{"id":"https://openalex.org/W7160270219","doi":"https://doi.org/10.1109/wacv61042.2026.00081","title":"DICE: Discrete Inversion Enabling Controllable Editing for Masked Generative Models","display_name":"DICE: Discrete Inversion Enabling Controllable Editing for Masked Generative Models","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160270219","doi":"https://doi.org/10.1109/wacv61042.2026.00081"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"article","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/A5101730102","display_name":"Xiaoxiao He","orcid":"https://orcid.org/0000-0003-4581-0712"},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Xiaoxiao He","raw_affiliation_strings":["Rutgers University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5096517854","display_name":"\u7a32\u6cc9","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Quan Dao","raw_affiliation_strings":["Rutgers University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016596228","display_name":"Ligong Han","orcid":"https://orcid.org/0000-0003-3166-0848"},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ligong Han","raw_affiliation_strings":["Rutgers University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135391523","display_name":"Song Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Song Wen","raw_affiliation_strings":["Rutgers University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051750999","display_name":"Minhao Bai","orcid":"https://orcid.org/0009-0000-9069-6053"},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Minhao Bai","raw_affiliation_strings":["Rutgers University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135335041","display_name":"Di Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Di Liu","raw_affiliation_strings":["Rutgers University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135283746","display_name":"Han Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Han Zhang","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034751153","display_name":"Felix Juefei-Xu","orcid":"https://orcid.org/0000-0002-0857-8611"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Felix Juefei-Xu","raw_affiliation_strings":["NYU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NYU","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103012948","display_name":"Chaowei Tan","orcid":"https://orcid.org/0000-0002-5852-7118"},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Chaowei Tan","raw_affiliation_strings":["Rutgers University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135383186","display_name":"Bo Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I1330693074","display_name":"Walmart (United States)","ror":"https://ror.org/04j0gge90","country_code":"US","type":"company","lineage":["https://openalex.org/I1330693074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["Walmart Global Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Walmart Global Tech","institution_ids":["https://openalex.org/I1330693074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065576006","display_name":"Martin Renqiang Min","orcid":"https://orcid.org/0000-0002-8563-6133"},"institutions":[{"id":"https://openalex.org/I4210107353","display_name":"NEC (United States)","ror":"https://ror.org/01v791m31","country_code":"US","type":"company","lineage":["https://openalex.org/I118347220","https://openalex.org/I4210107353"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Renqiang Min","raw_affiliation_strings":["NEC Labs America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Labs America","institution_ids":["https://openalex.org/I4210107353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100456986","display_name":"Kang Li","orcid":"https://orcid.org/0000-0002-8136-9816"},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Kang Li","raw_affiliation_strings":["Rutgers University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040705509","display_name":"Faez Ahmed","orcid":"https://orcid.org/0000-0002-5227-2628"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Faez Ahmed","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135313806","display_name":"Akash Srivastava","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Akash Srivastava","raw_affiliation_strings":["MIT-IBM Watson AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT-IBM Watson AI Lab","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101819058","display_name":"Hongdong Li","orcid":"https://orcid.org/0000-0002-5407-4211"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongdong Li","raw_affiliation_strings":["ANU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ANU","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068865316","display_name":"Junzhou Huang","orcid":"https://orcid.org/0000-0002-9548-1227"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junzhou Huang","raw_affiliation_strings":["UT Arlington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UT Arlington","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135359083","display_name":"Dimitris N. Metaxas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Dimitris N. Metaxas","raw_affiliation_strings":["Rutgers University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":17,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.6918429,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"762","last_page":"772"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.5065000057220459,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.5065000057220459,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T11986","display_name":"Scientific Computing and Data Management","score":0.03819999843835831,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.03530000150203705,"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/inversion","display_name":"Inversion (geology)","score":0.5238999724388123},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.2777999937534332},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2766000032424927},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.2718999981880188},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.26019999384880066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5623000264167786},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.5238999724388123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45680001378059387},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42660000920295715},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2777999937534332},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26019999384880066},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2549999952316284},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2962785568","https://openalex.org/W2970641574","https://openalex.org/W3180355996","https://openalex.org/W3216352822","https://openalex.org/W4312254454","https://openalex.org/W4312388283","https://openalex.org/W4312546849","https://openalex.org/W4313021454","https://openalex.org/W4385527149","https://openalex.org/W4386075993","https://openalex.org/W4386076215","https://openalex.org/W4386076532","https://openalex.org/W4386113271","https://openalex.org/W4387211622","https://openalex.org/W4390872341","https://openalex.org/W4390872636","https://openalex.org/W4390873054","https://openalex.org/W4390873260","https://openalex.org/W4394596927","https://openalex.org/W4402716004","https://openalex.org/W4402753991","https://openalex.org/W4402816681","https://openalex.org/W4405003063","https://openalex.org/W4409262782","https://openalex.org/W4415796024","https://openalex.org/W4415800710","https://openalex.org/W4415800813","https://openalex.org/W7133216024","https://openalex.org/W7133249391"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,10,21,60,129],"discrete":[3,45,130],"diffusion":[4,46,54,69],"models":[5,95],"have":[6],"demonstrated":[7],"strong":[8],"performance":[9],"image":[11,90],"generation":[12],"and":[13,52,64,75,91,101],"masked":[14,50],"language":[15],"modeling,":[16],"yet":[17],"they":[18],"remain":[19],"limited":[20],"their":[22],"capacity":[23],"for":[24,33,44,125],"controlled":[25],"content":[26,127],"editing.":[27],"We":[28],"propose":[29],"DICE":[30,106],"(Discrete":[31],"Inversion":[32],"Controllable":[34],"Editing),":[35],"a":[36],"novel":[37],"framework":[38],"that":[39,105],"pioneers":[40],"precise":[41],"inversion":[42],"capabilities":[43],"models,":[47],"including":[48],"both":[49,72],"generative":[51],"multinomial":[53],"variants.":[55],"Our":[56],"key":[57],"innovation":[58],"lies":[59],"capturing":[61],"noise":[62],"sequences":[63],"masking":[65],"patterns":[66],"during":[67],"reverse":[68],"process,":[70],"enabling":[71],"accurate":[73],"reconstruction":[74],"flexible":[76],"editing":[77,118],"without":[78],"relying":[79],"on":[80],"predefined":[81],"masks":[82],"or":[83],"attention-based":[84],"manipulations.":[85],"Through":[86],"comprehensive":[87],"experiments":[88],"across":[89],"text":[92],"modalities":[93],"using":[94],"such":[96],"as":[97],"Paella,":[98],"VQ-Diffusion,":[99],"RoBERTa":[100],"LLaDA,":[102],"we":[103],"demonstrate":[104],"successfully":[107],"maintains":[108],"high":[109],"fidelity":[110],"to":[111],"the":[112],"original":[113],"data":[114],"while":[115],"significantly":[116],"expanding":[117],"capabilities.":[119],"These":[120],"results":[121],"establish":[122],"new":[123],"possibilities":[124],"fine-grained":[126],"manipulation":[128],"spaces.":[131]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-06T00:00:00"}
