{"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/2","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":2,"pages_in_order":3,"rows_per_page":100,"rows":[101,200],"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/1","next":"/task/mixture-of-experts/papers/ran/3","papers":[{"url":"/paper/meteora-multiple-tasks-embedded-lora-for","slug":"meteora-multiple-tasks-embedded-lora-for","title":"MeteoRA: Multiple-tasks Embedded LoRA for Large Language Models","date":"2024-05-19","arxiv_id":"2405.13053","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":2,"n_honours":3,"n_violates":0,"n_no_contract":2,"n_pointer_only":10,"phrase":"8 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/meteora-multiple-tasks-embedded-lora-for#ran","syntology_url":"https://syntology.ai/paper/2405.13053","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.13053"}},"official":{"repos":["paragonlight/meteor-of-lora"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/uni-moe-scaling-unified-multimodal-llms-with","slug":"uni-moe-scaling-unified-multimodal-llms-with","title":"Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts","date":"2024-05-18","arxiv_id":"2405.11273","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"6 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/uni-moe-scaling-unified-multimodal-llms-with#ran","syntology_url":"https://syntology.ai/paper/2405.11273","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.11273"}},"official":{"repos":["hitsz-tmg/umoe-scaling-unified-multimodal-llms"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/m-4-oe-a-foundation-model-for-medical","slug":"m-4-oe-a-foundation-model-for-medical","title":"M$^4$oE: A Foundation Model for Medical Multimodal Image Segmentation with Mixture of Experts","date":"2024-05-15","arxiv_id":"2405.09446","repositories_listed":1,"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":6,"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/m-4-oe-a-foundation-model-for-medical#ran","syntology_url":"https://syntology.ai/paper/2405.09446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.09446"}},"official":{"repos":["jefferyjiang-yf/m4oe"],"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/cumo-scaling-multimodal-llm-with-co-upcycled","slug":"cumo-scaling-multimodal-llm-with-co-upcycled","title":"CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts","date":"2024-05-09","arxiv_id":"2405.05949","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":6,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cumo-scaling-multimodal-llm-with-co-upcycled#ran","syntology_url":"https://syntology.ai/paper/2405.05949","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.05949"}},"official":{"repos":["shi-labs/cumo"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"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/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/m3oe-multi-domain-multi-task-mixture-of","slug":"m3oe-multi-domain-multi-task-mixture-of","title":"M3oE: Multi-Domain Multi-Task Mixture-of Experts Recommendation Framework","date":"2024-04-29","arxiv_id":"2404.18465","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/m3oe-multi-domain-multi-task-mixture-of#ran","syntology_url":"https://syntology.ai/paper/2404.18465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.18465"}},"official":{"repos":["applied-machine-learning-lab/m3oe"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-head-mixture-of-experts","slug":"multi-head-mixture-of-experts","title":"Multi-Head Mixture-of-Experts","date":"2024-04-23","arxiv_id":"2404.15045","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-head-mixture-of-experts#ran","syntology_url":"https://syntology.ai/paper/2404.15045","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.15045"}},"official":{"repos":["yushuiwx/mh-moe"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/xft-unlocking-the-power-of-code-instruction","slug":"xft-unlocking-the-power-of-code-instruction","title":"XFT: Unlocking the Power of Code Instruction Tuning by Simply Merging Upcycled Mixture-of-Experts","date":"2024-04-23","arxiv_id":"2404.15247","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/xft-unlocking-the-power-of-code-instruction#ran","syntology_url":"https://syntology.ai/paper/2404.15247","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.15247"}},"official":{"repos":["ise-uiuc/xft"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"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":6,"n_instrument":0,"n_unverified":5,"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) · 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":6,"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":4,"n_instrument":3,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 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":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/moe-ffd-mixture-of-experts-for-generalized","slug":"moe-ffd-mixture-of-experts-for-generalized","title":"MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection","date":"2024-04-12","arxiv_id":"2404.08452","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"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; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/moe-ffd-mixture-of-experts-for-generalized#ran","syntology_url":"https://syntology.ai/paper/2404.08452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.08452"}},"official":{"repos":["lovesiamesecat/moe-ffd"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/prompt-prompted-mixture-of-experts-for","slug":"prompt-prompted-mixture-of-experts-for","title":"Prompt-prompted Adaptive Structured Pruning for Efficient LLM