{"id":"https://openalex.org/W4413147195","doi":"https://doi.org/10.1109/cvpr52734.2025.01720","title":"Towards Transformer-Based Aligned Generation with Self-Coherence Guidance","display_name":"Towards Transformer-Based Aligned Generation with Self-Coherence Guidance","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413147195","doi":"https://doi.org/10.1109/cvpr52734.2025.01720"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.01720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078789660","display_name":"Shulei Wang","orcid":"https://orcid.org/0000-0001-7440-9544"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shulei Wang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wang Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang Lin","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103334613","display_name":"Huang Hai","orcid":"https://orcid.org/0009-0004-2793-1988"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hai Huang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072365834","display_name":"Hanting Wang","orcid":"https://orcid.org/0000-0003-2761-577X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanting Wang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sihang Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sihang Cai","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"WenKang Han","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"WenKang Han","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102011966","display_name":"Tao Jin","orcid":"https://orcid.org/0000-0003-3564-1628"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Jin","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100770062","display_name":"Jingyuan Chen","orcid":"https://orcid.org/0000-0001-8691-883X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyuan Chen","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037497972","display_name":"Jiacheng Sun","orcid":"https://orcid.org/0000-0002-2306-0124"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Jiacheng Sun","raw_affiliation_strings":["Huawei Noah&#x2019;s Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah&#x2019;s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100552790","display_name":"Jieming Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Jieming Zhu","raw_affiliation_strings":["Huawei Noah&#x2019;s Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah&#x2019;s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":11,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.864,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78645153,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"18455","last_page":"18464"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11408","display_name":"Advanced Optical Imaging Technologies","score":0.5835000276565552,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11408","display_name":"Advanced Optical Imaging Technologies","score":0.5835000276565552,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.5159000158309937,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6319053173065186},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5616189241409302},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.5033311247825623},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.23397409915924072},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1535908281803131},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.1383686065673828},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10277286171913147}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6319053173065186},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5616189241409302},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.5033311247825623},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.23397409915924072},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1535908281803131},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.1383686065673828},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10277286171913147},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.01720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"We":[0],"introduce":[1,71],"a":[2,74],"novel,":[3],"training-free":[4],"approach":[5],"for":[6,103],"enhancing":[7],"alignment":[8,90],"in":[9],"Transformer-based":[10,49],"Text-Guided":[11],"Diffusion":[12],"Models":[13],"(TGDMs).":[14],"Existing":[15],"TGDMs":[16],"often":[17],"struggle":[18],"to":[19,48],"generate":[20],"semantically":[21],"aligned":[22],"images,":[23],"particularly":[24],"when":[25],"dealing":[26],"with":[27],"complex":[28],"text":[29],"prompts":[30],"or":[31],"multi-concept":[32],"attribute":[33,106,109],"binding":[34],"challenges.":[35],"Previous":[36],"U-Net-based":[37],"methods":[38,127],"primarily":[39],"optimized":[40],"the":[41,66,117],"latent":[42],"space,":[43],"but":[44],"their":[45],"direct":[46],"application":[47],"architectures":[50],"has":[51],"shown":[52],"limited":[53],"effectiveness.":[54],"Our":[55,132],"method":[56,75],"addresses":[57],"these":[58],"challenges":[59],"by":[60],"directly":[61],"optimizing":[62],"cross-attention":[63],"maps":[64,80],"during":[65],"generation":[67],"process.":[68],"Specifically,":[69],"we":[70,98],"Self-Coherence":[72],"Guidance,":[73],"that":[76],"dynamically":[77],"refines":[78],"attention":[79],"using":[81],"masks":[82],"derived":[83],"from":[84],"previous":[85],"denoising":[86],"steps,":[87],"ensuring":[88],"precise":[89],"without":[91],"additional":[92],"training.":[93],"To":[94],"validate":[95],"our":[96,121],"approach,":[97],"constructed":[99],"more":[100],"challenging":[101],"benchmarks":[102],"evaluating":[104],"coarse-grained":[105],"binding,":[107,110],"fine-grained":[108],"and":[111],"style":[112],"binding.":[113],"Experimental":[114],"results":[115],"demonstrate":[116],"superior":[118],"performance":[119],"of":[120],"method,":[122],"significantly":[123],"surpassing":[124],"other":[125],"state-of-the-art":[126],"across":[128],"all":[129],"evaluated":[130],"tasks.":[131],"code":[133],"is":[134],"available":[135],"at":[136],"https://scg-diffusion.github.io/scg-diffusion.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
