{"id":"https://openalex.org/W4415708847","doi":"https://doi.org/10.1109/icme59968.2025.11210035","title":"Reinforced Model Merging","display_name":"Reinforced Model Merging","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708847","doi":"https://doi.org/10.1109/icme59968.2025.11210035"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210035","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210035","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5009352908","display_name":"Jiaqi Han","orcid":"https://orcid.org/0000-0003-4600-9337"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqi Han","raw_affiliation_strings":["Zhejiang University,College of Computer Science and Technology,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Computer Science and Technology,Hangzhou,China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113381545","display_name":"Jingwen Ye","orcid":"https://orcid.org/0009-0006-5860-2655"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jingwen Ye","raw_affiliation_strings":["National University of Singapore,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090854835","display_name":"Shunyu Liu","orcid":"https://orcid.org/0000-0003-0584-9129"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shunyu Liu","raw_affiliation_strings":["Nanyang Technological University,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102996603","display_name":"Haofei Zhang","orcid":"https://orcid.org/0000-0003-3247-6356"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haofei Zhang","raw_affiliation_strings":["Zhejiang University,College of Computer Science and Technology,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Computer Science and Technology,Hangzhou,China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047371218","display_name":"Jie Song","orcid":"https://orcid.org/0000-0003-3671-6521"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Song","raw_affiliation_strings":["Zhejiang University,School of Software Technology,Ningbo,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,School of Software Technology,Ningbo,China","institution_ids":["https://openalex.org/I109935558","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043914348","display_name":"Zunlei Feng","orcid":"https://orcid.org/0000-0001-8640-8434"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zunlei Feng","raw_affiliation_strings":["Zhejiang University,School of Software Technology,Ningbo,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,School of Software Technology,Ningbo,China","institution_ids":["https://openalex.org/I109935558","https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026532752","display_name":"Mingli Song","orcid":"https://orcid.org/0000-0003-2621-6048"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingli Song","raw_affiliation_strings":["Zhejiang University,College of Computer Science and Technology,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Computer Science and Technology,Hangzhou,China","institution_ids":["https://openalex.org/I168879160"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"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":"1","last_page":"6"},"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":0.34709998965263367,"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":0.34709998965263367,"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":0.14800000190734863,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.09510000050067902,"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/bottleneck","display_name":"Bottleneck","score":0.8323000073432922},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5705999732017517},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5455999970436096},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.46709999442100525},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4431999921798706},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4009999930858612},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.38589999079704285}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8323000073432922},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7476000189781189},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5705999732017517},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5455999970436096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4684999883174896},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.46709999442100525},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4431999921798706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4207000136375427},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4009999930858612},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.38589999079704285},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3765999972820282},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.25060001015663147},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11210035","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210035","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2251818205","https://openalex.org/W2473930607","https://openalex.org/W2692059227","https://openalex.org/W2951360122","https://openalex.org/W2963777504","https://openalex.org/W2971068072","https://openalex.org/W2996848635","https://openalex.org/W3127215335","https://openalex.org/W3194676777","https://openalex.org/W4283816018","https://openalex.org/W4313144836","https://openalex.org/W4362496263","https://openalex.org/W4379053908","https://openalex.org/W4406844855"],"related_works":[],"abstract_inverted_index":{"The":[0],"success":[1],"of":[2,32,145],"large":[3],"language":[4],"models":[5],"has":[6],"garnered":[7],"widespread":[8],"attention":[9],"for":[10,65,97],"model":[11,19],"merging":[12,66,74,81],"techniques,":[13],"especially":[14],"training-free":[15],"methods":[16],"which":[17,58],"combine":[18],"capabilities":[20],"within":[21],"the":[22,79,91,106,111,114,143,146],"parameter":[23],"space.":[24],"However,":[25],"two":[26],"challenges":[27],"remain:":[28],"(1)":[29],"uniform":[30],"treatment":[31],"all":[33],"parameters":[34],"leads":[35],"to":[36,71,77,123],"performance":[37,133],"degradation;":[38],"(2)":[39],"search-based":[40],"algorithms":[41],"are":[42],"often":[43],"inefficient.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,109],"present":[49],"an":[50,60],"innovative":[51],"framework":[52],"termed":[53],"Reinforced":[54],"Model":[55],"Merging":[56],"(RMM),":[57],"encompasses":[59],"environment":[61],"and":[62,137,140],"agent":[63],"tailored":[64],"tasks.":[67],"These":[68],"components":[69],"interact":[70],"execute":[72],"layer-wise":[73],"actions,":[75],"aiming":[76],"search":[78],"optimal":[80],"architecture.":[82],"Notably,":[83],"RMM":[84,120,130],"operates":[85],"without":[86],"any":[87],"gradient":[88],"computations":[89],"on":[90],"original":[92],"models,":[93],"rendering":[94],"it":[95],"feasible":[96],"edge":[98],"devices.":[99],"Furthermore,":[100],"by":[101,121],"utilizing":[102],"data":[103],"subsets":[104],"during":[105],"evaluation":[107],"process,":[108],"addressed":[110],"bottleneck":[112],"in":[113],"reward":[115],"feedback":[116],"phase,":[117],"thereby":[118],"accelerating":[119],"up":[122],"100":[124],"times.":[125],"Extensive":[126],"experiments":[127],"demonstrate":[128],"that":[129],"achieves":[131],"state-of-the-art":[132],"across":[134],"various":[135],"vision":[136],"NLP":[138],"datasets":[139],"effectively":[141],"overcomes":[142],"limitations":[144],"existing":[147],"baseline":[148],"methods.":[149],"Our":[150],"code":[151],"is":[152],"available":[153],"at":[154],"https://github.com/WuDiHJQ/Reinforced-Model-Merging.":[155]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}