Generation","date":"2024-04-01","arxiv_id":"2404.01365","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":10,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/prompt-prompted-mixture-of-experts-for#ran","syntology_url":"https://syntology.ai/paper/2404.01365","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01365"}},"official":{"repos":["hdong920/griffin"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-task-dense-prediction-via-mixture-of","slug":"multi-task-dense-prediction-via-mixture-of","title":"Multi-Task Dense Prediction via Mixture of Low-Rank Experts","date":"2024-03-26","arxiv_id":"2403.17749","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"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) · 2 unverified","sample_list":"/paper/multi-task-dense-prediction-via-mixture-of#ran","syntology_url":"https://syntology.ai/paper/2403.17749","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17749"}},"official":{"repos":["yuqiyang213/mlore"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"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/dynamic-tuning-towards-parameter-and","slug":"dynamic-tuning-towards-parameter-and","title":"Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation","date":"2024-03-18","arxiv_id":"2403.11808","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"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 0 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","sample_list":"/paper/dynamic-tuning-towards-parameter-and#ran","syntology_url":"https://syntology.ai/paper/2403.11808","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11808"}},"official":{"repos":["nus-hpc-ai-lab/dynamic-tuning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"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":9,"n_instrument":6,"n_unverified":3,"n_honours":3,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 6 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":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"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/unleashing-the-power-of-meta-tuning-for-few","slug":"unleashing-the-power-of-meta-tuning-for-few","title":"Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts","date":"2024-03-13","arxiv_id":"2403.08477","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unleashing-the-power-of-meta-tuning-for-few#ran","syntology_url":"https://syntology.ai/paper/2403.08477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.08477"}},"official":{"repos":["szc12153/sparse_meta_tuning"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/moai-mixture-of-all-intelligence-for-large","slug":"moai-mixture-of-all-intelligence-for-large","title":"MoAI: Mixture of All Intelligence for Large Language and Vision Models","date":"2024-03-12","arxiv_id":"2403.07508","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/moai-mixture-of-all-intelligence-for-large#ran","syntology_url":"https://syntology.ai/paper/2403.07508","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07508"}},"official":{"repos":["ByungKwanLee/MoAI"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/harder-tasks-need-more-experts-dynamic","slug":"harder-tasks-need-more-experts-dynamic","title":"Harder Tasks Need More Experts: Dynamic Routing in MoE Models","date":"2024-03-12","arxiv_id":"2403.07652","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/harder-tasks-need-more-experts-dynamic#ran","syntology_url":"https://syntology.ai/paper/2403.07652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07652"}},"official":{"repos":["zhenweian/dynamic_moe"],"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":["official","unlocated"]}}},{"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":7,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":4,"phrase":"9 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; 2 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":5,"n_unverified":0,"ran_from_kinds":["community","found_in_text","official"]}}},{"url":"/paper/testam-a-time-enhanced-spatio-temporal","slug":"testam-a-time-enhanced-spatio-temporal","title":"TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts","date":"2024-03-05","arxiv_id":"2403.02600","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/testam-a-time-enhanced-spatio-temporal#ran","syntology_url":"https://syntology.ai/paper/2403.02600","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.02600"}},"official":{"repos":["hyunwookl/testam"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-efficiency-in-sparse-models-with","slug":"enhancing-efficiency-in-sparse-models-with","title":"XMoE: Sparse Models with Fine-grained and Adaptive Expert Selection","date":"2024-02-27","arxiv_id":"2403.18926","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"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) · 0 unverified","sample_list":"/paper/enhancing-efficiency-in-sparse-models-with#ran","syntology_url":"https://syntology.ai/paper/2403.18926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18926"}},"official":{"repos":["ysngki/xmoe"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hypermoe-towards-better-mixture-of-experts","slug":"hypermoe-towards-better-mixture-of-experts","title":"HyperMoE: Towards Better Mixture of Experts via Transferring Among Experts","date":"2024-02-20","arxiv_id":"2402.12656","repositories_listed":1,"syntology":{"n":18,"n_ran":14,"n_constructed":2,"n_ran_checked":13,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":7,"phrase":"14 ran (of which 2 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/hypermoe-towards-better-mixture-of-experts#ran","syntology_url":"https://syntology.ai/paper/2402.12656","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12656"}},"official":{"repos":["bumble666/hypermoe_early_version"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/scaling-physics-informed-hard-constraints","slug":"scaling-physics-informed-hard-constraints","title":"Scaling physics-informed hard constraints with