.04667"}},"official":{"repos":["osayamenja/aristos","osayamenja/kleos"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hidream-i1-a-high-efficient-image-generative","slug":"hidream-i1-a-high-efficient-image-generative","title":"HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformer","date":"2025-05-28","arxiv_id":"2505.22705","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/hidream-i1-a-high-efficient-image-generative#ran","syntology_url":"https://syntology.ai/paper/2505.22705","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.22705"}},"official":{"repos":["hidream-ai/hidream-e1","hidream-ai/hidream-i1"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/competesmoe-statistically-guaranteed-mixture","slug":"competesmoe-statistically-guaranteed-mixture","title":"CompeteSMoE -- Statistically Guaranteed Mixture of Experts Training via Competition","date":"2025-05-19","arxiv_id":"2505.13380","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"6 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; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/competesmoe-statistically-guaranteed-mixture#ran","syntology_url":"https://syntology.ai/paper/2505.13380","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.13380"}},"official":{"repos":["fsoft-aic/competesmoe"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/brainmap-learning-multiple-activation","slug":"brainmap-learning-multiple-activation","title":"BrainMAP: Learning Multiple Activation Pathways in Brain Networks","date":"2024-12-23","arxiv_id":"2412.17404","repositories_listed":2,"syntology":null},{"url":"/paper/wonderful-matrices-combining-for-a-more","slug":"wonderful-matrices-combining-for-a-more","title":"Wonderful Matrices: Combining for a More Efficient and Effective Foundation Model Architecture","date":"2024-12-16","arxiv_id":"2412.11834","repositories_listed":2,"syntology":null},{"url":"/paper/olmoe-open-mixture-of-experts-language-models","slug":"olmoe-open-mixture-of-experts-language-models","title":"OLMoE: Open Mixture-of-Experts Language Models","date":"2024-09-03","arxiv_id":"2409.02060","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":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/olmoe-open-mixture-of-experts-language-models#ran","syntology_url":"https://syntology.ai/paper/2409.02060","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.02060"}},"official":{"repos":["allenai/OLMoE"],"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/jamba-1-5-hybrid-transformer-mamba-models-at","slug":"jamba-1-5-hybrid-transformer-mamba-models-at","title":"Jamba-1.5: Hybrid Transformer-Mamba Models at Scale","date":"2024-08-22","arxiv_id":"2408.12570","repositories_listed":2,"syntology":null},{"url":"/paper/moe-lpr-multilingual-extension-of-large","slug":"moe-lpr-multilingual-extension-of-large","title":"MoE-LPR: Multilingual Extension of Large Language Models through Mixture-of-Experts with Language Priors Routing","date":"2024-08-21","arxiv_id":"2408.11396","repositories_listed":2,"syntology":null},{"url":"/paper/llama-moe-building-mixture-of-experts-from","slug":"llama-moe-building-mixture-of-experts-from","title":"LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training","date":"2024-06-24","arxiv_id":"2406.16554","repositories_listed":2,"syntology":null},{"url":"/paper/interpretable-preferences-via-multi-objective","slug":"interpretable-preferences-via-multi-objective","title":"Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts","date":"2024-06-18","arxiv_id":"2406.12845","repositories_listed":2,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"9 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/interpretable-preferences-via-multi-objective#ran","syntology_url":"https://syntology.ai/paper/2406.12845","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12845"}},"official":{"repos":["RLHFlow/RLHF-Reward-Modeling"],"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/parrot-multilingual-visual-instruction-tuning","slug":"parrot-multilingual-visual-instruction-tuning","title":"Parrot: Multilingual Visual Instruction Tuning","date":"2024-06-04","arxiv_id":"2406.02539","repositories_listed":2,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":4,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/parrot-multilingual-visual-instruction-tuning#ran","syntology_url":"https://syntology.ai/paper/2406.02539","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02539"}},"official":{"repos":["aidc-ai/parrot"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-a-generalist-and-blind-rgb-x-tracker","slug":"towards-a-generalist-and-blind-rgb-x-tracker","title":"XTrack: Multimodal Training Boosts