{"id":"https://openalex.org/W4417447656","doi":"https://doi.org/10.18653/v1/2026.acl-demo.15","title":"MixtureKit: A General Framework for Composing, Training, and Visualizing Mixture-of-Experts Models","display_name":"MixtureKit: A General Framework for Composing, Training, and Visualizing Mixture-of-Experts Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4417447656","doi":"https://doi.org/10.18653/v1/2026.acl-demo.15"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-demo.15","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-demo.15","pdf_url":"https://aclanthology.org/2026.acl-demo.15.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-demo.15.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058423585","display_name":"Ahmad Chamma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmad Chamma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118628340","display_name":"Omar El Herraoui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Omar El Herraoui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038162261","display_name":"Guokan Shang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guokan Shang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03747425,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"148","last_page":"156"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.3433000147342682,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.3433000147342682,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.08420000225305557,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.06930000334978104,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.654699981212616},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5925999879837036},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5209000110626221},{"id":"https://openalex.org/keywords/data-visualization","display_name":"Data visualization","score":0.4544999897480011},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4268999993801117},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.40470001101493835},{"id":"https://openalex.org/keywords/router","display_name":"Router","score":0.3959999978542328},{"id":"https://openalex.org/keywords/inference-engine","display_name":"Inference engine","score":0.3564000129699707},{"id":"https://openalex.org/keywords/creative-visualization","display_name":"Creative visualization","score":0.3472000062465668}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.817300021648407},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.654699981212616},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5925999879837036},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5209000110626221},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.4544999897480011},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43630000948905945},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4268999993801117},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.40470001101493835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3991999924182892},{"id":"https://openalex.org/C2775896111","wikidata":"https://www.wikidata.org/wiki/Q642560","display_name":"Router","level":2,"score":0.3959999978542328},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.3564000129699707},{"id":"https://openalex.org/C14669888","wikidata":"https://www.wikidata.org/wiki/Q4014850","display_name":"Creative visualization","level":3,"score":0.3472000062465668},{"id":"https://openalex.org/C2776240099","wikidata":"https://www.wikidata.org/wiki/Q327018","display_name":"Interrogation","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33709999918937683},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.3303000032901764},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.329800009727478},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.32760000228881836},{"id":"https://openalex.org/C185578843","wikidata":"https://www.wikidata.org/wiki/Q10609775","display_name":"Information visualization","level":3,"score":0.30399999022483826},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C15845906","wikidata":"https://www.wikidata.org/wiki/Q1172338","display_name":"Data exchange","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C48105269","wikidata":"https://www.wikidata.org/wiki/Q1141160","display_name":"Header","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.26409998536109924},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C184896649","wikidata":"https://www.wikidata.org/wiki/Q290066","display_name":"Routing table","level":4,"score":0.25870001316070557},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-demo.15","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-demo.15","pdf_url":"https://aclanthology.org/2026.acl-demo.15.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.12121","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.12121","pdf_url":"https://arxiv.org/pdf/2512.12121","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.12121","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.12121","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-demo.15","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-demo.15","pdf_url":"https://aclanthology.org/2026.acl-demo.15.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417447656.pdf","grobid_xml":"https://content.openalex.org/works/W4417447656.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1],"MixtureKit,":[2],"a":[3,29,67,84,96],"modular":[4],"opensource":[5],"framework":[6],"for":[7,46,62,89],"constructing,":[8],"training,":[9],"and":[10,50,57,78,82,106],"analyzing":[11],"Mixture-of-Experts":[12],"(MoE)":[13],"models":[14,117],"from":[15],"arbitrary":[16],"pre-trained":[17],"or":[18,91],"fine-tuned":[19],"checkpoints.MixtureKit":[20],"supports":[21],"three":[22],"complementary":[23],"strategies:":[24],"(i)":[25],"Traditional":[26],"MoE,":[27],"using":[28],"single":[30,68],"router":[31],"per":[32],"transformer":[33],"block":[34],"to":[35,99],"select":[36],"experts;":[37],"(ii)":[38],"BTX":[39,116],"(Branch-Train-Mix),":[40],"adding":[41],"routers":[42],"at":[43],"user-specified":[44],"sub-layers":[45],"fine-grained":[47],"token":[48,101],"routing;":[49],"(iii)":[51],"BTS":[52],"(Branch-Train-Stitch),":[53],"preserving":[54],"experts":[55],"intact":[56],"introducing":[58],"lightweight":[59],"stitch":[60],"layers":[61],"controlled":[63],"hub-expert":[64],"information":[65],"exchange.Given":[66],"configuration":[69],"dictionary,":[70],"MixtureKit":[71,120],"automatically":[72],"modifies":[73],"model":[74],"configuration,":[75],"patches":[76],"decoder":[77],"causal":[79],"LM":[80],"classes,":[81],"exports":[83],"unified":[85],"transformerscompatible":[86],"checkpoint":[87],"ready":[88],"inference":[90],"further":[92],"fine-tuning.We":[93],"also":[94],"provide":[95],"visualization":[97],"interface":[98],"inspect":[100],"routing,":[102],"expert":[103],"weight":[104],"distributions,":[105],"layer-wise":[107],"contributions.Experiments":[108],"on":[109],"multilingual":[110],"codeswitched":[111],"(Arabic-Latin)":[112],"data":[113],"show":[114],"that":[115],"built":[118],"with":[119],"can":[121],"outperform":[122],"dense":[123],"baselines":[124],"across":[125],"multiple":[126],"benchmarks.The":[127],"library":[128],"is":[129],"accessible":[130],"at:":[131],"https://github.":[132],"com/MBZUAI-Paris/MixtureKit.":[133]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-12-17T00:00:00"}