{"id":"https://openalex.org/W7155213078","doi":"https://doi.org/10.48550/arxiv.2604.19406","title":"HP-Edit: A Human-Preference Post-Training Framework for Image Editing","display_name":"HP-Edit: A Human-Preference Post-Training Framework for Image Editing","publication_year":2026,"publication_date":"2026-04-21","ids":{"openalex":"https://openalex.org/W7155213078","doi":"https://doi.org/10.48550/arxiv.2604.19406"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.19406","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19406","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2604.19406","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100373584","display_name":"Fan Li","orcid":"https://orcid.org/0000-0002-8771-8992"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119507158","display_name":"Chonghuinan Wang","orcid":"https://orcid.org/0000-0001-9539-2155"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Chonghuinan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134320461","display_name":"Lina Lei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei, Lina","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041580368","display_name":"Yuping Qiu","orcid":"https://orcid.org/0000-0002-3803-1393"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiu, Yuping","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134361177","display_name":"Jiaqi Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Jiaqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133310120","display_name":"Jiaxiu Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Jiaxiu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134218417","display_name":"Xinran Qin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin, Xinran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134231682","display_name":"Zhikai Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Zhikai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111938544","display_name":"Fenglong Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Fenglong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134275294","display_name":"Zhixin Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhixin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102960782","display_name":"Renjing Pei","orcid":"https://orcid.org/0000-0001-7513-6576"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pei, Renjing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134228834","display_name":"Wangmeng Zuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zuo, Wangmeng","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":0.2879999876022339,"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":0.2879999876022339,"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":0.14059999585151672,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.07450000196695328,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6771000027656555},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.6740000247955322},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5896999835968018},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5135999917984009},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.43560001254081726},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4025000035762787},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3937999904155731}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8428999781608582},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6771000027656555},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.6740000247955322},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5896999835968018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5758000016212463},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5135999917984009},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46050000190734863},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.43560001254081726},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4025000035762787},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3937999904155731},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3903000056743622},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.31779998540878296},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3052000105381012},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27619999647140503},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.25769999623298645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.19406","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19406","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.19406","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19406","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Common":[0],"image":[1],"editing":[2,44,61,139,150],"tasks":[3,86],"typically":[4],"adopt":[5],"powerful":[6],"generative":[7],"diffusion":[8],"models":[9,160],"as":[10,25,132,162],"the":[11,133,138],"leading":[12],"paradigm":[13],"for":[14,73,136,147],"real-world":[15,81,149],"content":[16],"editing.":[17,91],"Meanwhile,":[18],"although":[19],"reinforcement":[20],"learning":[21],"(RL)":[22],"methods":[23],"such":[24,161],"Diffusion-DPO":[26],"and":[27,56,77,87,102,129],"Flow-GRPO":[28],"have":[29],"further":[30],"improved":[31],"generation":[32],"quality,":[33],"efficiently":[34,123],"applying":[35],"Reinforcement":[36],"Learning":[37],"from":[38],"Human":[39,74],"Feedback":[40],"(RLHF)":[41],"to":[42,49,59,110,122,130],"diffusion-based":[43],"remains":[45],"largely":[46],"unexplored,":[47],"due":[48],"a":[50,70,80,95,103,125,145],"lack":[51],"of":[52,98],"scalable":[53,126],"human-preference":[54,99],"datasets":[55],"frameworks":[57],"tailored":[58],"diverse":[60],"needs.":[62],"To":[63],"fill":[64],"this":[65],"gap,":[66],"we":[67],"propose":[68],"HP-Edit,":[69],"post-training":[71,137],"framework":[72],"Preference-aligned":[75],"Editing,":[76],"introduce":[78,143],"RealPref-50K,":[79],"dataset":[82,128],"across":[83],"eight":[84],"common":[85,89],"balancing":[88],"object":[90],"Specifically,":[92],"HP-Edit":[93],"leverages":[94],"small":[96],"amount":[97],"scoring":[100],"data":[101],"pretrained":[104],"visual":[105],"large":[106],"language":[107],"model":[108],"(VLM)":[109],"develop":[111],"HP-Scorer--an":[112],"automatic,":[113],"human":[114,170],"preference-aligned":[115],"evaluator.":[116],"We":[117,141],"then":[118],"use":[119],"HP-Scorer":[120],"both":[121],"build":[124],"preference":[127],"serve":[131],"reward":[134],"function":[135],"model.":[140],"also":[142],"RealPref-Bench,":[144],"benchmark":[146],"evaluating":[148],"performance.":[151],"Extensive":[152],"experiments":[153],"demonstrate":[154],"that":[155],"our":[156],"approach":[157],"significantly":[158],"enhances":[159],"Qwen-Image-Edit-2509,":[163],"aligning":[164],"their":[165],"outputs":[166],"more":[167],"closely":[168],"with":[169],"preference.":[171]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-23T00:00:00"}