{"id":"https://openalex.org/W7214005684","doi":"https://doi.org/10.1145/3767308.3835726","title":"PrismGPT: Proxy-Guided Learning for Region-Aware Photo Editing with Self-Synthesized Reasoning","display_name":"PrismGPT: Proxy-Guided Learning for Region-Aware Photo Editing with Self-Synthesized Reasoning","publication_year":2026,"publication_date":"2026-11-06","ids":{"openalex":"https://openalex.org/W7214005684","doi":"https://doi.org/10.1145/3767308.3835726"},"language":"en","primary_location":{"id":"doi:10.1145/3767308.3835726","doi":"https://doi.org/10.1145/3767308.3835726","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767308.3835726","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3767308.3835726","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5152475984","display_name":"Ke Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405259277","display_name":"Samsung Electronics (South Korea)","ror":"https://ror.org/020m7t761","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4405259277"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ke Zhao","raw_affiliation_strings":["AI Center-Toronto, Samsung Electronics, Toronto, Ontario, Canada"],"raw_orcid":"https://orcid.org/0000-0001-5000-7022","affiliations":[{"raw_affiliation_string":"AI Center-Toronto, Samsung Electronics, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I4405259277"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138407202","display_name":"Hue Nguyen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405259277","display_name":"Samsung Electronics (South Korea)","ror":"https://ror.org/020m7t761","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4405259277"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hue Nguyen","raw_affiliation_strings":["AI Center-Toronto, Samsung Electronics, Toronto, Ontario, Canada"],"raw_orcid":"https://orcid.org/0009-0001-0226-9519","affiliations":[{"raw_affiliation_string":"AI Center-Toronto, Samsung Electronics, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I4405259277"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051631051","display_name":"Abhijith Punnappurath","orcid":"https://orcid.org/0000-0003-3438-5896","observed_orcids":["https://orcid.org/0000-0003-3438-5896"]},"institutions":[{"id":"https://openalex.org/I4405259277","display_name":"Samsung Electronics (South Korea)","ror":"https://ror.org/020m7t761","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4405259277"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Abhijith Punnappurath","raw_affiliation_strings":["AI Center-Toronto, Samsung Electronics, Toronto, Ontario, Canada"],"raw_orcid":"https://orcid.org/0000-0003-3438-5896","affiliations":[{"raw_affiliation_string":"AI Center-Toronto, Samsung Electronics, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I4405259277"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025515518","display_name":"Zhongling Wang","orcid":"https://orcid.org/0000-0002-2129-1025","observed_orcids":["https://orcid.org/0000-0002-2129-1025"]},"institutions":[{"id":"https://openalex.org/I4405259277","display_name":"Samsung Electronics (South Korea)","ror":"https://ror.org/020m7t761","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4405259277"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Zhongling Wang","raw_affiliation_strings":["AI Center-Toronto, Samsung Electronics, Toronto, Ontario, Canada"],"raw_orcid":"https://orcid.org/0000-0002-2129-1025","affiliations":[{"raw_affiliation_string":"AI Center-Toronto, Samsung Electronics, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I4405259277"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138450763","display_name":"Iqbal Mohomed","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405259277","display_name":"Samsung Electronics (South Korea)","ror":"https://ror.org/020m7t761","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4405259277"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Iqbal Mohomed","raw_affiliation_strings":["AI Center-Toronto, Samsung Electronics, Toronto, Ontario, Canada"],"raw_orcid":"https://orcid.org/0009-0008-0598-8966","affiliations":[{"raw_affiliation_string":"AI Center-Toronto, Samsung Electronics, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I4405259277"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121261274","display_name":"Michael S. Brown","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405259277","display_name":"Samsung Electronics (South Korea)","ror":"https://ror.org/020m7t761","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4405259277"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Michael S. Brown","raw_affiliation_strings":["AI Center-Toronto, Samsung Electronics, Toronto, Ontario, Canada"],"raw_orcid":"https://orcid.org/0000-0002-6357-2562","affiliations":[{"raw_affiliation_string":"AI Center-Toronto, Samsung Electronics, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I4405259277"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4405259277"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.67629395,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15320","last_page":"15328"},"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":0.9595000147819519,"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":0.9595000147819519,"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/T11019","display_name":"Image Enhancement Techniques","score":0.025299999862909317,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.004399999976158142,"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/vision-language-models","display_name":"vision-language