{"id":"https://openalex.org/W4416034170","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.953","title":"MAFMO: Multi-modal Adaptive Fusion with Meta-template Optimization for Vision-Language Models","display_name":"MAFMO: Multi-modal Adaptive Fusion with Meta-template Optimization for Vision-Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034170","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.953"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.953","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.953","pdf_url":"https://aclanthology.org/2025.findings-emnlp.953.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.953.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102483182","display_name":"Mingrui Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingrui Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102017875","display_name":"Lulu Xu","orcid":"https://orcid.org/0000-0003-1082-1067"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lulu Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019087368","display_name":"Jianping Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junliang Du","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28859995,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17576","last_page":"17585"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.942799985408783,"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":0.942799985408783,"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/T12031","display_name":"Speech and dialogue systems","score":0.010099999606609344,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.006200000178068876,"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/fusion","display_name":"Fusion","score":0.30489999055862427},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.3025999963283539},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.299699991941452},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.27140000462532043}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5221999883651733},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34549999237060547},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31349998712539673},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.299699991941452},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2669999897480011},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.953","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.953","pdf_url":"https://aclanthology.org/2025.findings-emnlp.953.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.953","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.953","pdf_url":"https://aclanthology.org/2025.findings-emnlp.953.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034170.pdf","grobid_xml":"https://content.openalex.org/works/W4416034170.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-language":[0],"models":[1],"like":[2],"CLIP":[3],"demonstrate":[4,81],"exceptional":[5],"generalization":[6],"capabilities":[7],"but":[8],"face":[9],"significant":[10],"adaptation":[11],"challenges":[12],"due":[13],"to":[14,30],"parameter":[15],"scale,":[16],"prompt":[17],"sensitivity,":[18],"and":[19,33,61,92],"cross-modal":[20,49],"alignment":[21,32],"difficulties.Existing":[22],"approaches":[23],"primarily":[24],"focus":[25],"on":[26,88],"single-modality":[27],"adjustments,":[28],"leading":[29],"suboptimal":[31],"limited":[34],"generalization.We":[35],"introduce":[36],"MAFMO,":[37],"a":[38,43,53,63],"plugand-play":[39],"framework":[40],"comprising:":[41],"(1)":[42],"Harmonic":[44],"Cross-Modal":[45,64],"Adapter":[46],"enabling":[47],"efficient":[48],"knowledge":[50],"transfer;":[51],"(2)":[52],"Meta-Template":[54],"Optimization":[55],"module":[56],"dynamically":[57],"generating":[58],"input-dependent":[59],"templates;":[60],"(3)":[62],"Knowledge":[65],"Synthesis":[66],"mechanism":[67],"preserving":[68],"critical":[69],"structural":[70],"relationships":[71],"during":[72],"adaptation.Extensive":[73],"experiments":[74],"across":[75],"multiple":[76],"fine-grained":[77],"visual":[78],"recognition":[79],"benchmarks":[80],"MAFMO":[82],"consistently":[83],"improves":[84],"existing":[85],"methods'":[86],"performance":[87],"both":[89],"novel":[90],"classes":[91],"harmonic":[93],"mean,":[94],"while":[95],"maintaining":[96],"robustness":[97],"under":[98],"various":[99],"challenging":[100],"conditions":[101],"with":[102],"minimal":[103],"computational":[104],"overhead.":[105]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}