RGB-X Video Object Trackers","date":"2024-05-28","arxiv_id":"2405.17773","repositories_listed":2,"syntology":null},{"url":"/paper/mvmoe-multi-task-vehicle-routing-solver-with","slug":"mvmoe-multi-task-vehicle-routing-solver-with","title":"MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts","date":"2024-05-02","arxiv_id":"2405.01029","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mvmoe-multi-task-vehicle-routing-solver-with#ran","syntology_url":"https://syntology.ai/paper/2405.01029","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.01029"}},"official":{"repos":["ai4co/awesome-fm4co","royalskye/routing-mvmoe"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/swin2-mose-a-new-single-image-super","slug":"swin2-mose-a-new-single-image-super","title":"Swin2-MoSE: A New Single Image Super-Resolution Model for Remote Sensing","date":"2024-04-29","arxiv_id":"2404.18924","repositories_listed":2,"syntology":null},{"url":"/paper/mixlora-enhancing-large-language-models-fine","slug":"mixlora-enhancing-large-language-models-fine","title":"MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts","date":"2024-04-22","arxiv_id":"2404.15159","repositories_listed":2,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":5,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/mixlora-enhancing-large-language-models-fine#ran","syntology_url":"https://syntology.ai/paper/2404.15159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.15159"}},"official":{"repos":["TUDB-Labs/MixLoRA","mikecovlee/mLoRA"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/moe-tinymed-mixture-of-experts-for-tiny","slug":"moe-tinymed-mixture-of-experts-for-tiny","title":"Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models","date":"2024-04-16","arxiv_id":"2404.10237","repositories_listed":2,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/moe-tinymed-mixture-of-experts-for-tiny#ran","syntology_url":"https://syntology.ai/paper/2404.10237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.10237"}},"official":{"repos":["jiangsongtao/med-moe","jiangsongtao/tinymed"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/boosting-continual-learning-of-vision","slug":"boosting-continual-learning-of-vision","title":"Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters","date":"2024-03-18","arxiv_id":"2403.11549","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"2 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/boosting-continual-learning-of-vision#ran","syntology_url":"https://syntology.ai/paper/2403.11549","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11549"}},"official":{"repos":["jiazuoyu/moe-adapters4cl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/switch-diffusion-transformer-synergizing","slug":"switch-diffusion-transformer-synergizing","title":"Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts","date":"2024-03-14","arxiv_id":"2403.09176","repositories_listed":2,"syntology":{"n":18,"n_ran":15,"n_constructed":0,"n_ran_checked":8,"n_instrument":7,"n_unverified":3,"n_honours":4,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 0 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/switch-diffusion-transformer-synergizing#ran","syntology_url":"https://syntology.ai/paper/2403.09176","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09176"}},"official":{"repos":["byeongjun-park/Switch-DiT"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/multilinear-mixture-of-experts-scalable","slug":"multilinear-mixture-of-experts-scalable","title":"Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization","date":"2024-02-19","arxiv_id":"2402.12550","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":1,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multilinear-mixture-of-experts-scalable#ran","syntology_url":"https://syntology.ai/paper/2402.12550","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12550"}},"official":{"repos":["james-oldfield/mmoe","james-oldfield/mumoe"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/deepseekmoe-towards-ultimate-expert","slug":"deepseekmoe-towards-ultimate-expert","title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","date":"2024-01-11","arxiv_id":"2401.06066","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":3,"n_ran_checked":3,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/deepseekmoe-towards-ultimate-expert#ran","syntology_url":"https://syntology.ai/paper/2401.06066","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.06066"}},"official":{"repos":["deepseek-ai/deepseek-moe"],"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":["listed","official"]}}},{"url":"/paper/parameter-efficient-sparsity-crafting-from","slug":"parameter-efficient-sparsity-crafting-from","title":"Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks","date":"2024-01-05","arxiv_id":"2401.02731","repositories_listed":2,"syntology":null},{"url":"/paper/solar-10-7b-scaling-large-language-models","slug":"solar-10-7b-scaling-large-language-models","title":"SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling","date":"2023-12-23","arxiv_id":"2312.15166","repositories_listed":2,"syntology":{"n":26,"n_ran":22,"n_constructed":0,"n_ran_checked":10,"n_instrument":12,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":3,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 