{"id":"https://openalex.org/W7137858274","doi":"https://doi.org/10.48550/arxiv.2603.14916","title":"EditHF-1M: A Million-Scale Rich Human Preference Feedback for Image Editing","display_name":"EditHF-1M: A Million-Scale Rich Human Preference Feedback for Image Editing","publication_year":2026,"publication_date":"2026-03-16","ids":{"openalex":"https://openalex.org/W7137858274","doi":"https://doi.org/10.48550/arxiv.2603.14916"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.14916","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14916","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.14916","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129743277","display_name":"Zitong Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Zitong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129700981","display_name":"Huiyu Duan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duan, Huiyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060080802","display_name":"Zhongpeng Ji","orcid":"https://orcid.org/0000-0002-9532-7035"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji, Zhongpeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129734444","display_name":"Xinyun Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xinyun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129661025","display_name":"Yutao Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yutao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129716063","display_name":"Xiongkuo Min","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min, Xiongkuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129728723","display_name":"Ke Gu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gu, Ke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129680065","display_name":"Jian Dong Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042627504","display_name":"Shusong Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Shusong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129656378","display_name":"Jinwei Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jinwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129684283","display_name":"Bo Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Bo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129644847","display_name":"Guangtao Zhai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhai, Guangtao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"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":0.47510001063346863,"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":0.47510001063346863,"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":0.08209999650716782,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.07000000029802322,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6597999930381775},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6007999777793884},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.5737000107765198},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.531000018119812},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5249999761581421},{"id":"https://openalex.org/keywords/human-visual-system-model","display_name":"Human visual system model","score":0.45820000767707825},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4562999904155731}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7961000204086304},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6597999930381775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6171000003814697},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6007999777793884},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.5737000107765198},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.531000018119812},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5249999761581421},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.45820000767707825},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4562999904155731},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.45190000534057617},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3898000121116638},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3799000084400177},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2572999894618988},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.14916","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14916","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.14916","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14916","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"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":{"Recent":[0],"text-guided":[1,129],"image":[2,53,65,113,130,180],"editing":[3,66,131],"(TIE)":[4],"models":[5,39,51,132],"have":[6,30],"achieved":[7],"remarkable":[8],"progress,":[9],"while":[10],"many":[11],"edited":[12,35],"images":[13],"still":[14,41],"suffer":[15],"from":[16,82,112],"issues":[17],"such":[18],"as":[19,122,173],"artifacts,":[20],"unexpected":[21],"editings,":[22],"unaesthetic":[23],"contents.":[24],"Although":[25],"some":[26],"benchmarks":[27],"and":[28,74,90,147,185],"methods":[29],"been":[31],"proposed":[32],"for":[33,52],"evaluating":[34],"images,":[36],"scalable":[37],"evaluation":[38,106],"are":[40],"lacking,":[42],"which":[43,119,165],"limits":[44],"the":[45,57,123,128,157,167,179,183],"development":[46],"of":[47,169],"human":[48,71,76,145],"feedback":[49,111],"reward":[50,124,175],"editing.":[54,114,181],"To":[55],"address":[56],"challenges,":[58],"we":[59,96,116,155],"first":[60],"introduce":[61,117],"\\textbf{EditHF-1M},":[62],"a":[63,99,174],"million-scale":[64],"dataset":[67,184],"with":[68,144],"over":[69],"29M":[70],"preference":[72],"pairs":[73],"148K":[75],"mean":[77],"opinion":[78],"ratings,":[79],"both":[80],"evaluated":[81],"three":[83],"dimensions,":[84],"\\textit{i.e.},":[85],"visual":[86],"quality,":[87],"instruction":[88],"alignment,":[89],"attribute":[91],"preservation.":[92],"Based":[93],"on":[94,151],"EditHF-1M,":[95],"propose":[97],"\\textbf{EditHF},":[98],"multimodal":[100],"large":[101],"language":[102],"model":[103,176],"(MLLM)":[104],"based":[105],"model,":[107],"to":[108,126,171,177],"provide":[109],"human-aligned":[110],"Finally,":[115],"\\textbf{EditHF-Reward},":[118],"utilizes":[120],"EditHF":[121,140,170],"signal":[125],"optimize":[127],"through":[133],"reinforcement":[134],"learning.":[135],"Extensive":[136],"experiments":[137],"show":[138],"that":[139],"achieves":[141],"superior":[142],"alignment":[143],"preferences":[146],"demonstrates":[148,166],"strong":[149],"generalization":[150],"other":[152],"datasets.":[153],"Furthermore,":[154],"fine-tune":[156],"Qwen-Image-Edit":[158],"using":[159],"EditHF-Reward,":[160],"achieving":[161],"significant":[162],"performance":[163],"improvements,":[164],"ability":[168],"serve":[172],"scale-up":[178],"Both":[182],"code":[186],"will":[187],"be":[188],"released":[189],"in":[190],"our":[191],"GitHub":[192],"repository:":[193],"https://github.com/IntMeGroup/EditHF.":[194]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-18T00:00:00"}