{"id":"https://openalex.org/W7168359139","doi":"https://doi.org/10.48550/arxiv.2607.12787","title":"Do We Really Need Multimodal Emotion Language Models Larger Than 1B Parameters?","display_name":"Do We Really Need Multimodal Emotion Language Models Larger Than 1B Parameters?","publication_year":2026,"publication_date":"2026-07-14","ids":{"openalex":"https://openalex.org/W7168359139","doi":"https://doi.org/10.48550/arxiv.2607.12787"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.12787","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.12787","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2607.12787","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140863276","display_name":"Kaiwen Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Kaiwen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140872286","display_name":"Junchen Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Junchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140863969","display_name":"Wenhao Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng, Wenhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140796844","display_name":"Hu Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140927746","display_name":"Joemon M. Jose","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jose, Joemon M.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5140873998","display_name":"Xuri Ge","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ge, Xuri","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/T10667","display_name":"Emotion and Mood Recognition","score":0.9435999989509583,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9435999989509583,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.02810000069439411,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.002899999963119626,"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/inference","display_name":"Inference","score":0.6865000128746033},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6328999996185303},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6324999928474426},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.532800018787384},{"id":"https://openalex.org/keywords/multimodal-transport","display_name":"Multimodal transport","score":0.43689998984336853},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.43459999561309814},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.40790000557899475},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.36169999837875366}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7890999913215637},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6865000128746033},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6328999996185303},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6324999928474426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6032999753952026},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.532800018787384},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4625999927520752},{"id":"https://openalex.org/C2777974031","wikidata":"https://www.wikidata.org/wiki/Q493641","display_name":"Multimodal transport","level":2,"score":0.43689998984336853},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.43459999561309814},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.40790000557899475},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.36169999837875366},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3564999997615814},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3310999870300293},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3125},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27250000834465027},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.2718999981880188},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.26030001044273376}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.12787","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.12787","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2607.12787","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.12787","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"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":{"Recent":[0],"advances":[1],"in":[2,41],"multimodal":[3,14,82,118,146,231],"large":[4],"language":[5,233],"models":[6,101,234],"(MLLMs)":[7],"have":[8],"significantly":[9,220],"improved":[10],"the":[11,81,97,201,226],"performance":[12,33,194,218],"of":[13,204,229],"emotion":[15,147,232],"recognition":[16,122,150],"(MER)":[17],"and":[18,28,55,69,105,116,121,149,181,195],"enabled":[19],"interpretable":[20],"description":[21],"generation":[22],"by":[23,38],"jointly":[24],"modeling":[25],"video,":[26],"audio,":[27],"language,":[29],"etc.":[30],"However,":[31],"these":[32],"improvements":[34],"are":[35,102],"often":[36],"accompanied":[37],"an":[39],"increase":[40],"model":[42,84,135],"parameter":[43],"size":[44],"(e.g,":[45],"at":[46,198,241],"least":[47],"7B),":[48],"which":[49,113],"simultaneously":[50],"incurs":[51],"high":[52],"computational":[53],"costs":[54],"reduces":[56],"inference":[57,222],"efficiency,":[58,196],"thereby":[59],"hindering":[60],"real-time":[61],"deployment":[62,154],"on":[63,189,209],"resource-constrained":[64],"platforms":[65],"such":[66],"as":[67],"robots":[68],"mobile":[70],"devices.":[71],"This":[72,224],"raises":[73],"a":[74,107,131,137,168,183],"fundamental":[75],"question:":[76],"do":[77],"we":[78,95,157],"really":[79],"need":[80],"MER":[83,109,193],"larger":[85,100],"than":[86],"1B":[87],"parameters":[88],"for":[89,235],"high-quality":[90],"MER?":[91],"In":[92],"this":[93],"paper,":[94],"challenge":[96],"assumption":[98],"that":[99,173,191,214],"inherently":[103],"necessary":[104],"proposes":[106],"lightweight":[108,138],"framework":[110],"(called":[111],"Light-MER),":[112],"achieves":[114,216],"better":[115],"faster":[117],"sentiment":[119],"understanding":[120],"through":[123],"knowledge":[124,129,165],"distillation.":[125],"It":[126],"can":[127],"transfer":[128],"from":[130],"strong,":[132],"large-scale":[133],"teacher":[134],"to":[136,143,163],"sub-billion-parameter":[139],"student":[140,205],"model,":[141],"aiming":[142],"preserve":[144],"rich":[145],"reasoning":[148],"while":[151,219],"substantially":[152],"improving":[153,221],"efficiency.":[155,223],"Specifically,":[156],"introduce":[158],"two":[159],"new":[160,169,184],"optimization":[161,186],"strategies":[162],"enhance":[164],"transfer:":[166],"(1)":[167],"optimal":[170],"transport":[171],"loss":[172],"combines":[174],"Sliced":[175],"Wasserstein":[176],"Distance":[177],"with":[178],"hidden-state":[179],"alignment,":[180],"(2)":[182],"multi-reward":[185],"strategy":[187],"based":[188],"GRPO":[190],"balances":[192],"aimed":[197],"further":[199],"enhancing":[200],"learning":[202],"capabilities":[203],"models.":[206],"Extensive":[207],"experiments":[208],"nine":[210],"benchmark":[211],"datasets":[212],"demonstrate":[213],"Light-MER":[215],"state-of-the-art":[217],"highlights":[225],"strong":[227],"potential":[228],"small":[230],"future":[236],"research.":[237],"Code":[238],"is":[239],"available":[240],"https://github.com/GAIR-Lab/Light-MER.":[242]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-16T00:00:00"}