mixture-of-experts","date":"2024-02-20","arxiv_id":"2402.13412","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/scaling-physics-informed-hard-constraints#ran","syntology_url":"https://syntology.ai/paper/2402.13412","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13412"}},"official":{"repos":["ask-berkeley/physics-nns-hard-constraints"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"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":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"4 ran (of which 1 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","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/higher-layers-need-more-lora-experts","slug":"higher-layers-need-more-lora-experts","title":"Higher Layers Need More LoRA Experts","date":"2024-02-13","arxiv_id":"2402.08562","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"6 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/higher-layers-need-more-lora-experts#ran","syntology_url":"https://syntology.ai/paper/2402.08562","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.08562"}},"official":{"repos":["gcyzsl/mola"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/scaling-laws-for-fine-grained-mixture-of","slug":"scaling-laws-for-fine-grained-mixture-of","title":"Scaling Laws for Fine-Grained Mixture of Experts","date":"2024-02-12","arxiv_id":"2402.07871","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":1,"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; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/scaling-laws-for-fine-grained-mixture-of#ran","syntology_url":"https://syntology.ai/paper/2402.07871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07871"}},"official":{"repos":["llm-random/llm-random"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/interpretcc-conditional-computation-for","slug":"interpretcc-conditional-computation-for","title":"Intrinsic User-Centric Interpretability through Global Mixture of Experts","date":"2024-02-05","arxiv_id":"2402.02933","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/interpretcc-conditional-computation-for#ran","syntology_url":"https://syntology.ai/paper/2402.02933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02933"}},"official":{"repos":["epfl-ml4ed/interpretcc"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/fusemoe-mixture-of-experts-transformers-for","slug":"fusemoe-mixture-of-experts-transformers-for","title":"FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion","date":"2024-02-05","arxiv_id":"2402.03226","repositories_listed":0,"syntology":{"n":4,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/fusemoe-mixture-of-experts-transformers-for#ran","syntology_url":"https://syntology.ai/paper/2402.03226","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03226"}},"official":null}},{"url":"/paper/merging-multi-task-models-via-weight","slug":"merging-multi-task-models-via-weight","title":"Merging Multi-Task Models via Weight-Ensembling Mixture of Experts","date":"2024-02-01","arxiv_id":"2402.00433","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/merging-multi-task-models-via-weight#ran","syntology_url":"https://syntology.ai/paper/2402.00433","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.00433"}},"official":{"repos":["tanganke/weight-ensembling_moe"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/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":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 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":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"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/frequency-adaptive-pan-sharpening-with","slug":"frequency-adaptive-pan-sharpening-with","title":"Frequency-Adaptive Pan-Sharpening with Mixture of Experts","date":"2024-01-04","arxiv_id":"2401.02151","repositories_listed":1,"syntology":{"n":17,"n_ran":12,"n_constructed":10,"n_ran_checked":11,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":17,"phrase":"12 ran (of which 10 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/frequency-adaptive-pan-sharpening-with#ran","syntology_url":"https://syntology.ai/paper/2401.02151","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.02151"}},"official":{"repos":["alexhe101/fame-net"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":10,"n_ran_no_instrument_failure":11,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/fast-inference-of-mixture-of-experts-language","slug":"fast-inference-of-mixture-of-experts-language","title":"Fast Inference of Mixture-of-Experts Language Models with Offloading","date":"2023-12-28","arxiv_id":"2312.17238","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fast-inference-of-mixture-of-experts-language#ran","syntology_url":"https://syntology.ai/paper/2312.17238","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.17238"}},"official":{"repos":["dvmazur/mixtral-offloading"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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":17,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":17,"n_pointer_only":3,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 5 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/finemogen-fine-grained-spatio-temporal-motion-1","slug":"finemogen-fine-grained-spatio-temporal-motion-1","title":"FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing","date":"2023-12-22","arxiv_id":"2312.15004","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"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) · 0 unverified","sample_list":"/paper/finemogen-fine-grained-spatio-temporal-motion-1#ran","syntology_url":"https://syntology.ai/paper/2312.15004","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15004"}},"official":{"repos":["mingyuan-zhang/FineMoGen"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/when-parameter-efficient-tuning-meets-general","slug":"when-parameter-efficient-tuning-meets-general","title":"When Parameter-efficient Tuning Meets