{"id":"https://openalex.org/W7168343341","doi":"https://doi.org/10.48550/arxiv.2607.12112","title":"Continual Learning with Elastic Regularization and Synthetic Replay for Federated MLLM Fine-Tuning","display_name":"Continual Learning with Elastic Regularization and Synthetic Replay for Federated MLLM Fine-Tuning","publication_year":2026,"publication_date":"2026-07-13","ids":{"openalex":"https://openalex.org/W7168343341","doi":"https://doi.org/10.48550/arxiv.2607.12112"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.12112","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.12112","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.2607.12112","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140751939","display_name":"Jing Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140825335","display_name":"Chenxuanyin Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zou, Chenxuanyin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140846649","display_name":"Jiayang Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Jiayang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140826688","display_name":"Gaoyun Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang, Gaoyun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140800326","display_name":"Chengfang Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Chengfang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140806770","display_name":"Yan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140887702","display_name":"Zhenchao Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Zhenchao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5140870190","display_name":"Bo Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Bo","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.5773000121116638,"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":0.5773000121116638,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.06639999896287918,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.05730000138282776,"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/tuple","display_name":"Tuple","score":0.43650001287460327},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.41830000281333923},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.41370001435279846},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.41040000319480896},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.3928000032901764},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.387800008058548},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.36419999599456787},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.33320000767707825},{"id":"https://openalex.org/keywords/microservices","display_name":"Microservices","score":0.33250001072883606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8553000092506409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5012000203132629},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.43650001287460327},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.41850000619888306},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.41830000281333923},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.41370001435279846},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.41040000319480896},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38659998774528503},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C2778505942","wikidata":"https://www.wikidata.org/wiki/Q18344624","display_name":"Microservices","level":3,"score":0.33250001072883606},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.28209999203681946},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2766999900341034},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.12112","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.12112","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.2607.12112","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.12112","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":[{"score":0.5586959719657898,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Federated":[0,76],"fine-tuning":[1],"of":[2,65],"Multimodal":[3,78],"Large":[4],"Language":[5],"Models":[6],"(MLLMs)":[7],"across":[8,38,202],"distributed":[9],"networks":[10],"enables":[11,198],"privacy-sensitive":[12],"adaptation":[13,201],"to":[14,138],"evolving":[15],"data":[16,127,148],"streams,":[17],"yet":[18],"a":[19,81,132],"fundamental":[20],"obstacle":[21],"prevents":[22],"robust":[23,199],"deployment":[24],"in":[25,55],"dynamic":[26],"environments:":[27],"catastrophic":[28],"forgetting,":[29],"wherein":[30],"sequential":[31],"task":[32],"updates":[33,162],"erase":[34],"previously":[35],"acquired":[36],"knowledge":[37,67],"visual,":[39],"linguistic,":[40],"and":[41,115,159,170,190],"cross-modal":[42,116],"representations.":[43],"Addressing":[44],"this":[45],"challenge":[46],"is":[47],"especially":[48],"critical":[49],"for":[50,109],"autonomous":[51],"networked":[52,204],"AI":[53,205],"operating":[54],"safety-sensitive":[56],"domains,":[57],"such":[58],"as":[59],"content":[60],"moderation,":[61],"where":[62],"reliable":[63],"retention":[64],"prior":[66],"underpins":[68],"system":[69],"integrity.":[70],"To":[71],"overcome":[72],"this,":[73],"we":[74],"propose":[75],"Continual":[77],"Learning":[79],"(FedCMM),":[80],"framework":[82],"that":[83,182,194],"embeds":[84],"continual-learning":[85],"safeguards":[86],"into":[87],"the":[88,97,110,126,151,172],"federated":[89],"optimization":[90,197],"loop":[91],"at":[92],"three":[93],"complementary":[94],"levels.":[95],"At":[96,125,150],"parameter":[98],"level,":[99,128,153],"modality-aware":[100,196],"elastic":[101],"weight":[102],"consolidation":[103],"computes":[104],"separate":[105],"Fisher":[106],"information":[107],"matrices":[108],"vision":[111],"encoder,":[112],"language":[113],"backbone,":[114],"projector,":[117],"providing":[118],"granular,":[119],"asymmetry-aware":[120],"protection":[121],"against":[122],"modality-specific":[123],"forgetting.":[124],"each":[129],"client":[130,161],"trains":[131],"lightweight":[133],"local":[134],"generative":[135],"replay":[136,143],"module":[137],"synthesize":[139],"raw-data-free":[140],"embedding-level":[141],"multimodal":[142],"tuples":[144],"without":[145],"any":[146],"raw":[147],"sharing.":[149],"aggregation":[152,156],"Task-similarity-aware":[154],"gradient":[155,164],"autonomously":[157],"filters":[158],"reweights":[160],"by":[163],"cosine":[165],"similarity,":[166],"suppressing":[167],"conflicting":[168],"directions":[169],"stabilizing":[171],"global":[173],"learning":[174],"trajectory.":[175],"Extensive":[176],"experiments":[177],"on":[178,188],"two":[179],"benchmarks":[180],"demonstrate":[181],"FedCMM":[183],"consistently":[184],"outperforms":[185],"recent":[186],"baselines":[187],"accuracy":[189],"backward":[191],"transfer,":[192],"confirming":[193],"holistic,":[195],"evolutive":[200],"heterogeneous":[203],"deployments.":[206]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-16T00:00:00"}