{"id":"https://openalex.org/W7117125859","doi":"https://doi.org/10.48550/arxiv.2512.19686","title":"Visual-Aware CoT: Achieving High-Fidelity Visual Consistency in Unified Models","display_name":"Visual-Aware CoT: Achieving High-Fidelity Visual Consistency in Unified Models","publication_year":2025,"publication_date":"2025-12-22","ids":{"openalex":"https://openalex.org/W7117125859","doi":"https://doi.org/10.48550/arxiv.2512.19686"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2512.19686","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.19686","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2512.19686","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104265263","display_name":"Zixuan Ye","orcid":"https://orcid.org/0000-0001-8517-682X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ye, Zixuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054960327","display_name":"Quande Liu","orcid":"https://orcid.org/0000-0002-3921-5960"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Quande","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390541","display_name":"Cong Wei","orcid":"https://orcid.org/0000-0003-4660-6916"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Cong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020022791","display_name":"Yuanxing Zhang","orcid":"https://orcid.org/0000-0003-1460-8124"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yuanxing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050775360","display_name":"Xintao Wang","orcid":"https://orcid.org/0000-0003-1428-8677"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xintao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121194679","display_name":"Pengfei Wan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wan, Pengfei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097335717","display_name":"Kun Gai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gai, Kun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5121179699","display_name":"Wenhan Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Wenhan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5104265263"],"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":0.8495000004768372,"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":0.8495000004768372,"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":0.022700000554323196,"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/T10799","display_name":"Data Visualization and Analytics","score":0.022099999710917473,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.7628999948501587},{"id":"https://openalex.org/keywords/consistency-model","display_name":"Consistency model","score":0.6079000234603882},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.557699978351593},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4961000084877014},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4357999861240387},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4293000102043152},{"id":"https://openalex.org/keywords/iterative-and-incremental-development","display_name":"Iterative and incremental development","score":0.41440001130104065},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.40799999237060547},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.38580000400543213}],"concepts":[{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7628999948501587},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7400000095367432},{"id":"https://openalex.org/C37279795","wikidata":"https://www.wikidata.org/wiki/Q2492305","display_name":"Consistency model","level":3,"score":0.6079000234603882},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.557699978351593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5562999844551086},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4961000084877014},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4357999861240387},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4293000102043152},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.41440001130104065},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.40799999237060547},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.38580000400543213},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3756999969482422},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3352999985218048},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C137105694","wikidata":"https://www.wikidata.org/wiki/Q3407510","display_name":"Local consistency","level":4,"score":0.311599999666214},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.3061999976634979},{"id":"https://openalex.org/C175652121","wikidata":"https://www.wikidata.org/wiki/Q4379351","display_name":"Causal consistency","level":5,"score":0.3010999858379364},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.2953999936580658},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2662999927997589},{"id":"https://openalex.org/C2777055276","wikidata":"https://www.wikidata.org/wiki/Q7936580","display_name":"Visual approach","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C168820333","wikidata":"https://www.wikidata.org/wiki/Q448889","display_name":"Visual inspection","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2512.19686","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.19686","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2512.19686","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.19686","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"the":[1,9,20,29,33,37,42,47,60,78,83,90,109,124,131,147,152,165],"introduction":[2],"of":[3,12,55,85,112,126],"Chain-of-Thought":[4],"(CoT)":[5],"has":[6],"largely":[7],"improved":[8],"generation":[10,25],"ability":[11],"unified":[13,86,183],"models.":[14],"However,":[15],"it":[16],"is":[17],"observed":[18],"that":[19,177],"current":[21],"thinking":[22],"process":[23],"during":[24,46],"mainly":[26],"focuses":[27],"on":[28],"text":[30,34,188],"consistency":[31,57,81,95,114,167],"with":[32,41,123,187],"prompt,":[35],"ignoring":[36],"\\textbf{visual":[38],"context":[39,80,196],"consistency}":[40],"visual":[43,65,79,103,110,153,166,171,195],"reference":[44],"images":[45],"multi-modal":[48,191],"generation,":[49,192],"e.g.,":[50],"multi-reference":[51],"generation.":[52],"The":[53,174],"lack":[54],"such":[56,94],"results":[58],"in":[59,62,134,190],"failure":[61],"maintaining":[63],"key":[64],"features":[66],"(like":[67],"human":[68],"ID,":[69],"object":[70],"attribute,":[71],"style).":[72],"To":[73,138],"this":[74],"end,":[75],"we":[76,141],"integrate":[77],"into":[82],"reasoning":[84],"models,":[87],"explicitly":[88],"motivating":[89],"model":[91,148],"to":[92,106,145,150,162],"sustain":[93],"by":[96],"1)":[97],"Adaptive":[98],"Visual":[99,119],"Planning:":[100],"generating":[101],"structured":[102],"check":[104,127],"list":[105],"figure":[107],"out":[108],"element":[111],"needed":[113],"keeping,":[115],"and":[116,129,157,159,185],"2)":[117],"Iterative":[118],"Correction:":[120],"performing":[121],"self-reflection":[122,156],"guidance":[125],"lists":[128],"refining":[130],"generated":[132],"result":[133],"an":[135],"iterative":[136],"manner.":[137],"achieve":[139],"this,":[140],"use":[142,160],"supervised":[143],"finetuning":[144],"teach":[146],"how":[149],"plan":[151],"checking,":[154],"conduct":[155],"self-refinement,":[158],"flow-GRPO":[161],"further":[163],"enhance":[164],"through":[168],"a":[169],"customized":[170],"checking":[172],"reward.":[173],"experiments":[175],"show":[176],"our":[178],"method":[179],"outperforms":[180],"both":[181],"zero-shot":[182],"models":[184],"those":[186],"CoTs":[189],"demonstrating":[193],"higher":[194],"consistency.":[197]},"counts_by_year":[],"updated_date":"2025-12-24T23:14:05.333182","created_date":"2025-12-24T00:00:00"}