General-purpose Vision-language Models","date":"2023-12-16","arxiv_id":"2312.12458","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/when-parameter-efficient-tuning-meets-general#ran","syntology_url":"https://syntology.ai/paper/2312.12458","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12458"}},"official":{"repos":["melonking32/petal"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/the-art-of-balancing-revolutionizing-mixture","slug":"the-art-of-balancing-revolutionizing-mixture","title":"LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin","date":"2023-12-15","arxiv_id":"2312.09979","repositories_listed":1,"syntology":{"n":14,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":14,"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) · 5 unverified","sample_list":"/paper/the-art-of-balancing-revolutionizing-mixture#ran","syntology_url":"https://syntology.ai/paper/2312.09979","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.09979"}},"official":{"repos":["ablustrund/loramoe"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"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":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 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":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/adaptir-parameter-efficient-multi-task","slug":"adaptir-parameter-efficient-multi-task","title":"Parameter Efficient Adaptation for Image Restoration with Heterogeneous Mixture-of-Experts","date":"2023-12-12","arxiv_id":"2312.08881","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":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) · 0 unverified","sample_list":"/paper/adaptir-parameter-efficient-multi-task#ran","syntology_url":"https://syntology.ai/paper/2312.08881","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.08881"}},"official":{"repos":["csguoh/adaptir"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/graphmetro-mitigating-complex-distribution","slug":"graphmetro-mitigating-complex-distribution","title":"GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned Experts","date":"2023-12-07","arxiv_id":"2312.04693","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":9,"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) · 3 unverified","sample_list":"/paper/graphmetro-mitigating-complex-distribution#ran","syntology_url":"https://syntology.ai/paper/2312.04693","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04693"}},"official":{"repos":["wuyxin/graphmetro"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-task-reinforcement-learning-with-1","slug":"multi-task-reinforcement-learning-with-1","title":"Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts","date":"2023-11-19","arxiv_id":"2311.11385","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-task-reinforcement-learning-with-1#ran","syntology_url":"https://syntology.ai/paper/2311.11385","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.11385"}},"official":{"repos":["AhmedMagdyHendawy/MOORE"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/qmoe-practical-sub-1-bit-compression-of","slug":"qmoe-practical-sub-1-bit-compression-of","title":"QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models","date":"2023-10-25","arxiv_id":"2310.16795","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/qmoe-practical-sub-1-bit-compression-of#ran","syntology_url":"https://syntology.ai/paper/2310.16795","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.16795"}},"official":{"repos":["ist-daslab/qmoe"],"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":["official"]}}},{"url":"/paper/image-super-resolution-via-latent-diffusion-a","slug":"image-super-resolution-via-latent-diffusion-a","title":"Image Super-resolution Via Latent Diffusion: A Sampling-space Mixture Of Experts And Frequency-augmented Decoder Approach","date":"2023-10-18","arxiv_id":"2310.12004","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"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/image-super-resolution-via-latent-diffusion-a#ran","syntology_url":"https://syntology.ai/paper/2310.12004","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.12004"}},"official":{"repos":["tencent-ailab/frequency_aug_vae_moesr"],"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":["official","unlocated"]}}},{"url":"/paper/merging-experts-into-one-improving","slug":"merging-experts-into-one-improving","title":"Merging Experts into One: Improving Computational Efficiency of Mixture of Experts","date":"2023-10-15","arxiv_id":"2310.09832","repositories_listed":1,"syntology":{"n":21,"n_ran":18,"n_constructed":2,"n_ran_checked":15,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":14,"n_pointer_only":21,"phrase":"18 ran (of which 2 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 0 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/merging-experts-into-one-improving#ran","syntology_url":"https://syntology.ai/paper/2310.09832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.09832"}},"official":{"repos":["shwai-he/meo"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":2,"n_ran_no_instrument_failure":15,"n_unverified":3,"ran_from_kinds":["official"]}}},{"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":14,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":13,"n_pointer_only":2,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 1 