{"id":"https://openalex.org/W7137907667","doi":"https://doi.org/10.1609/aaai.v40i11.37868","title":"UniAlignment: Semantic Alignment for Unified Image Generation, Understanding, Manipulation and Perception","display_name":"UniAlignment: Semantic Alignment for Unified Image Generation, Understanding, Manipulation and Perception","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137907667","doi":"https://doi.org/10.1609/aaai.v40i11.37868"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i11.37868","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37868","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i11.37868","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129706861","display_name":"Xinyang Song","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinyang Song","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences\nInstitute of Automation, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences\nInstitute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129657542","display_name":"Libin Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Libin Wang","raw_affiliation_strings":["Ant Group"],"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129672651","display_name":"Weining Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weining Wang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129686807","display_name":"Shaozhen Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaozhen Liu","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences\nInstitute of Automation, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences\nInstitute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129694776","display_name":"Dandan Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dandan Zheng","raw_affiliation_strings":["Ant Group"],"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129746493","display_name":"Jingdong Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingdong Chen","raw_affiliation_strings":["Ant Group"],"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129663344","display_name":"Qi Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Li","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences\nInstitute of Automation, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences\nInstitute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129647973","display_name":"Zhenan Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenan Sun","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences\nInstitute of Automation, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences\nInstitute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5129706861"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14328358,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"11","first_page":"9116","last_page":"9126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.46790000796318054,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.46790000796318054,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4507000148296356,"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":0.006099999882280827,"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/consistency","display_name":"Consistency (knowledge bases)","score":0.6197999715805054},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5979999899864197},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5910999774932861},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5771999955177307},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4830999970436096},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4345000088214874},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.4320000112056732},{"id":"https://openalex.org/keywords/semantic-data-model","display_name":"Semantic data model","score":0.37560001015663147}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.810699999332428},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6197999715805054},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5979999899864197},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5910999774932861},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5771999955177307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5619999766349792},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4830999970436096},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4345000088214874},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.4320000112056732},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38119998574256897},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.37560001015663147},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.36970001459121704},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.35510000586509705},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.3474000096321106},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.32339999079704285},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2831999957561493},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i11.37868","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37868","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i11.37868","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37868","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.537553071975708,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"remarkable":[1],"success":[2],"of":[3,20,149],"diffusion":[4,86,92,150],"models":[5,56,151],"in":[6,13,42,152],"text-to-image":[7],"generation":[8,81],"has":[9],"sparked":[10],"growing":[11],"interest":[12],"expanding":[14],"their":[15],"capabilities":[16],"to":[17,65,123],"a":[18,78,84,90,118],"variety":[19],"multi-modal":[21],"tasks,":[22],"including":[23],"image":[24],"understanding,":[25],"manipulation,":[26],"and":[27,38,68,101,111,137],"perception.":[28],"These":[29],"tasks":[30,136],"require":[31],"advanced":[32],"semantic":[33,46,62,99,103,126],"comprehension":[34],"across":[35,134],"both":[36,97],"visual":[37],"textual":[39,130],"modalities,":[40],"especially":[41],"scenarios":[43],"involving":[44],"complex":[45,129],"instructions.":[47,131],"However,":[48],"existing":[49,143],"approaches":[50],"often":[51],"rely":[52],"heavily":[53],"on":[54],"vision-language":[55],"(VLMs)":[57],"or":[58],"modular":[59],"designs":[60],"for":[61],"guidance,":[63],"leading":[64],"fragmented":[66],"architectures":[67],"computational":[69],"inefficiency.":[70],"To":[71],"address":[72],"these":[73],"challenges,":[74],"we":[75,115],"propose":[76],"UniAlignment,":[77],"unified":[79,153],"multimodal":[80,125,154],"framework":[82],"within":[83],"single":[85],"transformer.":[87],"UniAlignment":[88,141],"introduces":[89],"dual-stream":[91],"training":[93],"strategy":[94],"that":[95,140],"incorporates":[96],"intrinsic-modal":[98],"alignment":[100],"cross-modal":[102,109],"alignment,":[104],"thereby":[105],"enhancing":[106],"the":[107,146],"model's":[108],"consistency":[110,127],"instruction-following":[112],"robustness.":[113],"Additionally,":[114],"present":[116],"SemGen-Bench,":[117],"new":[119],"benchmark":[120],"specifically":[121],"designed":[122],"evaluate":[124],"under":[128],"Extensive":[132],"experiments":[133],"multiple":[135],"benchmarks":[138],"demonstrate":[139],"outperforms":[142],"baselines,":[144],"underscoring":[145],"significant":[147],"potential":[148],"generation.":[155]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}