{"id":"https://openalex.org/W4417145602","doi":"https://doi.org/10.1109/wacv61042.2026.00338","title":"Language Integration in Fine-Tuning Multimodal Large Language Models for Image-Based Regression","display_name":"Language Integration in Fine-Tuning Multimodal Large Language Models for Image-Based Regression","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4417145602","doi":"https://doi.org/10.1109/wacv61042.2026.00338"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00338","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00338","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.14997","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062319365","display_name":"Roy H. Jennings","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131878","display_name":"Samsung (Israel)","ror":"https://ror.org/03k1ymh78","country_code":"IL","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210131878"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Roy H. Jennings","raw_affiliation_strings":["Samsung Israel R&#x0026;D Center,Tel-Aviv,Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Israel R&#x0026;D Center,Tel-Aviv,Israel","institution_ids":["https://openalex.org/I4210131878"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084021209","display_name":"Genady Paikin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131878","display_name":"Samsung (Israel)","ror":"https://ror.org/03k1ymh78","country_code":"IL","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210131878"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Genady Paikin","raw_affiliation_strings":["Samsung Israel R&#x0026;D Center,Tel-Aviv,Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Israel R&#x0026;D Center,Tel-Aviv,Israel","institution_ids":["https://openalex.org/I4210131878"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085622166","display_name":"Roy Shaul","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131878","display_name":"Samsung (Israel)","ror":"https://ror.org/03k1ymh78","country_code":"IL","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210131878"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Roy Shaul","raw_affiliation_strings":["Samsung Israel R&#x0026;D Center,Tel-Aviv,Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Israel R&#x0026;D Center,Tel-Aviv,Israel","institution_ids":["https://openalex.org/I4210131878"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085954960","display_name":"Evgeny Soloveichik","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131878","display_name":"Samsung (Israel)","ror":"https://ror.org/03k1ymh78","country_code":"IL","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210131878"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Evgeny Soloveichik","raw_affiliation_strings":["Samsung Israel R&#x0026;D Center,Tel-Aviv,Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Israel R&#x0026;D Center,Tel-Aviv,Israel","institution_ids":["https://openalex.org/I4210131878"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210131878"],"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":"3462","last_page":"3471"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5367000102996826,"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":0.5367000102996826,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.13740000128746033,"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/T10028","display_name":"Topic Modeling","score":0.055799998342990875,"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/leverage","display_name":"Leverage (statistics)","score":0.7509999871253967},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6225000023841858},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.5062999725341797},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4805000126361847},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4611000120639801},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.42170000076293945},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.39489999413490295},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"Regression analysis","score":0.3709999918937683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.794700026512146},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7509999871253967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6230000257492065},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6225000023841858},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5471000075340271},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5102999806404114},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.5062999725341797},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4805000126361847},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4611000120639801},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.42170000076293945},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.39489999413490295},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.3709999918937683},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3440999984741211},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3073999881744385},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.2702000141143799},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C120894424","wikidata":"https://www.wikidata.org/wiki/Q1322871","display_name":"Exploratory data analysis","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00338","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00338","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.14997","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.14997","pdf_url":"https://arxiv.org/pdf/2507.14997","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.14997","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.14997","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.14997","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.14997","pdf_url":"https://arxiv.org/pdf/2507.14997","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3,54],"(MLLMs)":[4],"show":[5],"promise":[6],"for":[7],"image-based":[8],"regression":[9],"tasks,":[10],"but":[11],"current":[12],"approaches":[13,47,91],"face":[14],"key":[15],"limitations.":[16],"Recent":[17],"methods":[18],"fine-tune":[19],"MLLMs":[20,142,175],"using":[21,55,117],"preset":[22,56],"output":[23],"vocabularies":[24,57],"and":[25,58,171,196],"generic":[26,59,131],"task-level":[27],"prompts":[28,60,126,134,155],"(e.g.,":[29],"\"How":[30],"would":[31],"you":[32],"rate":[33],"this":[34,37],"image?\"),":[35],"assuming":[36],"mimics":[38],"human":[39],"rating":[40],"behavior.":[41],"Our":[42],"analysis":[43],"reveals":[44],"that":[45,92,124,174],"these":[46],"provide":[48],"no":[49],"benefit":[50,176],"over":[51],"image-only":[52,64,161],"training.":[53],"perform":[61],"equivalently":[62],"to":[63,67,143,154],"models,":[65],"failing":[66],"leverage":[68,144],"semantic":[69,136,178],"understanding":[70],"from":[71,168,177],"textual":[72],"input.":[73],"We":[74,163,185],"propose":[75],"Regression":[76],"via":[77],"Transformer-Based":[78],"Classification":[79],"(RvTC),":[80],"which":[81],"replaces":[82],"vocabulary-constrained":[83],"classification":[84],"with":[85],"a":[86],"flexible":[87],"bin-based":[88],"approach.":[89],"Unlike":[90,130],"address":[93],"discretization":[94],"errors":[95],"through":[96,105,165],"complex":[97],"distributional":[98],"modeling,":[99],"RvTC":[100,187],"eliminates":[101],"manual":[102],"vocabulary":[103],"crafting":[104],"straightforward":[106],"bin":[107],"increase,":[108],"achieving":[109],"state-of-the-art":[110,160],"performance":[111],"on":[112],"four":[113],"image":[114],"assessment":[115],"datasets":[116,173],"only":[118],"images.":[119],"More":[120],"importantly,":[121],"we":[122],"demonstrate":[123,164],"data-specific":[125],"dramatically":[127],"improve":[128],"performance.":[129],"task":[132],"descriptions,":[133],"containing":[135],"information":[137],"about":[138],"specific":[139],"images":[140],"enable":[141],"cross-modal":[145],"understanding.":[146],"On":[147],"the":[148,169],"AVA":[149,170],"dataset,":[150],"adding":[151],"challenge":[152],"titles":[153],"substantially":[156],"improves":[157],"our":[158],"already":[159],"baseline.":[162],"empirical":[166],"evidence":[167],"AGIQA-3k":[172],"prompt":[179],"information,":[180],"surpassing":[181],"mere":[182],"statistical":[183],"biases.":[184],"validate":[186],"across":[188],"two":[189],"different":[190],"MLLM":[191],"architectures,":[192],"demonstrating":[193],"consistent":[194],"improvements":[195],"method":[197],"generalizability.":[198],"<sup":[199],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[200],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[201]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}