12 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/solar-10-7b-scaling-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2312.15166","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15166"}},"official":null}},{"url":"/paper/switchhead-accelerating-transformers-with","slug":"switchhead-accelerating-transformers-with","title":"SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention","date":"2023-12-13","arxiv_id":"2312.07987","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/switchhead-accelerating-transformers-with#ran","syntology_url":"https://syntology.ai/paper/2312.07987","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.07987"}},"official":{"repos":["robertcsordas/switchhead","robertcsordas/moe_attention"],"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/octavius-mitigating-task-interference-in","slug":"octavius-mitigating-task-interference-in","title":"Octavius: Mitigating Task Interference in MLLMs via LoRA-MoE","date":"2023-11-05","arxiv_id":"2311.02684","repositories_listed":2,"syntology":null},{"url":"/paper/sparse-universal-transformer","slug":"sparse-universal-transformer","title":"Sparse Universal Transformer","date":"2023-10-11","arxiv_id":"2310.07096","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/sparse-universal-transformer#ran","syntology_url":"https://syntology.ai/paper/2310.07096","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07096"}},"official":null}},{"url":"/paper/exploiting-transformer-activation-sparsity","slug":"exploiting-transformer-activation-sparsity","title":"Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion","date":"2023-10-06","arxiv_id":"2310.04361","repositories_listed":2,"syntology":{"n":17,"n_ran":15,"n_constructed":0,"n_ran_checked":13,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":12,"n_pointer_only":2,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/exploiting-transformer-activation-sparsity#ran","syntology_url":"https://syntology.ai/paper/2310.04361","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04361"}},"official":{"repos":["bartwojcik/d2dmoe","bartwojcik/sadmoe"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/hyperformer-enhancing-entity-and-relation","slug":"hyperformer-enhancing-entity-and-relation","title":"HyperFormer: Enhancing Entity and Relation Interaction for Hyper-Relational Knowledge Graph Completion","date":"2023-08-12","arxiv_id":"2308.06512","repositories_listed":2,"syntology":null},{"url":"/paper/deep-learning-techniques-for-blind-image","slug":"deep-learning-techniques-for-blind-image","title":"Deep learning techniques for blind image super-resolution: A high-scale multi-domain perspective evaluation","date":"2023-06-15","arxiv_id":"2306.09426","repositories_listed":2,"syntology":null},{"url":"/paper/patch-level-routing-in-mixture-of-experts-is","slug":"patch-level-routing-in-mixture-of-experts-is","title":"Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks","date":"2023-06-07","arxiv_id":"2306.04073","repositories_listed":2,"syntology":null},{"url":"/paper/comet-learning-cardinality-constrained","slug":"comet-learning-cardinality-constrained","title":"COMET: Learning Cardinality Constrained Mixture of Experts with Trees and Local Search","date":"2023-06-05","arxiv_id":"2306.02824","repositories_listed":2,"syntology":null},{"url":"/paper/re-iqa-unsupervised-learning-for-image","slug":"re-iqa-unsupervised-learning-for-image","title":"Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wild","date":"2023-04-02","arxiv_id":"2304.00451","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/re-iqa-unsupervised-learning-for-image#ran","syntology_url":"https://syntology.ai/paper/2304.00451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.00451"}},"official":{"repos":["avinabsaha/ReIQA"],"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/mixture-of-attention-heads-selecting","slug":"mixture-of-attention-heads-selecting","title":"Mixture of Attention Heads: Selecting Attention Heads Per