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":14,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/ft-shield-a-watermark-against-unauthorized","slug":"ft-shield-a-watermark-against-unauthorized","title":"FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Models","date":"2023-10-03","arxiv_id":"2310.02401","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"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; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ft-shield-a-watermark-against-unauthorized#ran","syntology_url":"https://syntology.ai/paper/2310.02401","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.02401"}},"official":null}},{"url":"/paper/merge-then-compress-demystify-efficient-smoe","slug":"merge-then-compress-demystify-efficient-smoe","title":"Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy","date":"2023-10-02","arxiv_id":"2310.01334","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":1,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":4,"n_pointer_only":0,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 2 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/merge-then-compress-demystify-efficient-smoe#ran","syntology_url":"https://syntology.ai/paper/2310.01334","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01334"}},"official":{"repos":["unites-lab/mc-smoe"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mocae-mixture-of-calibrated-experts","slug":"mocae-mixture-of-calibrated-experts","title":"MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection","date":"2023-09-26","arxiv_id":"2309.14976","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/mocae-mixture-of-calibrated-experts#ran","syntology_url":"https://syntology.ai/paper/2309.14976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.14976"}},"official":{"repos":["fiveai/MoCaE"],"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/pushing-mixture-of-experts-to-the-limit","slug":"pushing-mixture-of-experts-to-the-limit","title":"Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning","date":"2023-09-11","arxiv_id":"2309.05444","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"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 0 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","sample_list":"/paper/pushing-mixture-of-experts-to-the-limit#ran","syntology_url":"https://syntology.ai/paper/2309.05444","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.05444"}},"official":{"repos":["for-ai/parameter-efficient-moe"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/exploring-sparse-moe-in-gans-for-text","slug":"exploring-sparse-moe-in-gans-for-text","title":"Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis","date":"2023-09-07","arxiv_id":"2309.03904","repositories_listed":1,"syntology":{"n":24,"n_ran":19,"n_constructed":0,"n_ran_checked":18,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":18,"n_pointer_only":24,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 0 violated, 18 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/exploring-sparse-moe-in-gans-for-text#ran","syntology_url":"https://syntology.ai/paper/2309.03904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.03904"}},"official":{"repos":["zhujiapeng/aurora"],"state":"official (archive's flag): 19 ran","n_ran":19,"n_constructed":0,"n_ran_no_instrument_failure":18,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/motion-in-betweening-with-phase-manifolds","slug":"motion-in-betweening-with-phase-manifolds","title":"Motion In-Betweening with Phase Manifolds","date":"2023-08-24","arxiv_id":"2308.12751","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"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) · 0 unverified","sample_list":"/paper/motion-in-betweening-with-phase-manifolds#ran","syntology_url":"https://syntology.ai/paper/2308.12751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12751"}},"official":{"repos":["pauzii/phasebetweener"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/pre-gated-moe-an-algorithm-system-co-design","slug":"pre-gated-moe-an-algorithm-system-co-design","title":"Pre-gated MoE: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert Inference","date":"2023-08-23","arxiv_id":"2308.12066","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pre-gated-moe-an-algorithm-system-co-design#ran","syntology_url":"https://syntology.ai/paper/2308.12066","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12066"}},"official":{"repos":["ranggihwang/pregated_moe"],"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":["official"]}}},{"url":"/paper/enhancing-nerf-akin-to-enhancing-llms","slug":"enhancing-nerf-akin-to-enhancing-llms","title":"Enhancing NeRF akin to Enhancing LLMs: Generalizable NeRF Transformer with Mixture-of-View-Experts","date":"2023-08-22","arxiv_id":"2308.11793","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":4,"n_instrument":7,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":12,"phrase":"11 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; 7 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/enhancing-nerf-akin-to-enhancing-llms#ran","syntology_url":"https://syntology.ai/paper/2308.11793","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11793"}},"official":{"repos":["vita-group/gnt-move"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/beyond-sharing-conflict-aware-multivariate","slug":"beyond-sharing-conflict-aware-multivariate","title":"Beyond Sharing: Conflict-Aware Multivariate Time Series Anomaly Detection","date":"2023-08-17","arxiv_id":"2308.08915","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/beyond-sharing-conflict-aware-multivariate#ran","syntology_url":"https://syntology.ai/paper/2308.08915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.08915"}},"official":{"repos":["dawnvince/mts_cad"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/taskexpert-dynamically-assembling-multi-task","slug":"taskexpert-dynamically-assembling-multi-task","title":"TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts","date":"2023-07-28","arxiv_id":"2307.15324","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":1,"n_ran_checked":1,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 