{"id":"https://openalex.org/W4416034155","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1161","title":"Visual Self-Refinement for Autoregressive Models","display_name":"Visual Self-Refinement for Autoregressive Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034155","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1161","pmid":"https://pubmed.ncbi.nlm.nih.gov/41726124"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1161","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1161","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1161.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: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1161.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000592356","display_name":"Jiamian Wang","orcid":"https://orcid.org/0000-0002-0074-0274"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiamian Wang","raw_affiliation_strings":["Rochester Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ziqi Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziqi Zhou","raw_affiliation_strings":["Rochester Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077132380","display_name":"Chaithanya Kumar Mummadi","orcid":"https://orcid.org/0000-0002-1173-2720"},"institutions":[{"id":"https://openalex.org/I4210151956","display_name":"Robert Bosch (India)","ror":"https://ror.org/04my8ty22","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210151956","https://openalex.org/I889804353"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Chaithanya Kumar Mummadi","raw_affiliation_strings":["Bosch Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bosch Research","institution_ids":["https://openalex.org/I4210151956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113100360","display_name":"Sohail A. Dianat","orcid":null},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sohail Dianat","raw_affiliation_strings":["Rochester Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111726577","display_name":"Majid Rabbani","orcid":null},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Majid Rabbani","raw_affiliation_strings":["Rochester Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075151572","display_name":"Raghuveer Rao","orcid":"https://orcid.org/0000-0001-6481-4175"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]},{"id":"https://openalex.org/I2802705668","display_name":"United States Army Combat Capabilities Development Command","ror":"https://ror.org/02rdkx920","country_code":"US","type":"other","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raghuveer Rao","raw_affiliation_strings":["DEVCOM Army Research Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DEVCOM Army Research Laboratory","institution_ids":["https://openalex.org/I166416128","https://openalex.org/I2802705668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066436167","display_name":"Chen Qiu","orcid":"https://orcid.org/0000-0003-4727-6066"},"institutions":[{"id":"https://openalex.org/I4210151956","display_name":"Robert Bosch (India)","ror":"https://ror.org/04my8ty22","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210151956","https://openalex.org/I889804353"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Chen Qiu","raw_affiliation_strings":["Bosch Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bosch Research","institution_ids":["https://openalex.org/I4210151956"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021486404","display_name":"Zhiqiang Tao","orcid":"https://orcid.org/0000-0002-5639-7540"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiqiang Tao","raw_affiliation_strings":["Rochester Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology","institution_ids":["https://openalex.org/I155173764"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":0.36998652,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2025","issue":null,"first_page":"21291","last_page":"21300"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9434999823570251,"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":0.9434999823570251,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.010400000028312206,"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":0.010200000368058681,"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/autoregressive-model","display_name":"Autoregressive model","score":0.8495000004768372},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5515000224113464},{"id":"https://openalex.org/keywords/star-model","display_name":"STAR model","score":0.5349000096321106},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.358599990606308},{"id":"https://openalex.org/keywords/nonlinear-autoregressive-exogenous-model","display_name":"Nonlinear autoregressive exogenous model","score":0.3479999899864197},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.3246000111103058},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.29440000653266907}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.8495000004768372},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7462999820709229},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5515000224113464},{"id":"https://openalex.org/C194657046","wikidata":"https://www.wikidata.org/wiki/Q7394685","display_name":"STAR model","level":4,"score":0.5349000096321106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46779999136924744},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4255000054836273},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3952000141143799},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C42536954","wikidata":"https://www.wikidata.org/wiki/Q7049462","display_name":"Nonlinear autoregressive exogenous model","level":3,"score":0.3479999899864197},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3425999879837036},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3246000111103058},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C86426650","wikidata":"https://www.wikidata.org/wiki/Q7452504","display_name":"Sequential estimation","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C80478641","wikidata":"https://www.wikidata.org/wiki/Q195771","display_name":"Sequential analysis","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C24338571","wikidata":"https://www.wikidata.org/wiki/Q2566298","display_name":"Autoregressive integrated moving average","level":3,"score":0.2502000033855438}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1161","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1161","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1161.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: EMNLP 2025","raw_type":"proceedings-article"},{"id":"pmid:41726124","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41726124","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of ACL. EMNLP. Conference on Empirical Methods in Natural Language Processing","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:12922227","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12922227/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Find ACL EMNLP","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1161","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1161","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1161.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1516536792","display_name":null,"funder_award_id":"R16 GM159146","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034155.pdf","grobid_xml":"https://content.openalex.org/works/W4416034155.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Autoregressive":[0],"models":[1],"excel":[2],"in":[3],"sequential":[4,25,75,96],"modeling":[5,47,71],"and":[6,82],"have":[7],"proven":[8],"to":[9,31,41,60,112],"be":[10],"effective":[11],"for":[12],"vision-language":[13,70],"data.":[14],"However,":[15],"the":[16,24,43,49,85,90,95,101,105,109],"spatial":[17,45],"nature":[18],"of":[19,27,66],"visual":[20,51],"signals":[21],"conflicts":[22],"with":[23],"dependencies":[26],"next-token":[28],"prediction,":[29],"leading":[30],"suboptimal":[32],"results.":[33,116],"This":[34,53],"work":[35],"proposes":[36],"a":[37,57,73],"plug-and-play":[38],"refinement":[39],"module":[40,54],"enhance":[42],"complex":[44],"correspondence":[46],"within":[48,94],"generated":[50,64],"sequence.":[52],"operates":[55],"as":[56],"post-pretraining":[58],"step":[59],"jointly":[61],"refine":[62],"all":[63],"tokens":[65],"autoregressive":[67],"model,":[68],"enhancing":[69,108],"under":[72],"shared":[74],"prediction":[76],"framework.":[77],"By":[78],"leveraging":[79],"global":[80],"context":[81],"relationship":[83],"across":[84],"tokens,":[86],"our":[87],"method":[88,103],"mitigates":[89],"error":[91],"accumulation":[92],"issue":[93],"generation.":[97],"Experiments":[98],"demonstrate":[99],"that":[100],"proposed":[102],"improves":[104],"generation":[106],"quality,":[107],"model's":[110],"ability":[111],"produce":[113],"semantically":[114],"consistent":[115]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}