{"id":"https://openalex.org/W4403780546","doi":"https://doi.org/10.1145/3664647.3688995","title":"Demonstrative Instruction Following in Multimodal LLMs via Integrating Low-Rank Adaptation with Ensemble Learning","display_name":"Demonstrative Instruction Following in Multimodal LLMs via Integrating Low-Rank Adaptation with Ensemble Learning","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780546","doi":"https://doi.org/10.1145/3664647.3688995"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3688995","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3688995","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102082878","display_name":"Jingyu Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jingyu Wei","raw_affiliation_strings":["National University of Defense Technology, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000468857","display_name":"Yi Su","orcid":"https://orcid.org/0000-0001-8794-7376"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Su","raw_affiliation_strings":["National University of Defense Technology, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013340793","display_name":"Kele Xu","orcid":"https://orcid.org/0000-0001-5997-5169"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kele Xu","raw_affiliation_strings":["National University of Defense Technology, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103251142","display_name":"Lingbin Zeng","orcid":"https://orcid.org/0000-0002-4082-4798"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingbin Zeng","raw_affiliation_strings":["National University of Defense Technology, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050900731","display_name":"Bo Liu","orcid":"https://orcid.org/0000-0002-9953-8438"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["Strategic Assessments and Consultation Institute, Academy of Military Science, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Strategic Assessments and Consultation Institute, Academy of Military Science, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101522100","display_name":"Huaimin Wang","orcid":"https://orcid.org/0000-0002-3245-1901"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaimin Wang","raw_affiliation_strings":["National University of Defense Technology, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102082878"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.7724,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.77224801,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"11435","last_page":"11441"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9914000034332275,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9914000034332275,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9908000230789185,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9908000230789185,"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/demonstrative","display_name":"Demonstrative","score":0.9577754735946655},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7241189479827881},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6900064945220947},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.6374205350875854},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.5357019305229187},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4550027847290039},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.4499550461769104},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3223905563354492},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.1727536916732788},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1228674054145813},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10996448993682861},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08805164694786072}],"concepts":[{"id":"https://openalex.org/C2780277889","wikidata":"https://www.wikidata.org/wiki/Q282301","display_name":"Demonstrative","level":2,"score":0.9577754735946655},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7241189479827881},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6900064945220947},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.6374205350875854},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.5357019305229187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4550027847290039},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.4499550461769104},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3223905563354492},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.1727536916732788},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1228674054145813},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10996448993682861},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08805164694786072},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3688995","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3688995","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2560674852","https://openalex.org/W2747329762","https://openalex.org/W2914695977","https://openalex.org/W4212883601","https://openalex.org/W4321636575","https://openalex.org/W4385571189","https://openalex.org/W4387969627","https://openalex.org/W4402727764","https://openalex.org/W4403780639"],"related_works":["https://openalex.org/W2349070548","https://openalex.org/W2106761869","https://openalex.org/W3013971854","https://openalex.org/W2099127512","https://openalex.org/W3138993881","https://openalex.org/W2029584511","https://openalex.org/W2772359885","https://openalex.org/W3011471740","https://openalex.org/W2884580467","https://openalex.org/W2572315477"],"abstract_inverted_index":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs),":[4],"by":[5],"expanding":[6],"the":[7,41,45,49,75,85,154,165,184,201,206,210,212,219],"model's":[8],"capabilities":[9],"to":[10,38,97,176],"perceive":[11],"and":[12,67,128,140],"interact":[13],"through":[14],"multi-modalities,":[15],"have":[16],"significantly":[17],"enhanced":[18],"performance":[19,99,179,217],"across":[20],"various":[21],"tasks.":[22,181],"The":[23],"perception":[24],"of":[25,62,77,87,167,188],"vision":[26],"is":[27],"an":[28,124,196],"important":[29],"modality":[30],"developed":[31],"into":[32,123],"LLM,":[33],"enabling":[34],"research":[35],"in":[36,44,57,100],"vision-language":[37],"continuously":[39],"lead":[40,96],"cutting-edge":[42],"advancements":[43],"MLLM":[46,202],"community.":[47],"However,":[48],"standard":[50],"pre-training":[51],"pipeline":[52],"on":[53,90,180,218],"image-text":[54],"pairs":[55],"results":[56],"a":[58,80,112,131],"limited":[59],"model":[60,178],"understanding":[61],"relationships":[63],"between":[64],"multiple":[65,107],"images":[66],"texts,":[68],"as":[69,71],"well":[70],"visual":[72,82,88,161],"details.":[73],"Additionally,":[74,151],"setting":[76],"fine-tuning":[78,158],"with":[79,191],"frozen":[81],"backbone":[83],"hinders":[84],"enhancement":[86],"representations":[89,162],"new":[91],"data.":[92],"These":[93],"two":[94],"issues":[95],"suboptimal":[98],"models":[101],"for":[102,137],"demonstrative":[103],"instruction":[104],"following":[105],"about":[106],"images.":[108],"This":[109],"work":[110],"introduces":[111],"novel":[113],"framework":[114],"called":[115],"MLoEM,":[116],"which":[117],"first":[118],"converts":[119],"long":[120],"multimodal":[121,146],"data":[122],"interleaved":[125],"image-instruction":[126],"format,":[127],"then":[129],"adopts":[130],"fully":[132],"autoregressive":[133],"architecture":[134],"model,":[135],"allowing":[136],"more":[138],"robust":[139],"coherent":[141],"learning":[142],"from":[143],"naturally":[144],"occurring":[145],"documents":[147],"than":[148],"pair-based":[149],"pipeline.":[150],"we":[152,172,194],"incorporate":[153],"Low-Rank":[155],"Adaptation":[156],"(LoRA)":[157],"method,":[159],"enhancing":[160],"while":[163,203],"maintaining":[164],"stability":[166],"previously":[168],"learned":[169],"knowledge.":[170],"Finally,":[171],"utilize":[173],"ensemble":[174,197],"methods":[175],"enhance":[177],"To":[182],"alleviate":[183],"storage":[185],"overhead":[186],"issue":[187],"parallel":[189],"ensembles":[190],"large":[192],"models,":[193],"design":[195],"approach":[198],"that":[199],"shares":[200],"only":[204],"switching":[205],"LoRA":[207],"matrices.":[208],"In":[209],"experiments,":[211],"proposed":[213],"MLoEM":[214],"shows":[215],"superior":[216],"testing":[220],"set.":[221]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}