{"id":"https://openalex.org/W7203500331","doi":"https://doi.org/10.48550/arxiv.2608.12987","title":"Generative Universal Multimodal Retrieval with Dual-role Identifiers","display_name":"Generative Universal Multimodal Retrieval with Dual-role Identifiers","publication_year":2026,"publication_date":"2026-08-13","ids":{"openalex":"https://openalex.org/W7203500331","doi":"https://doi.org/10.48550/arxiv.2608.12987"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2608.12987","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.12987","pdf_url":"https://arxiv.org/pdf/2608.12987","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/2608.12987","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057545047","display_name":"Kaipeng Li","orcid":"https://orcid.org/0000-0002-2069-2337","observed_orcids":["https://orcid.org/0000-0002-2069-2337"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Kaipeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147147889","display_name":"Haitao Yu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Haitao","raw_affiliation_strings":["XUANCHEN ZHOU ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"XUANCHEN ZHOU ,","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5140404389","display_name":"Xuanchen Zhou","orcid":"https://orcid.org/0009-0002-1659-2592","observed_orcids":["https://orcid.org/0009-0002-1659-2592"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Xuanchen","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":true,"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":0.8065999746322632,"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":0.8065999746322632,"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":0.14219999313354492,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.02019999921321869,"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/multimodal-retrieval","display_name":"multimodal retrieval","score":0.9710000157356262},{"id":"https://openalex.org/keywords/residual-quantization","display_name":"residual quantization","score":0.7749999761581421},{"id":"https://openalex.org/keywords/autoregressive-decoding","display_name":"autoregressive decoding","score":0.7089999914169312},{"id":"https://openalex.org/keywords/text-to-image-retrieval","display_name":"text-to-image retrieval","score":0.7229999899864197},{"id":"https://openalex.org/keywords/dense-retrieval","display_name":"dense retrieval","score":0.5879999995231628},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6000000238418579}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.819599986076355},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.5974000096321106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.524399995803833},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5153999924659729},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5135999917984009},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.48579999804496765},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.482699990272522},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.48170000314712524},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.45260000228881836},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4406999945640564},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.41100001335144043},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.3865000009536743},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3711000084877014},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.25690001249313354},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.12987","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.12987","pdf_url":"https://arxiv.org/pdf/2608.12987","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.2608.12987","doi":"https://doi.org/10.48550/arxiv.2608.12987","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.12987","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.12987","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.12987","pdf_url":"https://arxiv.org/pdf/2608.12987","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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203500331.pdf","grobid_xml":"https://content.openalex.org/works/W7203500331.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generative":[0,99],"information":[1],"retrieval":[2,14,60,78,88,104,111,234],"(GIR)":[3],"has":[4],"emerged":[5],"as":[6,164],"a":[7,18,31,97,122,170,209],"compelling":[8],"alternative":[9],"to":[10,20,44,168],"the":[11,22,85,135,141,148,159,186,190,223],"conventional":[12],"index-retrieve-then-rank":[13],"pipeline":[15],"by":[16,91],"training":[17],"generator":[19],"produce":[21],"identifiers":[23],"of":[24,33,84],"relevant":[25],"items":[26,67],"directly.":[27],"Despite":[28],"its":[29,77,132,156],"promise,":[30],"number":[32],"open":[34],"challenges":[35],"still":[36,80],"remain.":[37],"First,":[38],"constrained":[39,176],"left-to-right":[40],"decoding":[41],"is":[42,120,137],"vulnerable":[43],"prefix-level":[45],"errors":[46],"and":[47,64,116,147,179,189,218,230],"local":[48],"optima.":[49],"Second,":[50],"most":[51],"prior":[52],"GIR":[53,73],"research":[54],"remains":[55],"largely":[56],"unimodal,":[57],"leaving":[58],"instruction-aware":[59],"across":[61,113,202],"text,":[62],"image,":[63],"mixed":[65],"image-text":[66],"underexplored.":[68],"Third,":[69],"although":[70],"discrete":[71],"identifier-based":[72],"offers":[74],"higher":[75],"efficiency,":[76],"accuracy":[79],"lags":[81],"behind":[82],"that":[83,126],"cutting-edge":[86],"dense-vector-based":[87],"methods.":[89],"Motivated":[90],"these":[92],"challenges,":[93],"we":[94],"propose":[95],"DrIG,":[96],"novel":[98],"framework":[100],"for":[101,239],"universal":[102],"multimodal":[103,200],"featuring":[105],"Dual-role":[106],"Identifiers,":[107],"which":[108,174],"supports":[109],"diverse":[110,203],"tasks":[112],"multiple":[114],"modalities":[115],"domains.":[117],"Each":[118],"candidate":[119],"assigned":[121],"single":[123],"residual-quantized":[124],"identifier":[125,136],"serves":[127],"two":[128],"complementary":[129],"roles.":[130],"In":[131,155],"sequential":[133],"role,":[134,158],"decoded":[138],"autoregressively,":[139],"where":[140],"first":[142],"token":[143],"explicitly":[144],"models":[145],"modality":[146],"remaining":[149],"tokens":[150,161],"capture":[151],"progressively":[152],"finer":[153],"semantics.":[154],"set-based":[157],"same":[160],"are":[162],"reinterpreted":[163],"an":[165],"unordered":[166],"set":[167],"provide":[169],"prefix-independent":[171],"relevance":[172],"prior,":[173],"guides":[175],"beam":[177,226],"search":[178],"alleviates":[180],"local-optimum":[181],"errors.":[182],"Extensive":[183],"experiments":[184],"on":[185],"M-BEIR":[187],"benchmark":[188],"text-to-image":[191],"evaluation":[192],"datasets":[193],"show":[194],"that:(1)DrIG":[195],"consistently":[196],"outperforms":[197],"state-of-the-art":[198],"generative":[199],"baselines":[201],"tasks,":[204],"while":[205],"hybrid":[206],"reranking":[207,228],"achieves":[208],"favorable":[210],"efficiency-effectiveness":[211],"trade-off":[212],"against":[213],"strong":[214],"dense":[215],"retrievers.":[216],"(2)Ablation":[217],"scaling":[219],"analyses":[220],"reveal":[221],"how":[222],"base":[224],"LMM,":[225],"size,":[227],"depth,":[229],"fusion":[231],"strategy":[232],"affect":[233],"performance,":[235],"providing":[236],"practical":[237],"guidance":[238],"system":[240],"design.":[241]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2026-08-15T00:00:00"}