{"id":"https://openalex.org/W4417513173","doi":"https://doi.org/10.48550/arxiv.2505.06592","title":"Batch Augmentation with Unimodal Fine-tuning for Multimodal Fusion of Large Language Models","display_name":"Batch Augmentation with Unimodal Fine-tuning for Multimodal Fusion of Large Language Models","publication_year":2025,"publication_date":"2025-05-10","ids":{"openalex":"https://openalex.org/W4417513173","doi":"https://doi.org/10.48550/arxiv.2505.06592"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.06592","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.06592","pdf_url":"https://arxiv.org/pdf/2505.06592","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,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.06592","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063766245","display_name":"H M Dipu Kabir","orcid":"https://orcid.org/0000-0002-3395-1772","observed_orcids":["https://orcid.org/0000-0002-3395-1772"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kabir, H M Dipu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064583762","display_name":"Subrota Kumar Mondal","orcid":"https://orcid.org/0000-0002-0008-7797","observed_orcids":["https://orcid.org/0000-0002-0008-7797"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mondal, Subrota Kumar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5034828056","display_name":"Mohammad Ali Moni","orcid":"https://orcid.org/0000-0003-0756-1006","observed_orcids":["https://orcid.org/0000-0003-0756-1006","https://orcid.org/0000-0002-5696-2802"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moni, Mohammad Ali","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":true,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980000257492065,"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":0.9980000257492065,"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":0.0010999999940395355,"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/T10036","display_name":"Advanced Neural Network Applications","score":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"multimodal learning","score":0.9950000047683716},{"id":"https://openalex.org/keywords/ultrasound-image-analysis","display_name":"ultrasound image analysis","score":0.5130000114440918},{"id":"https://openalex.org/keywords/clinical-narratives","display_name":"clinical text","score":0.5090000033378601},{"id":"https://openalex.org/keywords/multimodal-pretraining","display_name":"multimodal pre-training","score":0.5609999895095825},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.6990000009536743}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7944999933242798},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7932999730110168},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.6399000287055969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6049000024795532},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5031999945640564},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5013999938964844},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4302000105381012},{"id":"https://openalex.org/C172658912","wikidata":"https://www.wikidata.org/wiki/Q661613","display_name":"Batch processing","level":2,"score":0.4219000041484833},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3650999963283539},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.350600004196167},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3449999988079071},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33899998664855957},{"id":"https://openalex.org/C4441509","wikidata":"https://www.wikidata.org/wiki/Q6418787","display_name":"Multimodal therapy","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3052000105381012},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29159998893737793},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.26249998807907104}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.06592","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.06592","pdf_url":"https://arxiv.org/pdf/2505.06592","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,"listed_in":[],"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.2505.06592","doi":"https://doi.org/10.48550/arxiv.2505.06592","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.06592","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,"listed_in":[],"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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.06592","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.06592","pdf_url":"https://arxiv.org/pdf/2505.06592","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,"listed_in":[],"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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417513173.pdf","grobid_xml":"https://content.openalex.org/works/W4417513173.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,30,47,160],"propose":[4],"batch":[5,56,80,91,98],"augmentation":[6,81,92,99],"with":[7,15,24,55,124,181],"unimodal":[8,17,22,41,53,63,75],"fine-tuning":[9],"for":[10,100,165,171],"multimodal":[11,90,102,116,119],"learning.":[12],"We":[13,19,87,104,173],"start":[14],"pre-trained":[16],"models.":[18],"fine-tune":[20],"the":[21,25,49,60,83,97,101,106,110,125,129,134,145,155,162,168,175,178,185],"models":[23,42,64],"application":[26],"data.":[27,103],"After":[28],"that,":[29],"form":[31],"a":[32,89],"Multi-Layer":[33],"Perceptron":[34],"(MLP)":[35],"head":[36],"that":[37,95],"takes":[38],"information":[39],"from":[40],"and":[43,52,113,167],"provides":[44],"output.":[45],"Finally,":[46],"train":[48],"MLP":[50],"layer":[51],"parts":[54],"augmentation.":[57],"Depending":[58],"on":[59,109,154],"data,":[61],"some":[62],"can":[65,77],"be":[66],"replaced":[67],"by":[68],"hard-coded":[69],"scripts":[70,176],"or":[71],"AI":[72],"agents.":[73],"The":[74,118],"training":[76,127],"also":[78],"follow":[79],"when":[82],"data":[84],"is":[85],"augmentable.":[86],"write":[88],"dataloader":[93],"script":[94],"implements":[96],"investigate":[105],"proposed":[107,126,146,179],"method":[108,147,180],"FPU23":[111],"ultrasound":[112],"UPMC":[114,156],"Food-101":[115,157],"datasets.":[117,139],"large":[120],"language":[121],"model":[122,164,170],"(LLM)":[123],"achieves":[128,148],"best":[130],"average":[131],"result":[132],"among":[133],"investigated":[135],"methods":[136],"across":[137],"both":[138],"According":[140],"to":[141],"our":[142],"literature":[143],"search,":[144],"state-of-the-art":[149],"(SOTA)":[150],"accuracy":[151],"of":[152,177],"93.29%":[153],"dataset,":[158],"while":[159],"apply":[161],"ViT-L/16":[163],"vision":[166],"GPT-2":[169],"text.":[172],"share":[174],"traditional":[182],"counterparts":[183],"at":[184],"following":[186],"repository:":[187],"github.com/dipuk0506/multimodal":[188]},"counts_by_year":[],"updated_date":"2026-10-13T10:08:12.033832","created_date":"2025-10-10T00:00:00"}