Token","date":"2022-10-11","arxiv_id":"2210.05144","repositories_listed":2,"syntology":{"n":17,"n_ran":13,"n_constructed":2,"n_ran_checked":8,"n_instrument":5,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":4,"phrase":"13 ran (of which 2 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/mixture-of-attention-heads-selecting#ran","syntology_url":"https://syntology.ai/paper/2210.05144","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.05144"}},"official":{"repos":["yikangshen/moa"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","listed","official"]}}},{"url":"/paper/towards-understanding-mixture-of-experts-in","slug":"towards-understanding-mixture-of-experts-in","title":"Towards Understanding Mixture of Experts in Deep Learning","date":"2022-08-04","arxiv_id":"2208.02813","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"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) · 1 unverified","sample_list":"/paper/towards-understanding-mixture-of-experts-in#ran","syntology_url":"https://syntology.ai/paper/2208.02813","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.02813"}},"official":{"repos":["uclaml/MoE"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/deepspeed-inference-enabling-efficient","slug":"deepspeed-inference-enabling-efficient","title":"DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale","date":"2022-06-30","arxiv_id":"2207.00032","repositories_listed":2,"syntology":null},{"url":"/paper/towards-universal-sequence-representation","slug":"towards-universal-sequence-representation","title":"Towards Universal Sequence Representation Learning for Recommender Systems","date":"2022-06-13","arxiv_id":"2206.05941","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"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, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/towards-universal-sequence-representation#ran","syntology_url":"https://syntology.ai/paper/2206.05941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.05941"}},"official":{"repos":["rucaibox/unisrec"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/sparse-fusion-mixture-of-experts-are-domain","slug":"sparse-fusion-mixture-of-experts-are-domain","title":"Sparse Mixture-of-Experts are Domain Generalizable Learners","date":"2022-06-08","arxiv_id":"2206.04046","repositories_listed":2,"syntology":{"n":14,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":5,"n_honours":3,"n_violates":0,"n_no_contract":2,"n_pointer_only":14,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/sparse-fusion-mixture-of-experts-are-domain#ran","syntology_url":"https://syntology.ai/paper/2206.04046","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.04046"}},"official":{"repos":["luodian/sf-moe-dg"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/tutel-adaptive-mixture-of-experts-at-scale","slug":"tutel-adaptive-mixture-of-experts-at-scale","title":"Tutel: Adaptive Mixture-of-Experts at Scale","date":"2022-06-07","arxiv_id":"2206.03382","repositories_listed":2,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/tutel-adaptive-mixture-of-experts-at-scale#ran","syntology_url":"https://syntology.ai/paper/2206.03382","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.03382"}},"official":{"repos":["microsoft/Swin-Transformer","microsoft/tutel"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/text2human-text-driven-controllable-human","slug":"text2human-text-driven-controllable-human","title":"Text2Human: Text-Driven Controllable Human Image Generation","date":"2022-05-31","arxiv_id":"2205.15996","repositories_listed":2,"syntology":null},{"url":"/paper/on-the-representation-collapse-of-sparse","slug":"on-the-representation-collapse-of-sparse","title":"On the Representation Collapse of Sparse Mixture of Experts","date":"2022-04-20","arxiv_id":"2204.09179","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/on-the-representation-collapse-of-sparse#ran","syntology_url":"https://syntology.ai/paper/2204.09179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.09179"}},"official":{"repos":["microsoft/unilm"],"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/parameter-efficient-mixture-of-experts","slug":"parameter-efficient-mixture-of-experts","title":"Parameter-Efficient Mixture-of-Experts Architecture for Pre-trained Language Models","date":"2022-03-02","arxiv_id":"2203.01104","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/parameter-efficient-mixture-of-experts#ran","syntology_url":"https://syntology.ai/paper/2203.01104","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.01104"}},"official":{"repos":["rucaibox/mpo","rucaibox/mpoe"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dense-to-sparse-gate-for-mixture-of-experts-1","slug":"dense-to-sparse-gate-for-mixture-of-experts-1","title":"EvoMoE: