{"id":"https://openalex.org/W4378768739","doi":"https://doi.org/10.48550/arxiv.2305.17216","title":"Generating Images with Multimodal Language Models","display_name":"Generating Images with Multimodal Language Models","publication_year":2023,"publication_date":"2023-05-26","ids":{"openalex":"https://openalex.org/W4378768739","doi":"https://doi.org/10.48550/arxiv.2305.17216"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2305.17216","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.17216","pdf_url":"https://arxiv.org/pdf/2305.17216","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.17216","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009550511","display_name":"Jing Yu Koh","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Koh, Jing Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003637850","display_name":"Daniel Fried","orcid":"https://orcid.org/0000-0002-5327-2558"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fried, Daniel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5071983998","display_name":"Ruslan Salakhutdinov","orcid":"https://orcid.org/0000-0002-3752-2756"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Salakhutdinov, Ruslan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009550511"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":39,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9570000171661377,"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":0.7847219705581665},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6534522175788879},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6290994882583618},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6158947348594666},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5817950963973999},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5732347369194031},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.527554452419281},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.45052865147590637},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4308660924434662},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42144277691841125},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34324222803115845},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3427247107028961}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7847219705581665},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6534522175788879},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6290994882583618},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6158947348594666},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5817950963973999},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5732347369194031},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.527554452419281},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45052865147590637},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4308660924434662},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42144277691841125},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34324222803115845},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3427247107028961},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2305.17216","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.17216","pdf_url":"https://arxiv.org/pdf/2305.17216","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"doi:10.48550/arxiv.2305.17216","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2305.17216","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2305.17216","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.17216","pdf_url":"https://arxiv.org/pdf/2305.17216","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6800000071525574}],"awards":[{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G5103598966","display_name":null,"funder_award_id":"FA87502321015","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G6353494076","display_name":null,"funder_award_id":"N000142312368","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320307791","display_name":"Cisco Systems","ror":"https://ror.org/03yt1ez60"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2183306018","https://openalex.org/W2345479200","https://openalex.org/W2142795561","https://openalex.org/W2055243143","https://openalex.org/W2849310602","https://openalex.org/W4379251913"],"abstract_inverted_index":{"We":[0],"propose":[1,72],"a":[2,28,146,163,179],"method":[3],"to":[4,57,77,81,105,133,152,185],"fuse":[5],"frozen":[6],"text-only":[7],"large":[8],"language":[9,188],"models":[10,122,209],"(LLMs)":[11],"with":[12,125,162],"pre-trained":[13],"image":[14,34,37,53,60,69,135,143],"encoder":[15],"and":[16,39,54,127,149,195,201],"decoder":[17],"models,":[18,102],"by":[19],"mapping":[20,75,88],"between":[21],"their":[22],"embedding":[23,97],"spaces.":[24],"Our":[25,117,176],"model":[26,138,177],"demonstrates":[27],"wide":[29],"suite":[30],"of":[31,48,93,99,111,142,173,182],"multimodal":[32,40,187],"capabilities:":[33],"retrieval,":[35],"novel":[36,134],"generation,":[38,70,136],"dialogue.":[41],"Ours":[42],"is":[43,139,160],"the":[44,79,96,100,107,112,170,174],"first":[45],"approach":[46,118],"capable":[47,141],"conditioning":[49],"on":[50,68,123,169],"arbitrarily":[51],"interleaved":[52],"text":[55,94,109,203],"inputs":[56],"generate":[58,155],"coherent":[59],"(and":[61],"text)":[62],"outputs.":[63,116],"To":[64],"achieve":[65],"strong":[66,108],"performance":[67],"we":[71],"an":[73,82],"efficient":[74],"network":[76,89],"ground":[78],"LLM":[80,113],"off-the-shelf":[83],"text-to-image":[84,212],"generation":[85,121,208],"model.":[86],"This":[87,159],"translates":[90],"hidden":[91,171],"representations":[92,110,172],"into":[95],"space":[98],"visual":[101,115],"enabling":[103],"us":[104],"leverage":[106],"for":[114],"outperforms":[119],"baseline":[120],"tasks":[124,213],"longer":[126],"more":[128],"complex":[129],"language.":[130],"In":[131],"addition":[132],"our":[137],"also":[140],"retrieval":[144],"from":[145],"prespecified":[147],"dataset,":[148],"decides":[150],"whether":[151],"retrieve":[153],"or":[154],"at":[156],"inference":[157],"time.":[158],"done":[161],"learnt":[164],"decision":[165],"module":[166],"which":[167],"conditions":[168],"LLM.":[175],"exhibits":[178],"wider":[180],"range":[181],"capabilities":[183],"compared":[184],"prior":[186],"models.":[189],"It":[190],"can":[191],"process":[192],"image-and-text":[193],"inputs,":[194],"produce":[196],"retrieved":[197],"images,":[198,200],"generated":[199,202],"--":[204],"outperforming":[205],"non-LLM":[206],"based":[207],"across":[210],"several":[211],"that":[214],"measure":[215],"context":[216],"dependence.":[217]},"counts_by_year":[{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}