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; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/taskexpert-dynamically-assembling-multi-task#ran","syntology_url":"https://syntology.ai/paper/2307.15324","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.15324"}},"official":{"repos":["prismformore/multi-task-transformer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/ntk-approximating-mlp-fusion-for-efficient","slug":"ntk-approximating-mlp-fusion-for-efficient","title":"MLP Fusion: Towards Efficient Fine-tuning of Dense and Mixture-of-Experts Language Models","date":"2023-07-18","arxiv_id":"2307.08941","repositories_listed":1,"syntology":{"n":14,"n_ran":10,"n_constructed":5,"n_ran_checked":9,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":14,"phrase":"10 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/ntk-approximating-mlp-fusion-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2307.08941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.08941"}},"official":{"repos":["weitianxin/mlp_fusion"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":5,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/shiftaddvit-mixture-of-multiplication-1","slug":"shiftaddvit-mixture-of-multiplication-1","title":"ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer","date":"2023-06-10","arxiv_id":"2306.06446","repositories_listed":1,"syntology":{"n":20,"n_ran":14,"n_constructed":4,"n_ran_checked":12,"n_instrument":2,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":2,"phrase":"14 ran (of which 4 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/shiftaddvit-mixture-of-multiplication-1#ran","syntology_url":"https://syntology.ai/paper/2306.06446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.06446"}},"official":{"repos":["gatech-eic/shiftaddvit"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":4,"n_ran_no_instrument_failure":12,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/moduleformer-learning-modular-large-language","slug":"moduleformer-learning-modular-large-language","title":"ModuleFormer: Modularity Emerges from Mixture-of-Experts","date":"2023-06-07","arxiv_id":"2306.04640","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/moduleformer-learning-modular-large-language#ran","syntology_url":"https://syntology.ai/paper/2306.04640","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.04640"}},"official":{"repos":["ibm/moduleformer"],"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/emergent-modularity-in-pre-trained","slug":"emergent-modularity-in-pre-trained","title":"Emergent Modularity in Pre-trained Transformers","date":"2023-05-28","arxiv_id":"2305.18390","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/emergent-modularity-in-pre-trained#ran","syntology_url":"https://syntology.ai/paper/2305.18390","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18390"}},"official":{"repos":["thunlp/modularity-analysis"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/condensing-multilingual-knowledge-with","slug":"condensing-multilingual-knowledge-with","title":"Condensing Multilingual Knowledge with Lightweight Language-Specific Modules","date":"2023-05-23","arxiv_id":"2305.13993","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 2 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) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/condensing-multilingual-knowledge-with#ran","syntology_url":"https://syntology.ai/paper/2305.13993","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13993"}},"official":{"repos":["fe1ixxu/lms_fd"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lifting-the-curse-of-capacity-gap-in","slug":"lifting-the-curse-of-capacity-gap-in","title":"Lifting the Curse of Capacity Gap in Distilling Language Models","date":"2023-05-20","arxiv_id":"2305.12129","repositories_listed":1,"syntology":{"n":13,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":6,"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) · 6 unverified","sample_list":"/paper/lifting-the-curse-of-capacity-gap-in#ran","syntology_url":"https://syntology.ai/paper/2305.12129","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.12129"}},"official":{"repos":["genezc/minimoe"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official"]}}},{"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/learning-a-sparse-transformer-network-for","slug":"learning-a-sparse-transformer-network-for","title":"Learning A Sparse Transformer Network for Effective Image Deraining","date":"2023-03-21","arxiv_id":"2303.11950","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":8,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":11,"phrase":"8 ran (of which 8 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) · 3 unverified; every one of the 8 samples that ran constructed an object rather than computing a result","sample_list":"/paper/learning-a-sparse-transformer-network-for#ran","syntology_url":"https://syntology.ai/paper/2303.11950","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.11950"}},"official":{"repos":["cschenxiang/drsformer"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":8,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/sparse-moe-as-the-new-dropout-scaling-dense","slug":"sparse-moe-as-the-new-dropout-scaling-dense","title":"Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers","date":"2023-03-02","arxiv_id":"2303.01610","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sparse-moe-as-the-new-dropout-scaling-dense#ran","syntology_url":"https://syntology.ai/paper/2303.01610","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.01610"}},"official":{"repos":["vita-group/random-moe-as-dropout"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sparse-upcycling-training-mixture-of-experts","slug":"sparse-upcycling-training-mixture-of-experts","title":"Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints","date":"2022-12-09","arxiv_id":"2212.05055","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sparse-upcycling-training-mixture-of-experts#ran","syntology_url":"https://syntology.ai/paper/2212.05055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.05055"}},"official":{"repos":["google-research/vmoe"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/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/spatial-mixture-of-experts","slug":"spatial-mixture-of-experts","title":"Spatial