{"id":"https://openalex.org/W4403555280","doi":"https://doi.org/10.48550/arxiv.2408.07666","title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","display_name":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","publication_year":2024,"publication_date":"2024-08-14","ids":{"openalex":"https://openalex.org/W4403555280","doi":"https://doi.org/10.48550/arxiv.2408.07666"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2408.07666","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.07666","pdf_url":"https://arxiv.org/pdf/2408.07666","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/2408.07666","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yang, Enneng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Enneng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107117626","display_name":"Shen Li","orcid":"https://orcid.org/0000-0002-7111-8861","observed_orcids":["https://orcid.org/0000-0002-7111-8861","https://orcid.org/0000-0001-9494-4552","https://orcid.org/0000-0003-0573-0822"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Li","raw_affiliation_strings":["GUIBING GUO * ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GUIBING GUO * ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007061198","display_name":"Guibing Guo","orcid":"https://orcid.org/0000-0002-1709-5056","observed_orcids":["https://orcid.org/0000-0002-1709-5056"]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo, Guibing","raw_affiliation_strings":["Shenzhen Campus of Sun Yat-sen University , China;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Campus of Sun Yat-sen University , China;","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100326915","display_name":"Xingwei Wang","orcid":"https://orcid.org/0000-0003-2856-4716","observed_orcids":["https://orcid.org/0000-0003-2856-4716","https://orcid.org/0000-0001-8314-2642","https://orcid.org/0009-0000-9338-3693"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xingwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068837264","display_name":"Xiaochun Cao","orcid":"https://orcid.org/0000-0001-7141-708X","observed_orcids":["https://orcid.org/0000-0001-7141-708X"]},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cao, Xiaochun","raw_affiliation_strings":["Northeastern University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University , China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114328665","display_name":"Jie Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5074103823","display_name":"Dacheng Tao","orcid":"https://orcid.org/0000-0001-7225-5449","observed_orcids":["https://orcid.org/0000-0001-7225-5449","https://orcid.org/0000-0002-5979-578X","https://orcid.org/0000-0002-9209-036X"]},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao, Dacheng","raw_affiliation_strings":["Northeastern University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University , China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9922000169754028,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9922000169754028,"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":0.004100000020116568,"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":0.0010999999940395355,"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/model-merging","display_name":"model merging","score":0.996999979019165},{"id":"https://openalex.org/keywords/knowledge-distillation","display_name":"knowledge distillation","score":0.8320000171661377},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8569999933242798},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.9959999918937683},{"id":"https://openalex.org/keywords/continual-learning","display_name":"continual learning","score":0.9509999752044678},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"multi-task learning","score":0.9940000176429749},{"id":"https://openalex.org/keywords/few-shot-learning","display_name":"few-shot learning","score":1.0}],"concepts":[{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.34877097606658936},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3219677805900574}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2408.07666","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.07666","pdf_url":"https://arxiv.org/pdf/2408.07666","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":"pmh:oai:dr.ntu.edu.sg:10356/219754","doi":null,"is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/219754","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"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":"Journal Article"},{"id":"doi:10.48550/arxiv.2408.07666","doi":"https://doi.org/10.48550/arxiv.2408.07666","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2408.07666","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2408.07666","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.07666","pdf_url":"https://arxiv.org/pdf/2408.07666","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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403555280.pdf","grobid_xml":"https://content.openalex.org/works/W4403555280.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7134986073","https://openalex.org/W4416220943","https://openalex.org/W4415101298","https://openalex.org/W4407245141","https://openalex.org/W4403444153","https://openalex.org/W4393108834","https://openalex.org/W7127160659","https://openalex.org/W4416256598","https://openalex.org/W4414459098","https://openalex.org/W4416034030"],"abstract_inverted_index":{"Model":[0],"merging":[1,30,45,74,102,111,144,157],"is":[2,38,50,158],"an":[3],"efficient":[4],"empowerment":[5],"technique":[6],"in":[7,54,80,113],"the":[8,16,42,55,107,139],"machine":[9,125],"learning":[10,126],"community":[11],"that":[12,97],"does":[13,23],"not":[14,24],"require":[15,25],"collection":[17],"of":[18,63,72,109,142,153],"raw":[19],"training":[20],"data":[21],"and":[22,60,76,83,85,121,145],"expensive":[26],"computation.":[27],"As":[28],"model":[29,44,73,101,110,143,156],"becomes":[31],"increasingly":[32],"prevalent":[33],"across":[34],"various":[35,81],"fields,":[36],"it":[37],"crucial":[39],"to":[40],"understand":[41],"available":[43,159],"techniques":[46,112],"comprehensively.":[47],"However,":[48],"there":[49],"a":[51,58,69,93],"significant":[52],"gap":[53],"literature":[56],"regarding":[57],"systematic":[59],"thorough":[61],"review":[62],"these":[64],"techniques.":[65],"This":[66],"survey":[67],"provides":[68],"comprehensive":[70,151],"overview":[71],"methods":[75],"theories,":[77],"their":[78],"applications":[79],"domains":[82],"settings,":[84],"future":[86,147],"research":[87,148],"directions.":[88,149],"Specifically,":[89],"we":[90,105,137],"first":[91],"propose":[92],"new":[94],"taxonomic":[95],"approach":[96],"exhaustively":[98],"discusses":[99],"existing":[100],"methods.":[103],"Secondly,":[104],"discuss":[106,146],"application":[108],"large":[114,118],"language":[115,119],"models,":[116,120],"multimodal":[117],"more":[122],"than":[123],"ten":[124],"subfields,":[127],"including":[128],"continual":[129],"learning,":[130,132,134],"multi-task":[131],"few-shot":[133],"etc.":[135],"Finally,":[136],"highlight":[138],"remaining":[140],"challenges":[141],"A":[150],"list":[152],"papers":[154],"about":[155],"at":[160],"https://github.com/EnnengYang/Awesome-Model-Merging-Methods-Theories-Applications.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2024-10-19T00:00:00"}