{"id":"https://openalex.org/W6989703290","doi":null,"title":"Building the Next Generation of Multimodal Models","display_name":"Building the Next Generation of Multimodal Models","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W6989703290"},"language":"en","primary_location":{"id":"pmh:oai:digital.lib.washington.edu:1773/51333","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1773/51333","pdf_url":"https://digital.lib.washington.edu/bitstreams/ee7993a7-4a2e-4c7f-9936-40f7c41e395c/download","source":{"id":"https://openalex.org/S4306401128","display_name":"ResearchWorks at the University of Washington (University of Washington)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I201448701","host_organization_name":"University of Washington","host_organization_lineage":["https://openalex.org/I201448701"],"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":null,"raw_type":"Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://digital.lib.washington.edu/bitstreams/ee7993a7-4a2e-4c7f-9936-40f7c41e395c/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068360032","display_name":"Gabriel Ilharco","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ilharco, Gabriel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5068360032"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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":true,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":9.999999747378752e-05,"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":0.0,"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-models","display_name":"multimodal models","score":0.9589999914169312},{"id":"https://openalex.org/keywords/data-curation","display_name":"data curation","score":0.9430000185966492},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.9020000100135803},{"id":"https://openalex.org/keywords/image-text-models","display_name":"image-text models","score":0.5070000290870667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.78329998254776},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7591000199317932},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6819000244140625},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6467000246047974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5914999842643738},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.567300021648407},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.508899986743927},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.445499986410141},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26409998536109924}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:digital.lib.washington.edu:1773/51333","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1773/51333","pdf_url":"https://digital.lib.washington.edu/bitstreams/ee7993a7-4a2e-4c7f-9936-40f7c41e395c/download","source":{"id":"https://openalex.org/S4306401128","display_name":"ResearchWorks at the University of Washington (University of Washington)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I201448701","host_organization_name":"University of Washington","host_organization_lineage":["https://openalex.org/I201448701"],"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":null,"raw_type":"Thesis"}],"best_oa_location":{"id":"pmh:oai:digital.lib.washington.edu:1773/51333","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1773/51333","pdf_url":"https://digital.lib.washington.edu/bitstreams/ee7993a7-4a2e-4c7f-9936-40f7c41e395c/download","source":{"id":"https://openalex.org/S4306401128","display_name":"ResearchWorks at the University of Washington (University of Washington)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I201448701","host_organization_name":"University of Washington","host_organization_lineage":["https://openalex.org/I201448701"],"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":null,"raw_type":"Thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6989703290.pdf","grobid_xml":"https://content.openalex.org/works/W6989703290.grobid-xml"},"referenced_works_count":118,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W1889081078","https://openalex.org/W1972420097","https://openalex.org/W2061873838","https://openalex.org/W2070983531","https://openalex.org/W2081580037","https://openalex.org/W2126204609","https://openalex.org/W2130158090","https://openalex.org/W2468328197","https://openalex.org/W2525332836","https://openalex.org/W2531542820","https://openalex.org/W2542459869","https://openalex.org/W2546241758","https://openalex.org/W2560647685","https://openalex.org/W2563399268","https://openalex.org/W2593864460","https://openalex.org/W2626967530","https://openalex.org/W2740802195","https://openalex.org/W2750384547","https://openalex.org/W2765407302","https://openalex.org/W2768404247","https://openalex.org/W2773446523","https://openalex.org/W2793333878","https://openalex.org/W2799054028","https://openalex.org/W2804935296","https://openalex.org/W2903996579","https://openalex.org/W2914666366","https://openalex.org/W2920807444","https://openalex.org/W2942810103","https://openalex.org/W2949605076","https://openalex.org/W2949650786","https://openalex.org/W2950233433","https://openalex.org/W2951940613","https://openalex.org/W2953212746","https://openalex.org/W2962933129","https://openalex.org/W2964194231","https://openalex.org/W2970971581","https://openalex