{"id":"https://openalex.org/W7138867703","doi":"https://doi.org/10.48550/arxiv.2603.16455","title":"Evo-Retriever: LLM-Guided Curriculum Evolution with Viewpoint-Pathway Collaboration for Multimodal Document Retrieval","display_name":"Evo-Retriever: LLM-Guided Curriculum Evolution with Viewpoint-Pathway Collaboration for Multimodal Document Retrieval","publication_year":2026,"publication_date":"2026-03-17","ids":{"openalex":"https://openalex.org/W7138867703","doi":"https://doi.org/10.48550/arxiv.2603.16455"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.16455","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16455","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.16455","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129782487","display_name":"Weiqing Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Li, Weiqing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123326728","display_name":"Jinyue Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Jinyue","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129833228","display_name":"Yaqi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yaqi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130042376","display_name":"Haiyang Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Haiyang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130113452","display_name":"Yuewei Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yuewei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130048873","display_name":"Guohua LIU","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Guohua","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129641638","display_name":"Hao Henry Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Hao Henry","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5129782487"],"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":0.9592000246047974,"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":0.9592000246047974,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.008200000040233135,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.0052999998442828655,"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/consistency","display_name":"Consistency (knowledge bases)","score":0.7235000133514404},{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.6114000082015991},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5097000002861023},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41780000925064087},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.38609999418258667},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.33149999380111694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7849000096321106},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7235000133514404},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.6114000082015991},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5116999745368958},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5097000002861023},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41780000925064087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4129999876022339},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.38609999418258667},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.30300000309944153},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3012999892234802},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.290800005197525},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28130000829696655},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.28130000829696655},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27410000562667847}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.16455","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16455","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.16455","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16455","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":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5385289788246155}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Visual-language":[0],"models":[1],"(VLMs)":[2],"excel":[3],"at":[4],"data":[5],"mappings,":[6],"but":[7],"real-world":[8],"document":[9],"heterogeneity":[10],"and":[11,34,80,92,99,136,148],"unstructuredness":[12],"disrupt":[13],"the":[14,40,106,110,122,130],"consistency":[15],"of":[16,146],"cross-modal":[17,45],"embeddings.":[18],"Recent":[19],"late-interaction":[20],"methods":[21],"enhance":[22,75],"image-text":[23],"alignment":[24,73],"through":[25],"multi-vector":[26],"representations,":[27],"yet":[28],"traditional":[29],"training":[30,123],"with":[31,143],"limited":[32],"samples":[33],"static":[35],"strategies":[36],"cannot":[37],"adapt":[38],"to":[39,74,102,128],"model's":[41,131],"dynamic":[42],"evolution,":[43],"causing":[44],"retrieval":[46,55],"confusion.":[47],"To":[48],"overcome":[49],"this,":[50],"we":[51,69],"introduce":[52],"Evo-Retriever,":[53],"a":[54,64,84],"framework":[56],"featuring":[57],"an":[58,116],"LLM-guided":[59],"curriculum":[60,124],"evolution":[61],"built":[62],"upon":[63],"novel":[65],"Viewpoint-Pathway":[66],"collaboration.":[67],"First,":[68],"employ":[70],"multi-view":[71],"image":[72],"fine-grained":[76],"matching":[77],"via":[78],"multi-scale":[79],"multi-directional":[81],"perspectives.":[82],"Then,":[83],"bidirectional":[85],"contrastive":[86],"learning":[87,95],"strategy":[88],"generates":[89],"\"hard":[90],"queries\"":[91],"establishes":[93],"complementary":[94],"paths":[96],"for":[97],"visual":[98],"textual":[100],"disambiguation":[101],"rebalance":[103],"supervision.":[104],"Finally,":[105],"model-state":[107],"summary":[108],"from":[109],"above":[111],"collaboration":[112],"is":[113],"fed":[114],"into":[115],"LLM":[117],"meta-controller,":[118],"which":[119],"adaptively":[120],"adjusts":[121],"using":[125],"expert":[126],"knowledge":[127],"promote":[129],"evolution.":[132],"On":[133],"ViDoRe":[134],"V2":[135],"MMEB":[137],"(VisDoc),":[138],"Evo-Retriever":[139],"achieves":[140],"state-of-the-art":[141],"performance,":[142],"nDCG@5":[144],"scores":[145],"65.2%":[147],"77.1%.":[149]},"counts_by_year":[],"updated_date":"2026-03-20T20:54:20.808490","created_date":"2026-03-20T00:00:00"}