{"id":"https://openalex.org/W4405627210","doi":"https://doi.org/10.1109/iccv51701.2025.01579","title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","display_name":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405627210","doi":"https://doi.org/10.1109/iccv51701.2025.01579"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01579","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01579","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.14164","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055545928","display_name":"Shengbang Tong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengbang Tong","raw_affiliation_strings":["FAIR, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"David Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Fan","raw_affiliation_strings":["FAIR, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiachen Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiachen Zhu","raw_affiliation_strings":["FAIR, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115560962","display_name":"Yunyang Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunyang Xiong","raw_affiliation_strings":["Meta Reality Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016095713","display_name":"Xinlei Chen","orcid":"https://orcid.org/0000-0001-8271-5023"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinlei Chen","raw_affiliation_strings":["FAIR, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109576489","display_name":"Koustuv Sinha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Koustuv Sinha","raw_affiliation_strings":["FAIR, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089819604","display_name":"Michael Rabbat","orcid":"https://orcid.org/0000-0003-0536-7904"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Rabbat","raw_affiliation_strings":["FAIR, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001226970","display_name":"Yann LeCun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yann LeCun","raw_affiliation_strings":["FAIR, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102416863","display_name":"Saining Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saining Xie","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100452089","display_name":"Zhuang Liu","orcid":"https://orcid.org/0000-0001-6395-0212"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuang Liu","raw_affiliation_strings":["FAIR, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17001","last_page":"17012"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9794999957084656,"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/T12031","display_name":"Speech and dialogue systems","score":0.9794999957084656,"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/multimodal-therapy","display_name":"Multimodal therapy","score":0.4126623570919037},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3928642272949219},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.34779471158981323},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.23665007948875427},{"id":"https://openalex.org/keywords/internal-medicine","display_name":"Internal medicine","score":0.1283951699733734}],"concepts":[{"id":"https://openalex.org/C4441509","wikidata":"https://www.wikidata.org/wiki/Q6418787","display_name":"Multimodal therapy","level":2,"score":0.4126623570919037},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3928642272949219},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.34779471158981323},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.23665007948875427},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.1283951699733734}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01579","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01579","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2412.14164","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.14164","pdf_url":"https://arxiv.org/pdf/2412.14164","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.14164","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.14164","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.14164","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.14164","pdf_url":"https://arxiv.org/pdf/2412.14164","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7688596227","display_name":null,"funder_award_id":"RS-2024-00457882","funder_id":"https://openalex.org/F4320322428","funder_display_name":"Norske Skog"}],"funders":[{"id":"https://openalex.org/F4320322428","display_name":"Norske Skog","ror":"https://ror.org/00etk3t37"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4405627210.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W2948807893","https://openalex.org/W2899084033","https://openalex.org/W2778153218","https://openalex.org/W2748952813","https://openalex.org/W1531601525","https://openalex.org/W4391375266","https://openalex.org/W2078814861","https://openalex.org/W2527526854","https://openalex.org/W1976181487"],"abstract_inverted_index":{"In":[0,142],"this":[1],"work,":[2],"we":[3,103,127],"propose":[4],"Visual-Predictive":[5],"Instruction":[6],"Tuning":[7],"(VPiT)":[8],"-":[9],"a":[10,21,82,95,191],"simple":[11,193],"and":[12,37,49,59,89,106,132,140,151,158,188],"effective":[13],"extension":[14],"to":[15,24,44,108,115,184],"visual":[16,38,51,77,87,138,143,186],"instruction":[17,194],"tuning":[18,195],"that":[19,171,179],"enables":[20],"pretrained":[22],"LLM":[23,43,156],"quickly":[25],"morph":[26],"into":[27],"an":[28,42,64],"unified":[29],"autoregressive":[30],"model":[31,131],"capable":[32],"of":[33,57,74,85,98],"generating":[34],"both":[35,116,137,185],"text":[36,47,60],"tokens.":[39],"VPiT":[40],"teaches":[41],"predict":[45],"discrete":[46],"tokens":[48,52],"continuous":[50],"from":[53,155],"any":[54],"input":[55],"sequence":[56],"image":[58],"data":[61,113],"curated":[62],"in":[63],"instruction-following":[65],"format.":[66],"Our":[67,168],"empirical":[68],"investigation":[69],"reveals":[70],"several":[71],"intriguing":[72],"properties":[73],"VPiT:":[75],"(1)":[76],"generation":[78,99,107,121,166,189],"ability":[79],"emerges":[80],"as":[81],"natural":[83],"byproduct":[84],"improved":[86],"understanding,":[88],"can":[90,146,180],"be":[91,109,181],"unlocked":[92],"efficiently":[93,182],"with":[94,190],"small":[96],"amount":[97],"data;":[100],"(2)":[101],"while":[102],"find":[104],"understanding":[105,112,139,187],"mutually":[110],"beneficial,":[111],"contributes":[114],"capabilities":[117,178],"more":[118],"effectively":[119],"than":[120],"data.":[122],"Building":[123],"upon":[124],"these":[125],"findings,":[126],"train":[128],"our":[129],"MetaMorph":[130,145],"achieve":[133],"competitive":[134],"performance":[135],"on":[136],"generation.":[141],"generation,":[144],"leverage":[147],"the":[148],"world":[149],"knowledge":[150],"reasoning":[152],"abilities":[153],"gained":[154],"pretraining,":[157],"overcome":[159],"common":[160],"failure":[161],"modes":[162],"exhibited":[163],"by":[164],"other":[165],"models.":[167],"results":[169],"suggest":[170],"LLMs":[172],"may":[173],"have":[174],"strong":[175],"\"prior\"":[176],"vision":[177],"adapted":[183],"relatively":[192],"process.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}