{"id":"https://openalex.org/W7166877309","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1453","title":"SCOPE: Preserving Modality-Specific Cues to Mitigate Modality Laziness in Multimodal Learning","display_name":"SCOPE: Preserving Modality-Specific Cues to Mitigate Modality Laziness in Multimodal Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166877309","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1453"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1453","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1453","pdf_url":"https://aclanthology.org/2026.findings-acl.1453.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: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1453.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139716840","display_name":"Jingfan Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingfan Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139848855","display_name":"Rui Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104307226","display_name":"Hong Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang Hong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139822890","display_name":"Ke Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ke Yuan","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86525162,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"29066","last_page":"29078"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.11540000140666962,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.11540000140666962,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.05829999968409538,"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/T10730","display_name":"Language Development and Disorders","score":0.04859999939799309,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6057000160217285},{"id":"https://openalex.org/keywords/laziness","display_name":"Laziness","score":0.5735999941825867},{"id":"https://openalex.org/keywords/multimodal-therapy","display_name":"Multimodal therapy","score":0.32030001282691956},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.302700012922287},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.2948000133037567},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.2915000021457672}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6057000160217285},{"id":"https://openalex.org/C2776447739","wikidata":"https://www.wikidata.org/wiki/Q484","display_name":"Laziness","level":2,"score":0.5735999941825867},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5038999915122986},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4700999855995178},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4083000123500824},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3292999863624573},{"id":"https://openalex.org/C4441509","wikidata":"https://www.wikidata.org/wiki/Q6418787","display_name":"Multimodal therapy","level":2,"score":0.32030001282691956},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.30149999260902405},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28349998593330383},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C96851999","wikidata":"https://www.wikidata.org/wiki/Q848369","display_name":"Subconscious","level":3,"score":0.2603999972343445},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.25600001215934753},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1453","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1453","pdf_url":"https://aclanthology.org/2026.findings-acl.1453.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: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1453","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1453","pdf_url":"https://aclanthology.org/2026.findings-acl.1453.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: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4554742357","display_name":null,"funder_award_id":"62276213","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322186","display_name":"Natural Science Foundation of Hubei Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166877309.pdf","grobid_xml":"https://content.openalex.org/works/W7166877309.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"learning":[1,62],"aims":[2],"to":[3,77,111,133],"learn":[4],"unified":[5,59],"multimodal":[6,18,64],"representations":[7],"from":[8,81],"heterogeneous":[9],"modalities":[10,90],"and":[11,29,49,84,114],"supports":[12],"many":[13],"natural":[14],"language":[15],"processing":[16],"tasks.However,":[17],"models":[19],"often":[20],"exhibit":[21],"modality":[22,28,40],"laziness:":[23],"over-relying":[24],"on":[25,120],"a":[26,58,72],"dominant":[27],"under-exploiting":[30],"complementary":[31,115],"signals.Existing":[32],"approaches":[33],"typically":[34],"strengthen":[35],"unimodal":[36],"training":[37],"or":[38],"rebalance":[39],"contributions,":[41],"but":[42],"they":[43],"may":[44],"still":[45],"emphasize":[46],"shared":[47,79,113],"semantics":[48,80],"overlook":[50],"modality-specific":[51,82],"cues.To":[52],"address":[53],"this,":[54],"we":[55],"propose":[56],"SCOPE,":[57],"framework":[60],"for":[61],"complete":[63],"representations,":[65],"achieving":[66,131],"Shared-and-COmplementary":[67],"cue":[68],"PrEservation.Firstly,":[69],"SCOPE":[70,88,103,126],"uses":[71],"mutual":[73],"informationguided":[74],"disentanglement":[75],"module":[76],"separate":[78],"cues":[83,116],"mitigate":[85],"representation":[86],"collapse.Secondly,":[87],"aligns":[89],"by":[91],"enforcing":[92],"structural":[93],"consistency":[94],"between":[95],"modality-wise":[96],"semantic":[97],"graphs,":[98],"avoiding":[99],"brittle":[100],"point-wise":[101],"matching.Finally,":[102],"performs":[104],"balanced":[105],"fusion":[106],"via":[107],"structure-aware":[108],"diffusion":[109],"attention":[110],"integrate":[112],"without":[117],"feature":[118],"homogenization.Experiments":[119],"five":[121],"benchmark":[122],"datasets":[123],"show":[124],"that":[125],"consistently":[127],"outperforms":[128],"SOTA":[129],"baselines,":[130],"up":[132],"27.10%":[134],"accuracy":[135],"improvement.":[136]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