An Evolutional Mixture-of-Experts Training Framework via Dense-To-Sparse Gate","date":"2021-12-29","arxiv_id":"2112.14397","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/dense-to-sparse-gate-for-mixture-of-experts-1#ran","syntology_url":"https://syntology.ai/paper/2112.14397","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.14397"}},"official":{"repos":["codecaution/evomoe"],"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/unsupervised-foreground-extraction-via-deep","slug":"unsupervised-foreground-extraction-via-deep","title":"Unsupervised Foreground Extraction via Deep Region Competition","date":"2021-10-29","arxiv_id":"2110.15497","repositories_listed":2,"syntology":{"n":15,"n_ran":13,"n_constructed":10,"n_ran_checked":12,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":11,"n_pointer_only":15,"phrase":"13 ran (of which 10 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/unsupervised-foreground-extraction-via-deep#ran","syntology_url":"https://syntology.ai/paper/2110.15497","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.15497"}},"official":{"repos":["yupeiyu98/deep-region-competition","yupeiyu98/drc"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":10,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-video-text-retrieval-by-multi","slug":"improving-video-text-retrieval-by-multi","title":"Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss","date":"2021-09-09","arxiv_id":"2109.04290","repositories_listed":2,"syntology":null},{"url":"/paper/cross-domain-label-adaptive-stance-detection","slug":"cross-domain-label-adaptive-stance-detection","title":"Cross-Domain Label-Adaptive Stance Detection","date":"2021-04-15","arxiv_id":"2104.07467","repositories_listed":2,"syntology":null},{"url":"/paper/multi-view-depth-estimation-using-epipolar","slug":"multi-view-depth-estimation-using-epipolar","title":"Multi-view Depth Estimation using Epipolar Spatio-Temporal Networks","date":"2020-11-26","arxiv_id":"2011.13118","repositories_listed":2,"syntology":null},{"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/learninghome-crowdsourced-training-of-large","slug":"learninghome-crowdsourced-training-of-large","title":"Towards Crowdsourced Training of Large Neural Networks using Decentralized Mixture-of-Experts","date":"2020-02-10","arxiv_id":"2002.04013","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":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/learninghome-crowdsourced-training-of-large#ran","syntology_url":"https://syntology.ai/paper/2002.04013","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.04013"}},"official":{"repos":["mryab/learning-at-home"],"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/moet-interpretable-and-verifiable","slug":"moet-interpretable-and-verifiable","title":"MoËT: Mixture of Expert Trees and its Application to Verifiable Reinforcement Learning","date":"2019-06-16","arxiv_id":"1906.06717","repositories_listed":2,"syntology":null},{"url":"/paper/mofe-time-mixture-of-frequency-domain-experts","slug":"mofe-time-mixture-of-frequency-domain-experts","title":"MoFE-Time: Mixture of Frequency Domain Experts for Time-Series Forecasting Models","date":"2025-07-09","arxiv_id":"2507.06502","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-on-prompt-tuning","slug":"a-survey-on-prompt-tuning","title":"A Survey on Prompt Tuning","date":"2025-07-08","arxiv_id":"2507.06085","repositories_listed":1,"syntology":null},{"url":"/paper/growing-transformers-modular-composition-and","slug":"growing-transformers-modular-composition-and","title":"Growing Transformers: Modular Composition and Layer-wise Expansion on a Frozen Substrate","date":"2025-07-08","arxiv_id":"2507.07129","repositories_listed":1,"syntology":null},{"url":"/paper/learning-robust-stereo-matching-in-the-wild","slug":"learning-robust-stereo-matching-in-the-wild","title":"Learning Robust Stereo Matching in the Wild with Selective Mixture-of-Experts","date":"2025-07-07","arxiv_id":"2507.04631","repositories_listed":1,"syntology":null},{"url":"/paper/latent-prototype-routing-achieving-near","slug":"latent-prototype-routing-achieving-near","title":"Latent Prototype Routing: Achieving Near-Perfect Load Balancing in Mixture-of-Experts","date":"2025-06-26","arxiv_id":"2506.21328","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-skip-the-middle-layers-of","slug":"learning-to-skip-the-middle-layers-of","title":"Learning to Skip the Middle Layers of Transformers","date":"2025-06-26","arxiv_id":"2506.21103","repositories_listed":1,"syntology":null},{"url":"/paper/guilomo-allocating-expert-number-and-rank-for","slug":"guilomo-allocating-expert-number-and-rank-for","title":"GuiLoMo: