{"id":"https://openalex.org/W7169853144","doi":"https://doi.org/10.48550/arxiv.2607.17017","title":"WHALE: A Scalable Unified Model for Recommendation with Wukong-HSTU Architecture","display_name":"WHALE: A Scalable Unified Model for Recommendation with Wukong-HSTU Architecture","publication_year":2026,"publication_date":"2026-07-19","ids":{"openalex":"https://openalex.org/W7169853144","doi":"https://doi.org/10.48550/arxiv.2607.17017"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.17017","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.17017","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2607.17017","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067853952","display_name":"Renqin Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai, Renqin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141303334","display_name":"Dawei Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Dawei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006561445","display_name":"Yuanjun Yao","orcid":"https://orcid.org/0009-0006-3709-0216"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Yuanjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141276523","display_name":"Zhiyong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhiyong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141234984","display_name":"Velvin Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Velvin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141285902","display_name":"Maggie Zhuang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuang, Maggie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100902783","display_name":"Y Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112049384","display_name":"Zhongnan Fang","orcid":"https://orcid.org/0000-0003-3463-7766"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang, Zhongnan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141280865","display_name":"Xuan Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Xuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141254866","display_name":"Jing Qian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian, Jing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5052597908","display_name":"R K Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Rui","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9833999872207642,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9833999872207642,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.0019000000320374966,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.0019000000320374966,"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/scalability","display_name":"Scalability","score":0.8205000162124634},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5892000198364258},{"id":"https://openalex.org/keywords/unified-model","display_name":"Unified Model","score":0.5871000289916992},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5647000074386597},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5299999713897705},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5138999819755554},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4239000082015991}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8205000162124634},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7827000021934509},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5892000198364258},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.5871000289916992},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5647000074386597},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5299999713897705},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5138999819755554},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4239000082015991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3833000063896179},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.37070000171661377},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3637000024318695},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.35679998993873596},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34380000829696655},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.2786000072956085},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26460000872612},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.17017","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.17017","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:10.48550/arxiv.2607.17017","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.17017","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.48393407464027405,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"scalability":[1],"becomes":[2],"increasingly":[3],"important":[4],"in":[5,117,185,204,224],"recommendation":[6,87,179,227],"modeling,":[7,57],"recent":[8],"architectures":[9,70],"have":[10,43],"advanced":[11],"the":[12,133],"modeling":[13,78],"of":[14,18,76,98,213,218],"two":[15,74,216],"broad":[16],"sources":[17,217],"ranking":[19],"signals":[20],"along":[21],"separate":[22],"paths:":[23,51],"non-sequence":[24,55,92],"features,":[25],"including":[26],"user,":[27],"item,":[28],"context,":[29],"and":[30,33,41,93,100,112,135,165,173],"cross":[31],"features;":[32],"sequence":[34,63,94],"features":[35,95],"from":[36,149],"user":[37,151],"behavior":[38,124],"histories.":[39,152],"Wukong":[40,52,99,107],"HSTU":[42,59,110],"emerged":[44],"as":[45],"representative":[46],"scalable":[47,85],"backbones":[48,130],"for":[49,157],"these":[50,73,215],"scales":[53,60],"high-order":[54,141],"feature-interaction":[56],"while":[58],"long":[61,150],"user-behavior":[62],"modeling.":[64],"Despite":[65],"their":[66],"complementary":[67],"strengths,":[68],"practical":[69,156,211],"that":[71,89],"combine":[72],"types":[75],"feature":[77,142],"remain":[79],"underexplored.":[80],"We":[81],"present":[82],"WHALE,":[83],"a":[84,106,195,210],"unified":[86,223],"architecture":[88],"jointly":[90],"models":[91],"on":[96],"top":[97],"HSTU.":[101],"Each":[102],"WHALE":[103,155,181,208],"layer":[104],"contains":[105],"module,":[108,111],"an":[109,113,225],"attention-based":[114],"fusion":[115],"module":[116],"which":[118],"Wukong-derived":[119],"interaction":[120],"representations":[121],"query":[122],"HSTU-derived":[123],"representations.":[125],"This":[126],"design":[127],"keeps":[128],"both":[129],"active":[131],"throughout":[132],"network":[134],"enables":[136],"progressive":[137],"Wukong-HSTU":[138],"exchange,":[139],"allowing":[140],"crosses":[143],"to":[144,170],"repeatedly":[145],"retrieve":[146],"fine-grained":[147],"evidence":[148],"To":[153],"make":[154],"industrial":[158,178,226],"deployment,":[159],"we":[160],"introduce":[161],"customized":[162],"Triton":[163],"kernels":[164],"other":[166],"model-systems":[167],"co-design":[168],"techniques":[169],"improve":[171],"training":[172],"inference":[174],"efficiency.":[175],"On":[176],"large-scale":[177],"data,":[180],"achieves":[182],"consistent":[183],"gains":[184,193],"offline":[186],"experiments.":[187],"Additionally,":[188],"it":[189],"delivers":[190],"positive":[191],"online":[192],"with":[194],"modest":[196],"serving-throughput":[197],"trade-off.":[198],"The":[199],"method":[200],"has":[201],"been":[202],"deployed":[203],"production":[205],"systems.":[206],"Overall,":[207],"provides":[209],"example":[212],"how":[214],"information":[219],"can":[220],"be":[221],"scalably":[222],"model.":[228]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-22T00:00:00"}