{"id":"https://openalex.org/W4412888851","doi":"https://doi.org/10.18653/v1/2025.findings-acl.143","title":"Progressive LoRA for Multimodal Continual Instruction Tuning","display_name":"Progressive LoRA for Multimodal Continual Instruction Tuning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888851","doi":"https://doi.org/10.18653/v1/2025.findings-acl.143"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.143","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.143","pdf_url":"https://aclanthology.org/2025.findings-acl.143.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.143.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039143276","display_name":"Yahan Yu","orcid":"https://orcid.org/0000-0003-1610-1167"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yahan Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119204572","display_name":"Duzhen Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duzhen Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002346706","display_name":"Yong Ren","orcid":"https://orcid.org/0000-0003-0312-9371"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yong Ren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104174550","display_name":"Xuanle Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuanle Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009070585","display_name":"Xiuyi Chen","orcid":"https://orcid.org/0000-0002-9351-4160"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiuyi Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102757632","display_name":"Chenhui Chu","orcid":"https://orcid.org/0000-0001-9848-6384"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenhui Chu","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":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2779","last_page":"2796"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9573000073432922,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9573000073432922,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9498000144958496,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9039999842643738,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6251856088638306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6251856088638306}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.143","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.143","pdf_url":"https://aclanthology.org/2025.findings-acl.143.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.143","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.143","pdf_url":"https://aclanthology.org/2025.findings-acl.143.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888851.pdf","grobid_xml":"https://content.openalex.org/works/W4412888851.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Multimodal":[0,6],"Continual":[1],"Instruction":[2],"Tuning":[3],"(MCIT)":[4],"empowers":[5],"Large":[7],"Language":[8],"Models":[9],"(MLLMs)":[10],"to":[11,13,39,54,63,91],"adapt":[12],"everevolving":[14],"requirements":[15],"without":[16],"continuous":[17],"costly":[18],"retraining.However,":[19],"MCIT":[20,148],"faces":[21],"challenges":[22],"in":[23],"mitigating":[24],"Catastrophic":[25],"Forgetting":[26],"(CF)":[27],"and":[28,37,66,81,110,135],"enhancing":[29],"Knowledge":[30],"Transfer":[31],"(KT).Existing":[32],"works":[33],"combine":[34],"Mixture-of-Expert":[35],"(MoE)":[36],"LoRA":[38,48,72,79,85],"address":[40],"these.However,":[41],"using":[42],"a":[43,77,83,126,136],"fixed":[44],"number":[45],"of":[46,57],"shared":[47],"blocks":[49],"across":[50],"tasks":[51],"can":[52],"lead":[53],"the":[55,70,115,130,140,146],"overwriting":[56],"acquired":[58,105],"knowledge,":[59],"making":[60],"MLLMs":[61],"harder":[62],"handle":[64],"CF":[65],"KT.Therefore,":[67],"we":[68,124],"propose":[69],"Progressive":[71],"framework":[73],"(ProgLoRA),":[74],"which":[75],"contains":[76],"progressive":[78],"pool":[80],"trains":[82],"new":[84],"block":[86],"for":[87,102,113,129,139],"each":[88],"incremental":[89],"task":[90,109,111],"reduce":[92],"knowledge":[93,106],"interference.Specifically,":[94],"ProgLoRA":[95,128,138,152],"has":[96],"two":[97],"key":[98],"mechanisms:":[99],"task-aware":[100],"allocation":[101],"effectively":[103],"leveraging":[104],"at":[107],"current":[108],"recall":[112],"realigning":[114],"model":[116],"with":[117],"learned":[118],"tasks.Additionally,":[119],"considering":[120],"different":[121],"application":[122],"scenarios,":[123],"design":[125],"static":[127],"more":[131,141],"idealized":[132],"basic":[133],"setting":[134],"dynamic":[137],"realistic":[142],"challenging":[143],"setting.Experiments":[144],"on":[145],"latest":[147],"benchmark":[149],"demonstrate":[150],"that":[151],"outperforms":[153],"existing":[154],"approaches.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}