{"id":"https://openalex.org/W4403791489","doi":"https://doi.org/10.1145/3664647.3689177","title":"Multimodal Large Language Models and Tunings: Vision, Language, Sensors, Audio, and Beyond","display_name":"Multimodal Large Language Models and Tunings: Vision, Language, Sensors, Audio, and Beyond","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791489","doi":"https://doi.org/10.1145/3664647.3689177"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3689177","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3689177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5084419965","display_name":"Soyeon Caren Han","orcid":"https://orcid.org/0000-0002-1948-6819"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Soyeon Caren Han","raw_affiliation_strings":["University of Melbourne, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0002-1948-6819","affiliations":[{"raw_affiliation_string":"University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010425049","display_name":"Feiqi Cao","orcid":"https://orcid.org/0000-0002-4910-5925"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Feiqi Cao","raw_affiliation_strings":["University of Sydney, University of Sydney, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4910-5925","affiliations":[{"raw_affiliation_string":"University of Sydney, University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085086413","display_name":"Josiah Poon","orcid":"https://orcid.org/0000-0003-3371-8628"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Josiah Poon","raw_affiliation_strings":["University of Sydney, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3371-8628","affiliations":[{"raw_affiliation_string":"University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026648049","display_name":"Roberto Navigli","orcid":"https://orcid.org/0000-0003-3831-9706"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Roberto Navigli","raw_affiliation_strings":["Sapienza University of Rome, Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0003-3831-9706","affiliations":[{"raw_affiliation_string":"Sapienza University of Rome, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.663,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.91281635,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"11294","last_page":"11295"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9887999892234802,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7200382947921753},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.44547039270401},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3721305727958679},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34665101766586304},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3408958613872528},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3226664662361145},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.18468546867370605}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7200382947921753},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.44547039270401},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3721305727958679},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34665101766586304},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3408958613872528},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3226664662361145},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.18468546867370605}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3689177","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3689177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5600000023841858,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W3213351348","https://openalex.org/W4285605356"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W3204019825"],"abstract_inverted_index":{"This":[0,109],"tutorial":[1,69,110],"explores":[2],"recent":[3],"advancements":[4],"in":[5],"multimodal":[6,40,56,76,97,125,144],"pretrained":[7,59,145],"and":[8,14,24,42,58,65,79,105,116,121,146,150],"large":[9,77,147],"models,":[10,60,98,149],"capable":[11],"of":[12,31,35,39,75,142],"integrating":[13],"processing":[15],"diverse":[16],"data":[17],"forms":[18],"such":[19],"as":[20],"text,":[21],"images,":[22],"audio,":[23],"video.":[25],"Participants":[26],"will":[27,52,70,91],"gain":[28],"an":[29],"understanding":[30,143],"the":[32,37,43,54,68,73,119,131],"foundational":[33],"concepts":[34],"multimodality,":[36],"evolution":[38],"research,":[41],"key":[44],"technical":[45],"challenges":[46],"addressed":[47],"by":[48],"these":[49],"models.":[50],"We":[51],"cover":[53],"latest":[55],"datasets":[57],"including":[61],"those":[62],"beyond":[63],"vision":[64],"language.":[66],"Additionally,":[67],"delve":[71],"into":[72],"intricacies":[74],"models":[78],"instruction":[80],"tuning":[81,152],"strategies":[82],"to":[83,112,123],"optimise":[84],"performance":[85],"for":[86,134],"specific":[87],"tasks.":[88],"Hands-on":[89],"laboratories":[90],"offer":[92],"practical":[93],"experience":[94],"with":[95,118,139],"state-of-the-art":[96],"demonstrating":[99],"real-world":[100],"applications":[101],"like":[102],"visual":[103,106],"storytelling":[104],"question":[107],"answering.":[108],"aims":[111],"equip":[113],"researchers,":[114],"practitioners,":[115],"newcomers":[117],"knowledge":[120],"skills":[122],"leverage":[124],"AI.":[126],"ACM":[127],"Multimedia":[128],"2024":[129],"is":[130],"ideal":[132],"venue":[133],"this":[135],"tutorial,":[136],"aligning":[137],"perfectly":[138],"our":[140],"goal":[141],"language":[148],"their":[151],"mechanisms.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}