{"id":"https://openalex.org/W7128375942","doi":"https://doi.org/10.48550/arxiv.2602.06654","title":"Multimodal Generative Retrieval Model with Staged Pretraining for Food Delivery on Meituan","display_name":"Multimodal Generative Retrieval Model with Staged Pretraining for Food Delivery on Meituan","publication_year":2026,"publication_date":"2026-02-06","ids":{"openalex":"https://openalex.org/W7128375942","doi":"https://doi.org/10.48550/arxiv.2602.06654"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2602.06654","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.06654","pdf_url":"https://arxiv.org/pdf/2602.06654","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2602.06654","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111335733","display_name":"Boyu Chen","orcid":"https://orcid.org/0009-0002-2419-7517","observed_orcids":["https://orcid.org/0009-0002-2419-7517"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Boyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125421069","display_name":"Tai Guo","orcid":"https://orcid.org/0009-0002-1864-9468","observed_orcids":["https://orcid.org/0009-0002-1864-9468"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Tai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037775888","display_name":"Weiyu Cui","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, Weiyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125381219","display_name":"Yuqing Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yuqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125387075","display_name":"Xingxing Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xingxing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125392151","display_name":"Chuan Shi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Chuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125401219","display_name":"Cheng Yang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Cheng","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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.34689998626708984,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.34689998626708984,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.27469998598098755,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.17110000550746918,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/multimodal-retrieval","display_name":"multimodal retrieval","score":0.9430000185966492},{"id":"https://openalex.org/keywords/generative-retrieval","display_name":"generative retrieval","score":0.8090000152587891},{"id":"https://openalex.org/keywords/click-through-rate","display_name":"click-through rate","score":0.625},{"id":"https://openalex.org/keywords/meituan","display_name":"Meituan","score":0.7580000162124634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.802299976348877},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7480999827384949},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7184000015258789},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.585099995136261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5024999976158142},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.46000000834465027},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.453000009059906},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.45190000534057617},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4323999881744385},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.4189999997615814},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.40059998631477356},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3714999854564667},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3619999885559082},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3562999963760376},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.27000001072883606}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.06654","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.06654","pdf_url":"https://arxiv.org/pdf/2602.06654","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2602.06654","doi":"https://doi.org/10.48550/arxiv.2602.06654","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.06654","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:2602.06654","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.06654","pdf_url":"https://arxiv.org/pdf/2602.06654","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":null,"license_id":null,"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":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7172299291","https://openalex.org/W4221143724","https://openalex.org/W4290927857","https://openalex.org/W7124501875","https://openalex.org/W7213887503","https://openalex.org/W4415251124","https://openalex.org/W7125230074","https://openalex.org/W7167890985","https://openalex.org/W3194603040","https://openalex.org/W4412877118"],"abstract_inverted_index":{"Multimodal":[0],"retrieval":[1],"models":[2],"are":[3,64],"becoming":[4],"increasingly":[5],"important":[6],"in":[7,76,216,222,233],"scenarios":[8],"such":[9],"as":[10],"food":[11],"delivery,":[12],"where":[13],"rich":[14],"multimodal":[15,110,138],"features":[16],"can":[17,73],"meet":[18],"diverse":[19],"user":[20],"needs":[21],"and":[22,35,37,43,108,112,144,157,180,185,187,190,195,218,228],"enable":[23],"precise":[24],"retrieval.":[25],"Mainstream":[26],"approaches":[27],"typically":[28],"employ":[29],"a":[30,86,213,219],"dual-tower":[31],"architecture":[32],"between":[33,154],"queries":[34],"items,":[36],"perform":[38],"joint":[39,50],"optimization":[40,51],"of":[41,177,230],"intra-tower":[42],"inter-tower":[44],"tasks.":[45],"However,":[46],"we":[47,84,140],"observe":[48],"that":[49,135,172,209],"often":[52],"leads":[53],"to":[54,94,104,107,123,129,147,198],"certain":[55],"modalities":[56,63,72],"dominating":[57],"the":[58,77,92,117,125,132,149,152,205,226],"training":[59,69,118],"process,":[60],"while":[61],"other":[62],"neglected.":[65],"In":[66],"addition,":[67],"inconsistent":[68],"speeds":[70],"across":[71],"easily":[74],"result":[75],"one-epoch":[78,126],"problem.":[79,127],"To":[80],"address":[81],"these":[82],"challenges,":[83],"propose":[85],"staged":[87],"pretraining":[88],"strategy,":[89],"which":[90],"guides":[91],"model":[93,150],"focus":[95],"on":[96,166,182,192,204],"specialized":[97],"tasks":[98,146],"at":[99,120],"each":[100,121],"stage,":[101],"enabling":[102],"it":[103],"effectively":[105],"attend":[106],"utilize":[109,131],"features,":[111,159],"allowing":[113],"flexible":[114],"control":[115],"over":[116],"process":[119],"stage":[122],"avoid":[124],"Furthermore,":[128],"better":[130],"semantic":[133],"IDs":[134],"compress":[136],"high-dimensional":[137],"embeddings,":[139],"design":[141],"both":[142],"generative":[143],"discriminative":[145],"help":[148],"understand":[151],"associations":[153],"SIDs,":[155],"queries,":[156],"item":[158],"thereby":[160],"improving":[161],"overall":[162],"performance.":[163],"Extensive":[164],"experiments":[165],"large-scale":[167],"real-world":[168],"Meituan":[169,206],"data":[170],"demonstrate":[171],"our":[173,210,231],"method":[174,232],"achieves":[175,212],"improvements":[176],"3.80%,":[178],"2.64%,":[179],"2.17%":[181],"R@5,":[183],"R@10,":[184],"R@20,":[186],"5.10%,":[188],"4.22%,":[189],"2.09%":[191],"N@5,":[193],"N@10,":[194],"N@20":[196],"compared":[197],"mainstream":[199],"baselines.":[200],"Online":[201],"A/B":[202],"testing":[203],"platform":[207],"shows":[208],"approach":[211],"1.12%":[214],"increase":[215,221],"revenue":[217],"1.02%":[220],"click-through":[223],"rate,":[224],"validating":[225],"effectiveness":[227],"superiority":[229],"practical":[234],"applications.":[235]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-10T00:00:00"}