Allocating Expert Number and Rank for LoRA-MoE via Bilevel Optimization with GuidedSelection Vectors","date":"2025-06-17","arxiv_id":"2506.14646","repositories_listed":1,"syntology":null},{"url":"/paper/minimax-m1-scaling-test-time-compute","slug":"minimax-m1-scaling-test-time-compute","title":"MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention","date":"2025-06-16","arxiv_id":"2506.13585","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/minimax-m1-scaling-test-time-compute#ran","syntology_url":"https://syntology.ai/paper/2506.13585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.13585"}},"official":{"repos":["minimax-ai/minimax-m1"],"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/structural-similarity-inspired-unfolding-for","slug":"structural-similarity-inspired-unfolding-for","title":"Structural Similarity-Inspired Unfolding for Lightweight Image Super-Resolution","date":"2025-06-13","arxiv_id":"2506.11823","repositories_listed":1,"syntology":null},{"url":"/paper/a-two-phase-deep-learning-framework-for","slug":"a-two-phase-deep-learning-framework-for","title":"A Two-Phase Deep Learning Framework for Adaptive Time-Stepping in High-Speed Flow Modeling","date":"2025-06-09","arxiv_id":"2506.07969","repositories_listed":1,"syntology":null},{"url":"/paper/moe-mlora-for-multi-domain-ctr-prediction","slug":"moe-mlora-for-multi-domain-ctr-prediction","title":"MoE-MLoRA for Multi-Domain CTR Prediction: Efficient Adaptation with Expert Specialization","date":"2025-06-09","arxiv_id":"2506.07563","repositories_listed":1,"syntology":null},{"url":"/paper/stamimputer-spatio-temporal-attention-moe-for","slug":"stamimputer-spatio-temporal-attention-moe-for","title":"STAMImputer: Spatio-Temporal Attention MoE for Traffic Data Imputation","date":"2025-06-09","arxiv_id":"2506.08054","repositories_listed":1,"syntology":null},{"url":"/paper/space-your-genomic-profile-predictor-is-a","slug":"space-your-genomic-profile-predictor-is-a","title":"SPACE: Your Genomic Profile Predictor is a Powerful DNA Foundation Model","date":"2025-06-02","arxiv_id":"2506.01833","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":3,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 2 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/space-your-genomic-profile-predictor-is-a#ran","syntology_url":"https://syntology.ai/paper/2506.01833","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.01833"}},"official":{"repos":["zhujiwei111/space"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mastering-massive-multi-task-reinforcement","slug":"mastering-massive-multi-task-reinforcement","title":"Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer","date":"2025-05-30","arxiv_id":"2505.24378","repositories_listed":1,"syntology":null},{"url":"/paper/from-knowledge-to-noise-ctim-rover-and-the","slug":"from-knowledge-to-noise-ctim-rover-and-the","title":"From Knowledge to Noise: CTIM-Rover and the Pitfalls of Episodic Memory in Software Engineering Agents","date":"2025-05-29","arxiv_id":"2505.23422","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/from-knowledge-to-noise-ctim-rover-and-the#ran","syntology_url":"https://syntology.ai/paper/2505.23422","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23422"}},"official":{"repos":["liqs-v2/ctim-rover"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-human-centric-approach-to-explainable-ai","slug":"a-human-centric-approach-to-explainable-ai","title":"A Human-Centric Approach to Explainable AI for Personalized Education","date":"2025-05-28","arxiv_id":"2505.22541","repositories_listed":1,"syntology":null},{"url":"/paper/flame-moe-a-transparent-end-to-end-research","slug":"flame-moe-a-transparent-end-to-end-research","title":"FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models","date":"2025-05-26","arxiv_id":"2505.20225","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-gating-mechanism-in-sparse-moe","slug":"rethinking-gating-mechanism-in-sparse-moe","title":"Rethinking Gating Mechanism in Sparse MoE: Handling Arbitrary Modality Inputs with Confidence-Guided Gate","date":"2025-05-26","arxiv_id":"2505.19525","repositories_listed":1,"syntology":{"n":8,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"3 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; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/rethinking-gating-mechanism-in-sparse-moe#ran","syntology_url":"https://syntology.ai/paper/2505.19525","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19525"}},"official":{"repos":["icuraslw/official-repository-of-confsmoe"],"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":["found_in_text","official"]}}},{"url":"/paper/wina-weight-informed-neuron-activation-for","slug":"wina-weight-informed-neuron-activation-for","title":"WINA: