{"id":"https://openalex.org/W7164052315","doi":"https://doi.org/10.48550/arxiv.2606.08231","title":"Test-Time Scaling in Multimodal Foundation Models: A Comprehensive Survey of Generation and Reasoning","display_name":"Test-Time Scaling in Multimodal Foundation Models: A Comprehensive Survey of Generation and Reasoning","publication_year":2026,"publication_date":"2026-06-06","ids":{"openalex":"https://openalex.org/W7164052315","doi":"https://doi.org/10.48550/arxiv.2606.08231"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.08231","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08231","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.08231","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138208111","display_name":"Cong Wan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wan, Cong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138278609","display_name":"Ying He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Ying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138233889","display_name":"Zhongzhan Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Zhongzhan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138257435","display_name":"Hefeng Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Hefeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.28279998898506165,"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":0.28279998898506165,"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":0.2655999958515167,"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/T12031","display_name":"Speech and dialogue systems","score":0.06629999727010727,"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/foundation","display_name":"Foundation (evidence)","score":0.5809999704360962},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5684000253677368},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.4921000003814697},{"id":"https://openalex.org/keywords/open-research","display_name":"Open research","score":0.44830000400543213},{"id":"https://openalex.org/keywords/systematic-review","display_name":"Systematic review","score":0.33820000290870667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6499000191688538},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.5809999704360962},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5684000253677368},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.49230000376701355},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4921000003814697},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.4742000102996826},{"id":"https://openalex.org/C2778464652","wikidata":"https://www.wikidata.org/wiki/Q309849","display_name":"Open research","level":2,"score":0.44830000400543213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3490000069141388},{"id":"https://openalex.org/C189708586","wikidata":"https://www.wikidata.org/wiki/Q1504425","display_name":"Systematic review","level":3,"score":0.33820000290870667},{"id":"https://openalex.org/C43540301","wikidata":"https://www.wikidata.org/wiki/Q689971","display_name":"Paradigm shift","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.2648000121116638},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.08231","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08231","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.08231","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08231","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.43440601229667664}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Test-time":[0],"Scaling":[1],"(TTS)":[2],"has":[3],"emerged":[4],"as":[5],"a":[6,46,77,125],"pivotal":[7],"research":[8,73,122],"direction":[9],"for":[10,74,128],"enhancing":[11],"model":[12],"performance":[13],"by":[14],"dynamically":[15],"allocating":[16],"computational":[17],"resources":[18],"during":[19],"inference.":[20],"Recent":[21],"advancements":[22],"have":[23],"adapted":[24],"this":[25,63,114,132],"paradigm":[26],"to":[27,53,103],"Multimodal":[28],"Foundation":[29],"Models":[30],"(MFMs),":[31],"unlocking":[32],"their":[33],"potential":[34],"in":[35,108,131],"multimodal":[36,59,105],"reasoning":[37,111],"and":[38,49,91,99,110,119],"generation.":[39],"Despite":[40],"rapid":[41],"progress,":[42],"the":[43,55,67],"field":[44],"lacks":[45],"systematic":[47,126],"survey":[48,115],"unified":[50,78],"theoretical":[51],"framework":[52,80],"delineate":[54],"developmental":[56],"landscape":[57],"of":[58,71],"TTS.":[60],"To":[61],"bridge":[62],"gap,":[64],"we":[65],"present":[66],"first":[68],"comprehensive":[69],"review":[70],"TTS":[72,106],"MFMs,":[75],"proposing":[76],"taxonomic":[79],"that":[81],"categorizes":[82],"existing":[83],"methodologies":[84],"into":[85],"three":[86],"distinct":[87],"strategies:":[88],"sampling-based,":[89],"feedback-based,":[90],"search-based":[92],"approaches.":[93],"We":[94],"further":[95],"summarize":[96],"representative":[97],"applications":[98],"benchmarks":[100],"commonly":[101],"utilized":[102],"evaluate":[104],"capabilities":[107],"generation":[109],"tasks.":[112],"Finally,":[113],"discusses":[116],"open":[117],"challenges":[118],"outlines":[120],"future":[121],"directions,":[123],"providing":[124],"roadmap":[127],"subsequent":[129],"studies":[130],"rapidly":[133],"evolving":[134],"field.":[135]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-10T00:00:00"}