{"id":"https://openalex.org/W7147230207","doi":"https://doi.org/10.48550/arxiv.2603.29897","title":"UniRank: End-to-End Domain-Specific Reranking of Hybrid Text-Image Candidates","display_name":"UniRank: End-to-End Domain-Specific Reranking of Hybrid Text-Image Candidates","publication_year":2026,"publication_date":"2026-02-08","ids":{"openalex":"https://openalex.org/W7147230207","doi":"https://doi.org/10.48550/arxiv.2603.29897"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.29897","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29897","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":"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.2603.29897","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124420727","display_name":"Yupei Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yupei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132578488","display_name":"Lin Lin Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123975495","display_name":"Wanxi Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng, Wanxi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132673647","display_name":"Lin Qu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qu, Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132700738","display_name":"Shikui Tu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tu, Shikui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5132554782","display_name":"Lei Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Lei","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.866599977016449,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.866599977016449,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.03629999980330467,"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/T10028","display_name":"Topic Modeling","score":0.027699999511241913,"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/pairwise-comparison","display_name":"Pairwise comparison","score":0.6126000285148621},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5234000086784363},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4941999912261963},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4787999987602234},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.4724000096321106},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46299999952316284},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4343999922275543},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.4138999879360199}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7983999848365784},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6126000285148621},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5752000212669373},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5234000086784363},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4941999912261963},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4787999987602234},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.4724000096321106},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46299999952316284},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4343999922275543},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.4138999879360199},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4138000011444092},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3894999921321869},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.37790000438690186},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.2897999882698059},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2556999921798706},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.29897","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29897","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":"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.2603.29897","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29897","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":"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reranking":[0],"is":[1,34,41],"a":[2,38,119,165,171],"critical":[3],"component":[4],"in":[5,13,109],"many":[6],"information":[7],"retrieval":[8,198],"pipelines.":[9],"Despite":[10],"remarkable":[11],"progress":[12],"text-only":[14],"settings,":[15],"multimodal":[16,75,98],"reranking":[17,121],"remains":[18],"challenging,":[19],"particularly":[20],"when":[21],"the":[22,35],"candidate":[23],"set":[24],"contains":[25],"hybrid":[26,128,138],"text":[27,39,45,88],"and":[28,54,68,86,106,126,169,181,199,214],"image":[29,49],"items.":[30],"A":[31],"key":[32],"difficulty":[33],"modality":[36,133],"gap:":[37],"reranker":[40],"intrinsically":[42],"closer":[43],"to":[44,48,52,73,164],"candidates":[46,83,130],"than":[47],"candidates,":[50],"leading":[51],"biased":[53],"suboptimal":[55],"cross-modal":[56,66,157],"ranking.":[57],"Vision-language":[58],"models":[59],"(VLMs)":[60],"mitigate":[61],"this":[62,137],"gap":[63],"through":[64,186],"strong":[65],"alignment":[67,174],"have":[69],"recently":[70],"been":[71],"adopted":[72],"build":[74],"rerankers.":[76],"However,":[77],"most":[78],"VLM-based":[79,120],"rerankers":[80,99],"encode":[81],"all":[82],"as":[84,89],"images,":[85],"treating":[87],"images":[90],"introduces":[91],"substantial":[92],"computational":[93],"overhead.":[94],"Meanwhile,":[95],"existing":[96],"open-source":[97],"are":[100],"typically":[101],"trained":[102],"on":[103,136,195],"general-domain":[104],"data":[105],"often":[107],"underperform":[108],"domain-specific":[110],"scenarios.":[111],"To":[112],"address":[113],"these":[114],"limitations,":[115],"we":[116],"propose":[117],"UniRank,":[118],"framework":[122],"that":[123,148,154,176,204],"natively":[124],"scores":[125],"orders":[127],"text-image":[129],"without":[131],"any":[132],"conversion.":[134],"Building":[135],"scoring":[139,159],"interface,":[140],"UniRank":[141,205],"provides":[142],"an":[143,151],"end-to-end":[144],"domain":[145],"adaptation":[146],"pipeline":[147],"includes:":[149],"(1)":[150],"instruction-tuning":[152],"stage":[153,175],"learns":[155],"calibrated":[156],"relevance":[158],"by":[160,212],"mapping":[161],"label-token":[162],"likelihoods":[163],"unified":[166],"scalar":[167],"score;":[168],"(2)":[170],"hard-negative-driven":[172],"preference":[173],"constructs":[177],"in-domain":[178],"pairwise":[179],"preferences":[180],"performs":[182],"query-level":[183],"policy":[184],"optimization":[185],"reinforcement":[187],"learning":[188],"from":[189],"human":[190],"feedback":[191],"(RLHF).":[192],"Extensive":[193],"experiments":[194],"scientific":[196],"literature":[197],"design":[200],"patent":[201],"search":[202],"demonstrate":[203],"consistently":[206],"outperforms":[207],"state-of-the-art":[208],"baselines,":[209],"improving":[210],"Recall@1":[211],"8.9%":[213],"7.3%,":[215],"respectively.":[216]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-02T00:00:00"}