{"id":"https://openalex.org/W7154589338","doi":"https://doi.org/10.48550/arxiv.2604.13737","title":"TokenFormer: Unify the Multi-Field and Sequential Recommendation Worlds","display_name":"TokenFormer: Unify the Multi-Field and Sequential Recommendation Worlds","publication_year":2026,"publication_date":"2026-04-15","ids":{"openalex":"https://openalex.org/W7154589338","doi":"https://doi.org/10.48550/arxiv.2604.13737"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.13737","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.13737","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":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.2604.13737","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101652171","display_name":"Yifeng Zhou","orcid":"https://orcid.org/0000-0002-1095-3580"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Yifeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102620266","display_name":"Yuehong Hu","orcid":"https://orcid.org/0009-0006-6833-4228"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Yuehong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100584528","display_name":"Zhixiang Feng","orcid":"https://orcid.org/0009-0005-1519-0227"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Zhixiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133810150","display_name":"Junwei Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Junwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133789624","display_name":"Kaihui Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Kaihui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133802686","display_name":"Hanyong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Hanyong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036962057","display_name":"Shangyu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Shangyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133750252","display_name":"Shudong Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Shudong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058004418","display_name":"Zhangbin Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Zhangbin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133155236","display_name":"Chengguo Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Chengguo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056695193","display_name":"Haijie Gu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gu, Haijie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133730183","display_name":"Jie Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Jie","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":0.9531999826431274,"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":0.9531999826431274,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.0038999998942017555,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.003800000064074993,"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/categorical-variable","display_name":"Categorical variable","score":0.6901000142097473},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6693000197410583},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5666000247001648},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5324000120162964},{"id":"https://openalex.org/keywords/multiplicative-function","display_name":"Multiplicative function","score":0.4909999966621399},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.4848000109195709},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4729999899864197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7559000253677368},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6901000142097473},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6693000197410583},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5666000247001648},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5324000120162964},{"id":"https://openalex.org/C42747912","wikidata":"https://www.wikidata.org/wiki/Q1048447","display_name":"Multiplicative function","level":2,"score":0.4909999966621399},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.4848000109195709},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4729999899864197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.461899995803833},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.43880000710487366},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3910999894142151},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.3659999966621399},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.36070001125335693},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.313400000333786},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2939000129699707},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2904999852180481},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.2847000062465668},{"id":"https://openalex.org/C2777742833","wikidata":"https://www.wikidata.org/wiki/Q1964083","display_name":"Reciprocal","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.13737","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.13737","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.13737","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.13737","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7406613826751709,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recommender":[0],"systems":[1],"have":[2],"historically":[3],"developed":[4],"along":[5],"two":[6,50],"largely":[7],"independent":[8],"paradigms:":[9],"feature":[10],"interaction":[11,30,66],"models":[12,22],"for":[13,23],"modeling":[14],"correlations":[15],"among":[16],"multi-field":[17],"categorical":[18],"features,":[19],"and":[20,113,144,161],"sequential":[21],"capturing":[24],"user":[25],"behavior":[26],"dynamics":[27],"from":[28],"historical":[29],"sequences.":[31],"Although":[32],"recent":[33],"trends":[34],"attempt":[35],"to":[36,54,74,135],"bridge":[37],"these":[38,49],"paradigms":[39],"within":[40],"shared":[41],"backbones,":[42],"we":[43,86,98,122],"empirically":[44],"reveal":[45],"that":[46,129,155],"naive":[47],"unifying":[48],"branches":[51],"may":[52],"lead":[53],"a":[55,89,100,124],"failure":[56],"mode":[57],"of":[58,78],"Sequential":[59],"Collapse":[60],"Propagation":[61],"(SCP).":[62],"That":[63],"is,":[64],"the":[65,75,79,94,110,118,136],"with":[67,93],"those":[68],"dimensionally":[69],"ill":[70],"non-sequence":[71],"fields":[72],"leads":[73],"dimensional":[76,159],"collapse":[77],"sequence":[80],"features.":[81],"To":[82],"overcome":[83],"this":[84],"challenge,":[85],"propose":[87],"TokenFormer,":[88],"unified":[90,165],"recommendation":[91],"architecture":[92],"following":[95],"innovations.":[96],"First,":[97],"introduce":[99,123],"Bottom-Full-Top-Sliding":[101],"(BFTS)":[102],"attention":[103,116],"scheme,":[104],"which":[105],"applies":[106,130],"full":[107],"self-attention":[108],"in":[109,117],"lower":[111],"layers":[112],"shrinking-window":[114],"sliding":[115],"upper":[119],"layers.":[120],"Second,":[121],"Non-Linear":[125],"Interaction":[126],"Representation":[127],"(NLIR)":[128],"one-sided":[131],"non-linear":[132],"multiplicative":[133],"transformations":[134],"hidden":[137],"states.":[138],"Extensive":[139],"experiments":[140],"on":[141],"public":[142],"benchmarks":[143],"Tencent's":[145],"advertising":[146],"platform":[147],"demonstrate":[148],"state-of-the-art":[149],"performance,":[150],"while":[151],"detailed":[152],"analysis":[153],"confirm":[154],"TokenFormer":[156],"significantly":[157],"improves":[158],"robustness":[160],"representation":[162],"discriminability":[163],"under":[164],"modeling.":[166]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-17T00:00:00"}