{"id":"https://openalex.org/W4415795206","doi":"https://doi.org/10.52202/079017-4145","title":"B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory","display_name":"B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4415795206","doi":"https://doi.org/10.52202/079017-4145"},"language":"en","primary_location":{"id":"doi:10.52202/079017-4145","doi":"https://doi.org/10.52202/079017-4145","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-4145","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2407.06324","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036782268","display_name":"Luca Zancato","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luca Zancato","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088197840","display_name":"Arjun Seshadri","orcid":"https://orcid.org/0000-0003-1827-9831","observed_orcids":["https://orcid.org/0000-0003-1827-9831"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arjun Seshadri","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027696000","display_name":"Yonatan Dukler","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yonatan Dukler","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026595166","display_name":"Aditya Golatkar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aditya Golatkar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102939275","display_name":"Yantao Shen","orcid":"https://orcid.org/0000-0001-5413-2445","observed_orcids":["https://orcid.org/0000-0001-5413-2445","https://orcid.org/0000-0003-0733-6407"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yantao Shen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Benjamin Bowman","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benjamin Bowman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030073760","display_name":"Matthew Trager","orcid":"https://orcid.org/0009-0001-1204-6378","observed_orcids":["https://orcid.org/0009-0001-1204-6378","https://orcid.org/0000-0001-9304-6427"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matthew Trager","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065386783","display_name":"Alessandro Achille","orcid":"https://orcid.org/0000-0002-8163-8326","observed_orcids":["https://orcid.org/0000-0002-8163-8326"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alessandro Achille","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038328783","display_name":"Stefano Soatto","orcid":"https://orcid.org/0000-0003-2902-6362","observed_orcids":["https://orcid.org/0000-0003-2902-6362"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefano Soatto","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":1.2542,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.84707971,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"130433","last_page":"130462"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11236","display_name":"Control Systems and Identification","score":0.9253000020980835,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11236","display_name":"Control Systems and Identification","score":0.9253000020980835,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.028200000524520874,"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/T10820","display_name":"Fuzzy Logic and Control Systems","score":0.003000000026077032,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/foundation-models","display_name":"foundation models","score":0.9539999961853027},{"id":"https://openalex.org/keywords/eidetic-memory","display_name":"eidetic memory","score":0.8809999823570251},{"id":"https://openalex.org/keywords/fading-memory","display_name":"fading memory","score":0.9929999709129333},{"id":"https://openalex.org/keywords/state-space-realization","display_name":"state-space realization","score":0.4359999895095825}],"concepts":[{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4763999879360199},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4433000087738037},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.4408000111579895},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4185999929904938},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.414900004863739},{"id":"https://openalex.org/C81978471","wikidata":"https://www.wikidata.org/wiki/Q1196572","display_name":"Fading","level":3,"score":0.414000004529953},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.3625999987125397},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.3465999960899353},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.34630000591278076},{"id":"https://openalex.org/C2777686260","wikidata":"https://www.wikidata.org/wiki/Q144037","display_name":"Calculus (dental)","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C62799726","wikidata":"https://www.wikidata.org/wiki/Q190056","display_name":"Hilbert space","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.2651999890804291},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25870001316070557},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.2581999897956848},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/079017-4145","doi":"https://doi.org/10.52202/079017-4145","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-4145","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2407.06324","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.06324","pdf_url":"https://arxiv.org/pdf/2407.06324","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2407.06324","doi":"https://doi.org/10.48550/arxiv.2407.06324","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2407.06324","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2407.06324","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.06324","pdf_url":"https://arxiv.org/pdf/2407.06324","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415795206.pdf","grobid_xml":"https://content.openalex.org/works/W4415795206.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391591680","https://openalex.org/W4416372109","https://openalex.org/W4389326242","https://openalex.org/W7134961138","https://openalex.org/W7140164665","https://openalex.org/W4404783458","https://openalex.org/W4405626118","https://openalex.org/W4416037562","https://openalex.org/W4399657245","https://openalex.org/W4390723179"],"abstract_inverted_index":{"We":[0,94,158,196],"describe":[1,179],"a":[2,16,42,103,180,216],"family":[3],"of":[4,26,105,176,272],"architectures":[5,32,62,169],"to":[6,13,15,36,82,88,101,109,127,183,228,234,240,243,251,266],"support":[7],"transductive":[8,200],"inference":[9,201,260],"by":[10,149],"allowing":[11],"memory":[12,92,115,135,139,142,147,256],"grow":[14],"finite":[17,27,43],"but":[18,69],"a-priori":[19],"unknown":[20],"bound":[21],"while":[22,237],"making":[23],"efficient":[24],"use":[25,33],"resources":[28,35],"for":[29],"inference.":[30],"Current":[31],"such":[34,164,170,203],"represent":[37],"data":[38],"either":[39],"eidetically":[40],"over":[41,50],"span":[44,53],"(\"context\"":[45],"in":[46,194,258],"Transformers),":[47],"or":[48,58,78],"fading":[49,67,114,141,255],"an":[51,117,154],"infinite":[52],"(in":[54],"State":[55],"Space":[56],"Models,":[57],"SSMs).":[59],"Recent":[60],"hybrid":[61,168],"have":[63],"combined":[64],"eidetic":[65,91,112,134,146,253],"and":[66,113,144,167,178,191,212,231,254],"memory,":[68],"with":[70],"limitations":[71],"that":[72,130,160,187,248],"do":[73],"not":[74],"allow":[75],"the":[76,79,85,90,270,273],"designer":[77],"learning":[80],"process":[81],"seamlessly":[83,110],"modulate":[84,252],"two,":[86],"nor":[87],"extend":[89],"span.":[93],"leverage":[95],"ideas":[96],"from":[97,153],"Stochastic":[98],"Realization":[99],"Theory":[100],"develop":[102],"class":[104],"models":[106,129],"called":[107],"B'MOJO":[108,177,198,224],"combine":[111],"within":[116],"elementary":[118],"composable":[119],"module.":[120],"The":[121],"overall":[122],"architecture":[123],"can":[124,131,188],"be":[125,184,189],"used":[126],"implement":[128],"access":[132],"short-term":[133],"\"in-context,\"":[136],"permanent":[137],"structural":[138],"\"in-weights,\"":[140],"\"in-state,\"":[143],"long-term":[145],"\"in-storage\"":[148],"natively":[150],"incorporating":[151],"retrieval":[152],"asynchronously":[155],"updated":[156],"memory.":[157],"show":[159,247],"Transformers,":[161],"existing":[162,210],"SSMs":[163,211,232],"as":[165,171,204,215],"Mamba,":[166],"Jamba":[172],"are":[173],"special":[174],"cases":[175],"basic":[181],"implementation,":[182],"open":[185],"sourced,":[186],"stacked":[190],"scaled":[192],"efficiently":[193],"hardware.":[195],"test":[197,219],"on":[199,261],"tasks,":[202],"associative":[205],"recall,":[206],"where":[207,223],"it":[208],"outperforms":[209],"Hybrid":[213],"models;":[214],"baseline,":[217],"we":[218,246],"ordinary":[220],"language":[221],"modeling":[222],"achieves":[225],"perplexity":[226],"comparable":[227],"similarly-sized":[229],"Transformers":[230],"up":[233,239,265],"1.4B":[235],"parameters,":[236],"being":[238],"10%":[241],"faster":[242],"train.":[244],"Finally,":[245],"B'MOJO's":[249],"ability":[250],"results":[257],"better":[259],"longer":[262],"sequences":[263,275],"tested":[264],"32K":[267],"tokens,":[268],"four-fold":[269],"length":[271],"longest":[274],"seen":[276],"during":[277],"training.":[278]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-11-03T00:00:00"}
