{"id":"https://openalex.org/W4403791424","doi":"https://doi.org/10.1145/3664647.3689171","title":"From Multimodal LLM to Human-level AI: Modality, Instruction, Reasoning and Beyond","display_name":"From Multimodal LLM to Human-level AI: Modality, Instruction, Reasoning and Beyond","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791424","doi":"https://doi.org/10.1145/3664647.3689171"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3689171","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3689171","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/A5055815455","display_name":"Hao Fei","orcid":null},"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":"Hao Fei","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-3026-6347","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089900108","display_name":"Xiangtai Li","orcid":"https://orcid.org/0000-0002-0550-8247"},"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":"Xiangtai Li","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-0550-8247","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100448792","display_name":"Haotian Liu","orcid":"https://orcid.org/0000-0001-7939-9242"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haotian Liu","raw_affiliation_strings":["University of Wisconsin-Madison, Wisconsin, USA"],"raw_orcid":"https://orcid.org/0000-0001-7939-9242","affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Wisconsin, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001943044","display_name":"Fuxiao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fuxiao Liu","raw_affiliation_strings":["University of Maryland, College Park, College Park, USA"],"raw_orcid":"https://orcid.org/0009-0009-4662-2810","affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, College Park, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070962435","display_name":"Zhuosheng Zhang","orcid":"https://orcid.org/0000-0002-4183-3645"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuosheng Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4183-3645","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042324027","display_name":"Hanwang Zhang","orcid":"https://orcid.org/0000-0001-7374-8739"},"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":"Hanwang Zhang","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7374-8739","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100381753","display_name":"Shuicheng Yan","orcid":"https://orcid.org/0000-0001-8906-3777"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuicheng Yan","raw_affiliation_strings":["Skywork AI, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-8906-3777","affiliations":[{"raw_affiliation_string":"Skywork AI, Singapore, Singapore","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11289","last_page":"11291"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9958000183105469,"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/T10759","display_name":"Translation Studies and Practices","score":0.9894999861717224,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7697316408157349},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6636316776275635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43747520446777344}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7697316408157349},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6636316776275635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43747520446777344}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3689171","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3689171","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":[{"score":0.5099999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2892181857","https://openalex.org/W2963224792","https://openalex.org/W4221143046","https://openalex.org/W4225323055","https://openalex.org/W4296605665","https://openalex.org/W4313591130","https://openalex.org/W4385570088","https://openalex.org/W4385571452","https://openalex.org/W4386076027","https://openalex.org/W4402753940","https://openalex.org/W6812380799"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Artificial":[0],"intelligence":[1],"(AI)":[2],"encompasses":[3],"knowledge":[4],"acquisition":[5],"and":[6,16,33,66,79,89],"real-world":[7],"grounding":[8],"across":[9],"various":[10],"modalities,":[11],"including":[12],"language,":[13],"visual,":[14],"auditory,":[15],"sensory":[17],"data.":[18],"Multimodal":[19],"large":[20],"language":[21],"models":[22],"(MLLMs)":[23],"have":[24],"thus":[25],"recently":[26],"garnered":[27],"growing":[28],"interest":[29],"in":[30,54],"both":[31],"academia":[32],"industry,":[34],"showing":[35],"an":[36],"unprecedented":[37],"trend":[38],"to":[39,46],"achieve":[40],"human-level":[41],"AI.":[42],"This":[43],"tutorial":[44],"aims":[45],"deliver":[47],"a":[48],"comprehensive":[49],"review":[50],"of":[51,69],"cutting-edge":[52],"research":[53],"MLLMs,":[55],"focusing":[56],"on":[57],"three":[58],"key":[59,77],"areas:":[60],"MLLM":[61],"architecture":[62],"design,":[63],"instructional":[64],"learning,":[65],"multimodal":[67],"reasoning":[68],"MLLMs.":[70],"We":[71],"will":[72,91],"explore":[73],"technical":[74],"advancements,":[75],"synthesize":[76],"challenges,":[78],"discuss":[80],"potential":[81],"avenues":[82],"for":[83],"future":[84],"research.":[85],"All":[86],"the":[87],"resources":[88],"materials":[90],"be":[92],"made":[93],"available":[94],"online.":[95],"https://mllm2024.github.io/ACM-MM2024":[96]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
