{"id":"https://openalex.org/W7160152793","doi":"https://doi.org/10.1109/iccv51701.2025.01492","title":"IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance","display_name":"IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7160152793","doi":"https://doi.org/10.1109/iccv51701.2025.01492"},"language":null,"primary_location":{"id":"doi:10.1109/iccv51701.2025.01492","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01492","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5057347296","display_name":"Jiayi Guo","orcid":"https://orcid.org/0000-0002-2272-0450"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiayi Guo","raw_affiliation_strings":["SHI Labs @ Georgia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SHI Labs @ Georgia Tech","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088055333","display_name":"Chuanhao Yan","orcid":"https://orcid.org/0000-0002-5165-2477"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chuanhao Yan","raw_affiliation_strings":["SHI Labs @ Georgia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SHI Labs @ Georgia Tech","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046341376","display_name":"Xingqian Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xingqian Xu","raw_affiliation_strings":["SHI Labs @ Georgia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SHI Labs @ Georgia Tech","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100633632","display_name":"Yue Wang","orcid":"https://orcid.org/0000-0003-0098-5359"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulin Wang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135187907","display_name":"Kai Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Wang","raw_affiliation_strings":["SHI Labs @ Georgia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SHI Labs @ Georgia Tech","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135208597","display_name":"Gao Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gao Huang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135097258","display_name":"Humphrey Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Humphrey Shi","raw_affiliation_strings":["SHI Labs @ Georgia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SHI Labs @ Georgia Tech","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"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":"16079","last_page":"16089"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.120899997651577,"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":0.120899997651577,"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/T12321","display_name":"Insect Pheromone Research and Control","score":0.020999999716877937,"subfield":{"id":"https://openalex.org/subfields/1109","display_name":"Insect Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T14394","display_name":"Cognitive Science and Education Research","score":0.020500000566244125,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.38179999589920044},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.375900000333786},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.3553999960422516},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3197999894618988},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.2992999851703644},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2831000089645386}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5424000024795532},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.38179999589920044},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.375900000333786},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3718000054359436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3659999966621399},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3197999894618988},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3012999892234802},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2831000089645386},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27090001106262207},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccv51701.2025.01492","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01492","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2997156820","display_name":"CAREER: Structure-Preserving Multimodal Alignment between Vision and Language","funder_award_id":"2427478","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G962119475","display_name":null,"funder_award_id":"2229873","funder_id":"https://openalex.org/F4320306106","funder_display_name":"U.S. Department of Education"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306106","display_name":"U.S. Department of Education","ror":"https://ror.org/021adze67"},{"id":"https://openalex.org/F4320332869","display_name":"College of Computing","ror":"https://ror.org/01zkghx44"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W3170883289","https://openalex.org/W4200635121","https://openalex.org/W4312901050","https://openalex.org/W4312933868","https://openalex.org/W4386066462","https://openalex.org/W4386071587","https://openalex.org/W4386076215","https://openalex.org/W4390872325","https://openalex.org/W4390873054","https://openalex.org/W4390874002","https://openalex.org/W4393148714","https://openalex.org/W4402727505","https://openalex.org/W4402727613","https://openalex.org/W4402727699","https://openalex.org/W4402727926","https://openalex.org/W4402753507","https://openalex.org/W4402753674","https://openalex.org/W4402753733","https://openalex.org/W4402753770","https://openalex.org/W4402753773","https://openalex.org/W4402753790","https://openalex.org/W4404625217","https://openalex.org/W4404985095","https://openalex.org/W4413144478","https://openalex.org/W4415796806","https://openalex.org/W7133217041","https://openalex.org/W7133231872","https://openalex.org/W7160019919"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-05T00:00:00"}