models","score":0.7379999756813049},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"multi-task learning","score":0.6990000009536743},{"id":"https://openalex.org/keywords/photo-retouching","display_name":"photo retouching","score":0.6769999861717224},{"id":"https://openalex.org/keywords/semantic-masks","display_name":"semantic masks","score":0.45500001311302185},{"id":"https://openalex.org/keywords/training-data-efficiency","display_name":"training data efficiency","score":0.4819999933242798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8115000128746033},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8015000224113464},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.565500020980835},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5482000112533569},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5360999703407288},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5253000259399414},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.46149998903274536},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.45559999346733093},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4106000065803528},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.3921999931335449},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3555000126361847},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3124000132083893},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.3057999908924103},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2786000072956085},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2711000144481659},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26759999990463257},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.26350000500679016},{"id":"https://openalex.org/C34585555","wikidata":"https://www.wikidata.org/wiki/Q1368723","display_name":"Learning curve","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3767308.3835726","doi":"https://doi.org/10.1145/3767308.3835726","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767308.3835726","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2609.24768","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.24768","pdf_url":"https://arxiv.org/pdf/2609.24768","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.24768","doi":"https://doi.org/10.48550/arxiv.2609.24768","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.24768","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3767308.3835726","doi":"https://doi.org/10.1145/3767308.3835726","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767308.3835726","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214005684.pdf","grobid_xml":"https://content.openalex.org/works/W7214005684.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W2624871570","https://openalex.org/W4415898428","https://openalex.org/W4416780398","https://openalex.org/W6910629509"],"related_works":["https://openalex.org/W7155164453","https://openalex.org/W7168464665","https://openalex.org/W4412673702","https://openalex.org/W6891896795","https://openalex.org/W4312949266","https://openalex.org/W4417531525","https://openalex.org/W4402753539","https://openalex.org/W7131890443","https://openalex.org/W7154689030","https://openalex.org/W4405468181"],"abstract_inverted_index":{"Professional":[0],"photo":[1],"finishing":[2],"relies":[3],"on":[4,46,155],"both":[5,59],"global":[6,60],"adjustments":[7],"and":[8,61,91,158],"region-specific":[9],"local":[10,62],"edits":[11],"guided":[12],"by":[13,141],"semantic":[14],"masks,":[15],"yet":[16],"current":[17],"automated":[18],"methods":[19],"handle":[20],"this":[21,80],"workflow":[22],"only":[23,175],"partially.":[24],"We":[25,78],"present":[26],"PrismGPT,":[27],"a":[28,40,51,104,150,160],"Vision-Language":[29],"Model":[30],"(VLM)":[31],"framework":[32],"that":[33,168],"produces":[34],"structured,":[35],"region-aware":[36,92],"editing":[37,67,124],"plans":[38],"from":[39,117],"single":[41],"input":[42],"image":[43],"without":[44],"relying":[45],"commercial":[47],"black-box":[48],"tools.":[49],"Training":[50],"VLM":[52],"to":[53,72,121,182],"simultaneously":[54],"diagnose":[55],"aesthetic":[56,93],"deficiencies":[57],"at":[58],"levels":[63],"while":[64,103,173],"predicting":[65],"precise":[66],"parameters":[68],"is":[69,129],"challenging":[70],"due":[71],"the":[73,97,100,110,118,122,142,147,178,183],"vast":[74],"combinatorial":[75],"decision":[76],"space.":[77],"address":[79],"through":[81],"proxy-guided":[82],"learning:":[83],"two":[84],"simpler":[85],"proxy":[86,119],"tasks":[87,120],"--":[88,95],"operation":[89],"decomposition":[90],"ranking":[94],"teach":[96],"foundational":[98],"skills":[99],"model":[101],"needs,":[102],"competence-based":[105],"dynamic":[106],"scheduler":[107],"automatically":[108],"rebalances":[109],"multi-task":[111],"training":[112,179],"ratio,":[113],"progressively":[114],"shifting":[115],"emphasis":[116],"primary":[123],"task":[125],"as":[126],"each":[127],"skill":[128],"mastered.":[130],"Crucially,":[131],"all":[132],"reasoning":[133],"traces":[134],"used":[135],"for":[136,149],"supervised":[137],"fine-tuning":[138],"are":[139],"self-synthesized":[140],"same":[143],"base":[144],"model,":[145],"eliminating":[146],"need":[148],"stronger":[151],"external":[152],"teacher.":[153],"Experiments":[154],"MIT-Adobe":[156],"FiveK":[157],"SPIRE,":[159],"new":[161],"professionally":[162],"retouched":[163],"benchmark":[164],"we":[165],"introduce,":[166],"show":[167],"PrismGPT":[169],"achieves":[170],"state-of-the-art":[171],"results":[172],"using":[174],"~6%":[176],"of":[177],"data":[180],"compared":[181],"previous":[184],"best":[185],"method.":[186]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-23T00:00:00"}