{"id":"https://openalex.org/W4387968365","doi":"https://doi.org/10.1145/3581783.3612665","title":"mPLUG-Octopus: The Versatile Assistant Empowered by A Modularized End-to-End Multimodal LLM","display_name":"mPLUG-Octopus: The Versatile Assistant Empowered by A Modularized End-to-End Multimodal LLM","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968365","doi":"https://doi.org/10.1145/3581783.3612665"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612665","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612665","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st 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/A5005965903","display_name":"Qinghao Ye","orcid":"https://orcid.org/0000-0002-7977-5540"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qinghao Ye","raw_affiliation_strings":["DAMO Academy, Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7977-5540","affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066544410","display_name":"Haiyang Xu","orcid":"https://orcid.org/0000-0001-9442-5912"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiyang Xu","raw_affiliation_strings":["DAMO Academy, Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9442-5912","affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100452477","display_name":"Ming Yan","orcid":"https://orcid.org/0000-0003-4959-8878"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Yan","raw_affiliation_strings":["DAMO Academy, Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4959-8878","affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084769712","display_name":"Chenlin Zhao","orcid":"https://orcid.org/0009-0009-1532-9451"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenlin Zhao","raw_affiliation_strings":["DAMO Academy, Alibaba Group &amp; Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-1532-9451","affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group &amp; Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I45928872","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018357502","display_name":"Junyang Wang","orcid":"https://orcid.org/0000-0002-3204-6607"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyang Wang","raw_affiliation_strings":["DAMO Academy, Alibaba Group &amp; Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3204-6607","affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group &amp; Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I45928872","https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083991825","display_name":"Xiaoshan Yang","orcid":"https://orcid.org/0000-0001-5453-9755"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoshan Yang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5453-9755","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329266","display_name":"Ji Zhang","orcid":"https://orcid.org/0000-0002-3835-7975"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji Zhang","raw_affiliation_strings":["DAMO Academy, Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3835-7975","affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101488344","display_name":"Fei Huang","orcid":"https://orcid.org/0000-0002-3709-5053"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Huang","raw_affiliation_strings":["DAMO Academy, Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3709-5053","affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023834030","display_name":"Jitao Sang","orcid":"https://orcid.org/0000-0002-0699-3205"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jitao Sang","raw_affiliation_strings":["Beijing Jiaotong University &amp; Beijing Peng Cheng Lab, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0699-3205","affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University &amp; Beijing Peng Cheng Lab, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022636178","display_name":"Changsheng Xu","orcid":"https://orcid.org/0000-0001-8343-9665"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changsheng Xu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8343-9665","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5005965903"],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":0.5112,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72242274,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"9365","last_page":"9367"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9973000288009644,"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/T12031","display_name":"Speech and dialogue systems","score":0.9936000108718872,"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/octopus","display_name":"octopus (software)","score":0.7910935282707214},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7512496709823608},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.6588175892829895},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6352807283401489},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5831143260002136},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5493643879890442},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5224001407623291},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3230676054954529},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11738920211791992},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.08365848660469055}],"concepts":[{"id":"https://openalex.org/C2779205690","wikidata":"https://www.wikidata.org/wiki/Q7077081","display_name":"octopus (software)","level":2,"score":0.7910935282707214},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7512496709823608},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.6588175892829895},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6352807283401489},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5831143260002136},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5493643879890442},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5224001407623291},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3230676054954529},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11738920211791992},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.08365848660469055},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612665","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612665","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6499999761581421}],"awards":[{"id":"https://openalex.org/G8434150956","display_name":null,"funder_award_id":"61832002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W4367367040"],"related_works":["https://openalex.org/W4401932566","https://openalex.org/W3092465102","https://openalex.org/W2002595366","https://openalex.org/W2074891905","https://openalex.org/W4393356534","https://openalex.org/W2525321787","https://openalex.org/W3180040367","https://openalex.org/W2961534621","https://openalex.org/W1974879511","https://openalex.org/W1965046275"],"abstract_inverted_index":{"Inspired":[0],"by":[1],"the":[2,69],"recent":[3],"developments":[4],"of":[5,44,88],"large":[6],"language":[7],"models":[8],"(LLMs),":[9],"we":[10],"propose":[11],"mPLUG-Octopus,":[12],"a":[13,41,58,85],"versatile":[14],"conversational":[15,120],"assistant":[16,121],"designed":[17],"to":[18,94,129],"provide":[19],"users":[20,98,110],"with":[21,57,97],"coherent,":[22],"engaging,":[23],"and":[24,31,52,79,102,116],"helpful":[25],"interaction":[26],"experiences":[27],"in":[28,104,111],"both":[29],"text-only":[30],"multi-modal":[32,53],"scenarios.":[33],"Unlike":[34],"traditional":[35],"pipeline":[36],"chatting":[37],"systems,":[38],"mPLUG-Octopus":[39,75],"offers":[40],"diverse":[42],"range":[43,87],"creative":[45],"capabilities":[46],"including":[47],"open-domain":[48,80,100],"QA,":[49],"multi-turn":[50,105],"chatting,":[51],"creation,":[54],"all":[55],"built":[56],"unified":[59],"multimodal":[60,72],"LLM":[61,73],"without":[62],"relying":[63],"on":[64,99,126],"any":[65],"external":[66],"API.":[67],"With":[68],"modularized":[70],"end-to-end":[71],"technology,":[74],"efficiently":[76],"facilitates":[77],"engaging":[78],"conversation":[81],"experience.":[82],"It":[83,107],"exhibits":[84],"wide":[86],"uni/multi-modal":[89],"elemental":[90],"capabilities,":[91],"enabling":[92],"it":[93],"seamlessly":[95],"communicate":[96],"topics":[101],"engage":[103],"conversations.":[106],"also":[108,123],"assists":[109],"accomplishing":[112],"various":[113],"content":[114],"creation":[115],"application":[117],"tasks.":[118],"Our":[119],"can":[122],"be":[124],"deployed":[125],"smart":[127],"hardware":[128],"drive":[130],"advanced":[131],"AIGC":[132],"applications.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