Weight Informed Neuron Activation for Accelerating Large Language Model Inference","date":"2025-05-26","arxiv_id":"2505.19427","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":3,"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/wina-weight-informed-neuron-activation-for#ran","syntology_url":"https://syntology.ai/paper/2505.19427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19427"}},"official":{"repos":["microsoft/wina"],"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/i2moe-interpretable-multimodal-interaction","slug":"i2moe-interpretable-multimodal-interaction","title":"I2MoE: Interpretable Multimodal Interaction-aware Mixture-of-Experts","date":"2025-05-25","arxiv_id":"2505.19190","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"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) · 0 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/i2moe-interpretable-multimodal-interaction#ran","syntology_url":"https://syntology.ai/paper/2505.19190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19190"}},"official":{"repos":["raina-xin/i2moe"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rankllm-a-python-package-for-reranking-with","slug":"rankllm-a-python-package-for-reranking-with","title":"RankLLM: A Python Package for Reranking with LLMs","date":"2025-05-25","arxiv_id":"2505.19284","repositories_listed":1,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/rankllm-a-python-package-for-reranking-with#ran","syntology_url":"https://syntology.ai/paper/2505.19284","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19284"}},"official":null}},{"url":"/paper/guiding-the-experts-semantic-priors-for","slug":"guiding-the-experts-semantic-priors-for","title":"Guiding the Experts: Semantic Priors for Efficient and Focused MoE Routing","date":"2025-05-24","arxiv_id":"2505.18586","repositories_listed":1,"syntology":null}],"syntology_records":57,"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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"papers_where_code_ran":216,"papers_where_code_ran_first_page":"/task/mixture-of-experts/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":14,"url":"/task/mixture-of-experts/papers/2","json":"/task/mixture-of-experts/papers/2.json","rows":100},{"order":"archive","page":3,"of":14,"url":"/task/mixture-of-experts/papers/3","json":"/task/mixture-of-experts/papers/3.json","rows":100},{"order":"archive","page":4,"of":14,"url":"/task/mixture-of-experts/papers/4","json":"/task/mixture-of-experts/papers/4.json","rows":100},{"order":"archive","page":5,"of":14,"url":"/task/mixture-of-experts/papers/5","json":"/task/mixture-of-experts/papers/5.json","rows":100},{"order":"archive","page":6,"of":14,"url":"/task/mixture-of-experts/papers/6","json":"/task/mixture-of-experts/papers/6.json","rows":100},{"order":"archive","page":7,"of":14,"url":"/task/mixture-of-experts/papers/7","json":"/task/mixture-of-experts/papers/7.json","rows":100},{"order":"archive","page":8,"of":14,"url":"/task/mixture-of-experts/papers/8","json":"/task/mixture-of-experts/papers/8.json","rows":100},{"order":"archive","page":9,"of":14,"url":"/task/mixture-of-experts/papers/9","json":"/task/mixture-of-experts/papers/9.json","rows":100},{"order":"archive","page":10,"of":14,"url":"/task/mixture-of-experts/papers/10","json":"/task/mixture-of-experts/papers/10.json","rows":100},{"order":"archive","page":11,"of":14,"url":"/task/mixture-of-experts/papers/11","json":"/task/mixture-of-experts/papers/11.json","rows":100},{"order":"archive","page":12,"of":14,"url":"/task/mixture-of-experts/papers/12","json":"/task/mixture-of-experts/papers/12.json","rows":100},{"order":"archive","page":13,"of":14,"url":"/task/mixture-of-experts/papers/13","json":"/task/mixture-of-experts/papers/13.json","rows":100},{"order":"archive","page":14,"of":14,"url":"/task/mixture-of-experts/papers/14","json":"/task/mixture-of-experts/papers/14.json","rows":12},{"order":"ran","page":1,"of":3,"url":"/task/mixture-of-experts/papers/ran/1","json":"/task/mixture-of-experts/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":3,"url":"/task/mixture-of-experts/papers/ran/2","json":"/task/mixture-of-experts/papers/ran/2.json","rows":100},{"order":"ran","page":3,"of":3,"url":"/task/mixture-of-experts/papers/ran/3","json":"/task/mixture-of-experts/papers/ran/3.json","rows":16}],"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":"7106e22fb50155a3ba6fcb2b957263e1f9ebe8cd8346869809fffce3dfc304b6","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}