.org/W2981852735","https://openalex.org/W2985940692","https://openalex.org/W2992525328","https://openalex.org/W2992604033","https://openalex.org/W2995100839","https://openalex.org/W3001279689","https://openalex.org/W3005700362","https://openalex.org/W3008526508","https://openalex.org/W3017567979","https://openalex.org/W3028351217","https://openalex.org/W3030163527","https://openalex.org/W3034251946","https://openalex.org/W3034363135","https://openalex.org/W3036224891","https://openalex.org/W3037492894","https://openalex.org/W3041133507","https://openalex.org/W3042608254","https://openalex.org/W3098033339","https://openalex.org/W3103836116","https://openalex.org/W3108907096","https://openalex.org/W3111643701","https://openalex.org/W3112486745","https://openalex.org/W3126337491","https://openalex.org/W3129576130","https://openalex.org/W3132995741","https://openalex.org/W3135099046","https://openalex.org/W3135159465","https://openalex.org/W3135367836","https://openalex.org/W3154575616","https://openalex.org/W3161821165","https://openalex.org/W3171007011","https://openalex.org/W3172942063","https://openalex.org/W3177096435","https://openalex.org/W3177900337","https://openalex.org/W3198675127","https://openalex.org/W3200668485","https://openalex.org/W3206867351","https://openalex.org/W3212456749","https://openalex.org/W3212868355","https://openalex.org/W3213454282","https://openalex.org/W3213647938","https://openalex.org/W3213758632","https://openalex.org/W3215626407","https://openalex.org/W3215698779","https://openalex.org/W4200629441","https://openalex.org/W4200634382","https://openalex.org/W4221155125","https://openalex.org/W4224952733","https://openalex.org/W4225567241","https://openalex.org/W4226037452","https://openalex.org/W4226202957","https://openalex.org/W4229009135","https://openalex.org/W4229042118","https://openalex.org/W4281384181","https://openalex.org/W4282980384","https://openalex.org/W4286562652","https://openalex.org/W4287077924","https://openalex.org/W4295689550","https://openalex.org/W4300886482","https://openalex.org/W4309217994","https://openalex.org/W4310998073","https://openalex.org/W4311000453","https://openalex.org/W4312310776","https://openalex.org/W4312629998","https://openalex.org/W4312933868","https://openalex.org/W4327810158","https://openalex.org/W4327811112","https://openalex.org/W4366390744","https://openalex.org/W4377864624","https://openalex.org/W4385572602","https://openalex.org/W4385573190","https://openalex.org/W4386075908","https://openalex.org/W4386790226","https://openalex.org/W4402264526","https://openalex.org/W6928992657","https://openalex.org/W6931203431","https://openalex.org/W7133195915","https://openalex.org/W7133216684","https://openalex.org/W7133217989","https://openalex.org/W7133230070","https://openalex.org/W7133234821"],"related_works":["https://openalex.org/W7126783933","https://openalex.org/W7155476345","https://openalex.org/W7126971085","https://openalex.org/W7126586872","https://openalex.org/W7202324722","https://openalex.org/W7110546411","https://openalex.org/W7214410209","https://openalex.org/W7126888021","https://openalex.org/W7217759033","https://openalex.org/W7126994194"],"abstract_inverted_index":{"One":[0],"of":[1,5,13,19,32,42,98,151,180],"the":[2,29,60,96,117,149,165,174,177],"fundamental":[3],"goals":[4],"machine":[6],"learning":[7],"is":[8],"to":[9,44,87,155],"create":[10],"systems":[11],"capable":[12],"processing":[14],"data":[15],"from":[16],"a":[17,39,65,76,113,144],"variety":[18],"modalities":[20],"such":[21],"as":[22],"images":[23],"and":[24,48,90,136],"text.":[25],"I":[26,63,120,142],"argue":[27],"that":[28,51,108],"next":[30,178],"generation":[31,179],"multimodal":[33,71,181],"models":[34,56,126],"will":[35],"be":[36],"enabled":[37],"by":[38,49,112],"deeper":[40],"understanding":[41],"how":[43],"design":[45],"pretraining":[46,106],"datasets,":[47],"techniques":[50,123,131,172],"offer":[52],"better":[53],"control":[54],"over":[55],"after":[57,127],"pretraining.":[58,128],"Towards":[59,116],"first":[61],"goal,":[62,119],"introduce":[64],"fully":[66],"open-source":[67],"benchmark":[68,74],"for":[69,80,124,147,176],"designing":[70],"datasets.":[72],"This":[73],"provides":[75],"shared":[77],"experimental":[78],"setting":[79],"research":[81],"on":[82,102],"dataset":[83,103],"curation,":[84,104],"allowing":[85],"researchers":[86],"conduct":[88],"rigorous":[89,99],"controlled":[91],"experiments.":[92],"Our":[93,129],"experiments":[94],"highlight":[95],"potential":[97],"empirical":[100],"work":[101],"finding":[105],"datasets":[107,111],"outperform":[109],"existing":[110],"large":[114],"margin.":[115],"second":[118],"present":[121,143],"multiple":[122],"improving":[125],"fine-tuning":[130],"improve":[132],"accuracy":[133],"without":[134,137],"overspecialization":[135],"increasing":[138],"inference":[139],"costs.":[140],"Moreover,":[141],"modular":[145],"framework":[146],"steering":[148],"behavior":[150],"trained":[152],"models,":[153],"designed":[154],"efficiently":[156],"add":[157],"or":[158],"delete":[159],"capabilities":[160],"while":[161],"operating":[162],"directly":[163],"within":[164],"models\u2019":[166],"weight":[167],"space.":[168],"Altogether,":[169],"these":[170],"new":[171],"pave":[173],"way":[175],"models.":[182]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-10-10T00:00:00"}