{"id":"https://openalex.org/W4414360138","doi":"https://doi.org/10.24963/ijcai.2025/107","title":"MAGE: Multimodal Alignment and Generation Enhancement via Bridging Visual and Semantic Spaces","display_name":"MAGE: Multimodal Alignment and Generation Enhancement via Bridging Visual and Semantic Spaces","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360138","doi":"https://doi.org/10.24963/ijcai.2025/107"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/107","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030895448","display_name":"E Shaojun","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaojun E","raw_affiliation_strings":["Global Tone Communication Technology Co., Ltd., Beijing, China","School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Global Tone Communication Technology Co., Ltd., Beijing, China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025414151","display_name":"Yuchen Yang","orcid":"https://orcid.org/0000-0001-8495-6103"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Yang","raw_affiliation_strings":["Faculty of computing, Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of computing, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100547153","display_name":"Jiaheng Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaheng Wu","raw_affiliation_strings":["Faculty of computing, Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of computing, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019954538","display_name":"Yan Zhang","orcid":"https://orcid.org/0000-0002-2598-8321"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan Zhang","raw_affiliation_strings":["Global Tone Communication Technology Co., Ltd., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Global Tone Communication Technology Co., Ltd., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101661008","display_name":"Tiejun Zhao","orcid":"https://orcid.org/0000-0003-4659-4935"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiejun Zhao","raw_affiliation_strings":["Faculty of computing, Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of computing, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ziyan Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyan Chen","raw_affiliation_strings":["Global Tone Communication Technology Co., Ltd., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Global Tone Communication Technology Co., Ltd., Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"954","last_page":"962"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13071","display_name":"Digital Storytelling and Education","score":0.9107999801635742,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T13071","display_name":"Digital Storytelling and Education","score":0.9107999801635742,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.8883000016212463},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.663100004196167},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.5741999745368958},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4657000005245209},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.38499999046325684},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.37439998984336853},{"id":"https://openalex.org/keywords/semantic-data-model","display_name":"Semantic data model","score":0.3643999993801117},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.35109999775886536}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.8883000016212463},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8203999996185303},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.663100004196167},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.5741999745368958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5299999713897705},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4657000005245209},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38929998874664307},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.38499999046325684},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.37439998984336853},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.3643999993801117},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.35109999775886536},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32910001277923584},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26510000228881836},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/107","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"the":[1,9,26,36,62,82,96,109,129,149],"latest":[2],"advancements":[3],"in":[4,58],"multimodal":[5,30,144,157],"learning,":[6],"effectively":[7],"addressing":[8],"spatial":[10],"and":[11,41,74,87,104,123,177,181],"semantic":[12,55,83,105],"losses":[13],"of":[14,28,85],"visual":[15,39],"data":[16],"after":[17],"encoding":[18],"remains":[19],"a":[20,77,117,140],"critical":[21],"challenge.":[22],"This":[23],"is":[24,32],"because":[25],"performance":[27,165],"large":[29,42,158],"models":[31],"positively":[33],"correlated":[34],"with":[35],"coupling":[37],"between":[38,111],"encoders":[40],"language":[43],"models.":[44],"Existing":[45],"approaches":[46],"often":[47],"face":[48],"issues":[49],"such":[50],"as":[51],"vector":[52],"gaps":[53],"or":[54],"disparities,":[56],"resulting":[57],"information":[59],"loss":[60],"during":[61],"propagation":[63],"process.":[64],"To":[65,107],"address":[66],"these":[67],"issues,":[68],"we":[69,115,138],"propose":[70],"MAGE":[71,101],"(Multimodal":[72],"Alignment":[73,98],"Generation":[75],"Enhancement),":[76],"novel":[78],"framework":[79],"that":[80,120],"bridges":[81],"spaces":[84],"vision":[86],"text":[88],"through":[89],"an":[90],"innovative":[91],"alignment":[92,130],"mechanism.":[93],"By":[94],"introducing":[95],"Intelligent":[97],"Network":[99],"(IAN),":[100],"achieves":[102],"dimensional":[103],"alignment.":[106],"reduce":[108],"gap":[110],"synonymous":[112],"heterogeneous":[113],"data,":[114],"employ":[116],"training":[118],"strategy":[119],"combines":[121],"cross-entropy":[122],"mean":[124],"squared":[125],"error,":[126],"significantly":[127,163],"enhancing":[128],"effect.":[131],"Moreover,":[132],"to":[133,147,167],"enhance":[134],"MAGE\u2019s":[135],"\u201cAny-to-Any\u201d":[136],"capability,":[137],"developed":[139],"fine-tuning":[141],"dataset":[142],"for":[143],"tool-calling":[145],"instructions":[146],"expand":[148],"model\u2019s":[150],"output":[151],"capability":[152],"boundaries.":[153],"Finally,":[154],"our":[155],"proposed":[156],"model":[159],"architecture,":[160],"MAGE,":[161],"achieved":[162],"better":[164],"compared":[166],"similar":[168],"works":[169],"across":[170],"various":[171],"evaluation":[172],"benchmarks,":[173],"including":[174],"MME,":[175],"MMBench,":[176],"SEED.":[178],"Complete":[179],"code":[180],"appendix":[182],"are":[183],"available":[184],"at:":[185],"https://github.com/GTCOM-NLP/MAGE":[186]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}