Mixture-of-Experts","date":"2022-11-24","arxiv_id":"2211.13491","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":2,"n_ran_checked":2,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/spatial-mixture-of-experts#ran","syntology_url":"https://syntology.ai/paper/2211.13491","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.13491"}},"official":{"repos":["spcl/smoe"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/m-3-vit-mixture-of-experts-vision-transformer","slug":"m-3-vit-mixture-of-experts-vision-transformer","title":"M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design","date":"2022-10-26","arxiv_id":"2210.14793","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/m-3-vit-mixture-of-experts-vision-transformer#ran","syntology_url":"https://syntology.ai/paper/2210.14793","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.14793"}},"official":{"repos":["vita-group/m3vit"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/automoe-neural-architecture-search-for","slug":"automoe-neural-architecture-search-for","title":"AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation","date":"2022-10-14","arxiv_id":"2210.07535","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":2,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"5 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/automoe-neural-architecture-search-for#ran","syntology_url":"https://syntology.ai/paper/2210.07535","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07535"}},"official":{"repos":["microsoft/automoe"],"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":["official","unlocated"]}}},{"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":10,"n_instrument":3,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":4,"phrase":"13 ran (of which 2 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 3 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":2,"n_unverified":0,"ran_from_kinds":["found_in_text","listed","official"]}}},{"url":"/paper/meta-dmoe-adapting-to-domain-shift-by-meta","slug":"meta-dmoe-adapting-to-domain-shift-by-meta","title":"Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Experts","date":"2022-10-08","arxiv_id":"2210.03885","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/meta-dmoe-adapting-to-domain-shift-by-meta#ran","syntology_url":"https://syntology.ai/paper/2210.03885","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03885"}},"official":{"repos":["n3il666/meta-dmoe"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/mask-and-reason-pre-training-knowledge-graph","slug":"mask-and-reason-pre-training-knowledge-graph","title":"Mask and Reason: Pre-Training Knowledge Graph Transformers for Complex Logical Queries","date":"2022-08-16","arxiv_id":"2208.07638","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mask-and-reason-pre-training-knowledge-graph#ran","syntology_url":"https://syntology.ai/paper/2208.07638","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.07638"}},"official":{"repos":["thudm/kgtransformer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["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/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/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":7,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":14,"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) · 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":7,"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":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":3,"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) · 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":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/se-moe-a-scalable-and-efficient-mixture-of","slug":"se-moe-a-scalable-and-efficient-mixture-of","title":"MoESys: A Distributed and Efficient Mixture-of-Experts Training and Inference System for Internet Services","date":"2022-05-20","arxiv_id":"2205.10034","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":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) · 0 unverified","sample_list":"/paper/se-moe-a-scalable-and-efficient-mixture-of#ran","syntology_url":"https://syntology.ai/paper/2205.10034","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.10034"}},"official":{"repos":["PaddlePaddle/FleetX"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/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/table-based-fact-verification-with-self-1","slug":"table-based-fact-verification-with-self-1","title":"Table-based Fact Verification with Self-adaptive Mixture of Experts","date":"2022-04-19","arxiv_id":"2204.08753","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"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) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/table-based-fact-verification-with-self-1#ran","syntology_url":"https://syntology.ai/paper/2204.08753","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.08753"}},"official":{"repos":["thumlp/samoe"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/stablemoe-stable-routing-strategy-for-mixture-1","slug":"stablemoe-stable-routing-strategy-for-mixture-1","title":"StableMoE: Stable Routing Strategy for Mixture of Experts","date":"2022-04-18","arxiv_id":"2204.08396","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":3,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/stablemoe-stable-routing-strategy-for-mixture-1#ran","syntology_url":"https://syntology.ai/paper/2204.08396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.08396"}},"official":{"repos":["hunter-ddm/stablemoe"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/3m-multi-loss-multi-path-and-multi-level","slug":"3m-multi-loss-multi-path-and-multi-level","title":"3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition","date":"2022-04-07","arxiv_id":"2204.03178","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":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) · 