{"id":"https://openalex.org/W7166816453","doi":"https://doi.org/10.18653/v1/2026.findings-acl.383","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":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166816453","doi":"https://doi.org/10.18653/v1/2026.findings-acl.383"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.383","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.383","pdf_url":"https://aclanthology.org/2026.findings-acl.383.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.383.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139730601","display_name":"Cong Wan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cong Wan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139835905","display_name":"Ying He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ying He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139756930","display_name":"Zhongzhan Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhongzhan Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139797429","display_name":"Hefeng Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hefeng Wu","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.80606979,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7751","last_page":"7767"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.2903999984264374,"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":0.2903999984264374,"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":0.1339000016450882,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.06880000233650208,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.5475000143051147},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.3686000108718872},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.28209999203681946},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.2759000062942505}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5562000274658203},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.5475000143051147},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.3686000108718872},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35899999737739563},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.3052999973297119},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2522999942302704},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.24779999256134033},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.24469999969005585}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.383","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.383","pdf_url":"https://aclanthology.org/2026.findings-acl.383.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.383","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.383","pdf_url":"https://aclanthology.org/2026.findings-acl.383.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6248067210","display_name":null,"funder_award_id":"2023A1515012845","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G7308144093","display_name":null,"funder_award_id":"62272494","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166816453.pdf","grobid_xml":"https://content.openalex.org/works/W7166816453.grobid-xml"},"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":[6,44,74,120],"pivotal":[7],"research":[8,70,117],"direction":[9],"for":[10,71,123],"enhancing":[11],"model":[12],"performance":[13],"by":[14],"dynamically":[15],"allocating":[16],"computational":[17],"resources":[18],"during":[19],"inference.Recent":[20],"advancements":[21],"have":[22],"adapted":[23],"this":[24,60,109,127],"paradigm":[25],"to":[26,51,99],"Multimodal":[27],"Foundation":[28],"Models":[29],"(MFMs),":[30],"unlocking":[31],"their":[32],"potential":[33],"in":[34,104,126],"multimodal":[35,57,101],"reasoning":[36,107],"and":[37,47,88,95,106,114],"generation.Despite":[38],"rapid":[39],"progress,":[40],"the":[41,53,64],"field":[42],"lacks":[43],"systematic":[45,121],"survey":[46,110],"unified":[48,75],"theoretical":[49],"framework":[50,77],"delineate":[52],"developmental":[54],"landscape":[55],"of":[56,68],"TTS.To":[58],"bridge":[59],"gap,":[61],"we":[62],"present":[63],"first":[65],"comprehensive":[66],"review":[67],"TTS":[69,102],"MFMs,":[72],"proposing":[73],"taxonomic":[76],"that":[78],"categorizes":[79],"existing":[80],"methodologies":[81],"into":[82],"three":[83],"distinct":[84],"strategies:":[85],"sampling-based,":[86],"feedbackbased,":[87],"search-based":[89],"approaches.We":[90],"further":[91],"summarize":[92],"representative":[93],"applications":[94],"benchmarks":[96],"commonly":[97],"utilized":[98],"evaluate":[100],"capabilities":[103],"generation":[105],"tasks.Finally,":[108],"discusses":[111],"open":[112],"challenges":[113],"outlines":[115],"future":[116],"directions,":[118],"providing":[119],"roadmap":[122],"subsequent":[124],"studies":[125],"rapidly":[128],"evolving":[129],"field.":[130]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}