0 unverified","sample_list":"/paper/3m-multi-loss-multi-path-and-multi-level#ran","syntology_url":"https://syntology.ai/paper/2204.03178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03178"}},"official":{"repos":["tencent-ailab/3m-asr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-and-degradation-adaptive-network","slug":"efficient-and-degradation-adaptive-network","title":"Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution","date":"2022-03-27","arxiv_id":"2203.14216","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/efficient-and-degradation-adaptive-network#ran","syntology_url":"https://syntology.ai/paper/2203.14216","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.14216"}},"official":{"repos":["csjliang/dasr"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/summareranker-a-multi-task-mixture-of-experts-1","slug":"summareranker-a-multi-task-mixture-of-experts-1","title":"SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive Summarization","date":"2022-03-13","arxiv_id":"2203.06569","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":2,"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 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/summareranker-a-multi-task-mixture-of-experts-1#ran","syntology_url":"https://syntology.ai/paper/2203.06569","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.06569"}},"official":{"repos":["ntunlp/summareranker"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"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/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/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":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/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":1,"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/taming-sparsely-activated-transformer-with","slug":"taming-sparsely-activated-transformer-with","title":"Taming Sparsely Activated Transformer with Stochastic Experts","date":"2021-10-08","arxiv_id":"2110.04260","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/taming-sparsely-activated-transformer-with#ran","syntology_url":"https://syntology.ai/paper/2110.04260","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.04260"}},"official":{"repos":["microsoft/stochastic-mixture-of-experts"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hydrasum-disentangling-stylistic-features-in-1","slug":"hydrasum-disentangling-stylistic-features-in-1","title":"HydraSum: Disentangling Stylistic Features in Text Summarization using Multi-Decoder Models","date":"2021-10-08","arxiv_id":"2110.04400","repositories_listed":1,"syntology":{"n":9,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":6,"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) · 6 unverified","sample_list":"/paper/hydrasum-disentangling-stylistic-features-in-1#ran","syntology_url":"https://syntology.ai/paper/2110.04400","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.04400"}},"official":{"repos":["salesforce/hydra-sum"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/sparse-moes-meet-efficient-ensembles","slug":"sparse-moes-meet-efficient-ensembles","title":"Sparse MoEs meet Efficient Ensembles","date":"2021-10-07","arxiv_id":"2110.03360","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":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/sparse-moes-meet-efficient-ensembles#ran","syntology_url":"https://syntology.ai/paper/2110.03360","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.03360"}},"official":{"repos":["google-research/vmoe"],"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/universal-simultaneous-machine-translation","slug":"universal-simultaneous-machine-translation","title":"Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policy","date":"2021-09-11","arxiv_id":"2109.05238","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"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) · 1 unverified","sample_list":"/paper/universal-simultaneous-machine-translation#ran","syntology_url":"https://syntology.ai/paper/2109.05238","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.05238"}},"official":{"repos":["ictnlp/moe-waitk"],"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":["official"]}}},{"url":"/paper/lifelong-mixture-of-variational-autoencoders","slug":"lifelong-mixture-of-variational-autoencoders","title":"Lifelong Mixture of Variational Autoencoders","date":"2021-07-09","arxiv_id":"2107.04694","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lifelong-mixture-of-variational-autoencoders#ran","syntology_url":"https://syntology.ai/paper/2107.04694","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.04694"}},"official":{"repos":["dtuzi123/LifelongMixtureVAEs"],"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":["official"]}}},{"url":"/paper/scaling-vision-with-sparse-mixture-of-experts","slug":"scaling-vision-with-sparse-mixture-of-experts","title":"Scaling Vision with Sparse Mixture of Experts","date":"2021-06-10","arxiv_id":"2106.05974","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scaling-vision-with-sparse-mixture-of-experts#ran","syntology_url":"https://syntology.ai/paper/2106.05974","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05974"}},"official":{"repos":["google-research/vmoe"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/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"]}}}],"record_sha256":"b3e9fa8a6e0000233b5994cee335358c41b76b9b21462013e229f3cf3107d1c0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}