{"id":"https://openalex.org/W7165373886","doi":"https://doi.org/10.48550/arxiv.2606.19531","title":"ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?","display_name":"ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?","publication_year":2026,"publication_date":"2026-06-17","ids":{"openalex":"https://openalex.org/W7165373886","doi":"https://doi.org/10.48550/arxiv.2606.19531"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.19531","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.19531","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.2606.19531","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139020547","display_name":"Yuyang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yuyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138990520","display_name":"Wenyao Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Wenyao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139024775","display_name":"Zekun Qi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi, Zekun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138970281","display_name":"He Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139013935","display_name":"Haitao Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Haitao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138967480","display_name":"Jingbo Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jingbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139011586","display_name":"Yao Mu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mu, Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030018760","display_name":"Xiaomin Yang","orcid":"https://orcid.org/0000-0002-5593-5108"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Xiaokang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139023048","display_name":"Wenjun Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Wenjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139009738","display_name":"Xin Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Xin","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":0.5480999946594238,"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":0.5480999946594238,"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":0.12049999833106995,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.05380000174045563,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5877000093460083},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5464000105857849},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5292999744415283},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.48969998955726624},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4823000133037567},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4359000027179718},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.37400001287460327},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.36800000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8102999925613403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6305999755859375},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5877000093460083},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5464000105857849},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5292999744415283},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5231999754905701},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.48969998955726624},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4823000133037567},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4359000027179718},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3840999901294708},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.37400001287460327},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.36800000071525574},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.35839998722076416},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.3537999987602234},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2865000069141388},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25519999861717224},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.19531","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.19531","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.2606.19531","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.19531","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":{"World":[0],"Action":[1],"Models":[2],"(WAMs)":[3],"commonly":[4],"rely":[5],"on":[6,36,104,139,194],"video":[7,32,65,87],"generation":[8],"to":[9,86,98,113,177,181,205],"bridge":[10],"visual":[11,107,115],"world":[12,60],"modeling":[13],"and":[14,39,42,109,159,170,179],"robot":[15,81],"control.":[16],"However,":[17],"video-based":[18,184,206],"WAMs":[19,162],"face":[20],"three":[21],"coupled":[22],"limitations:":[23],"dense":[24],"multi-frame":[25],"future":[26,44],"tokens":[27],"make":[28],"inference":[29,130],"costly,":[30],"full":[31],"prediction":[33],"spends":[34],"capacity":[35],"action-irrelevant":[37],"temporal":[38],"appearance":[40],"details,":[41],"long-horizon":[43],"imagination":[45],"may":[46],"introduce":[47],"errors":[48],"that":[49,74,190],"mislead":[50],"action":[51,61,82,137],"prediction.":[52,83],"These":[53],"issues":[54],"raise":[55],"a":[56,70,92,100,135,150],"simple":[57,71],"question:":[58],"Does":[59],"model":[62,99],"really":[63],"need":[64],"generation?":[66],"We":[67],"propose":[68],"ImageWAM,":[69],"WAM":[72],"framework":[73],"repurposes":[75],"pretrained":[76],"image":[77,89,199],"editing":[78,90,191,200],"models":[79],"for":[80],"In":[84,120],"contrast":[85],"generation,":[88],"provides":[91],"better-matched":[93],"prior:":[94],"it":[95,133],"only":[96],"needs":[97],"target-frame":[101],"transformation,":[102],"focuses":[103],"action-relevant":[105],"current-to-target":[106],"differences,":[108],"grounds":[110],"task":[111],"instructions":[112],"localized":[114],"changes":[116],"through":[117],"edit":[118],"pretraining.":[119],"practice,":[121],"ImageWAM":[122,154],"does":[123],"not":[124],"decode":[125],"the":[126,140],"target":[127],"frame":[128],"at":[129],"time;":[131],"instead,":[132],"conditions":[134],"flow-matching":[136],"expert":[138],"KV":[141],"caches":[142,192],"produced":[143],"by":[144],"image-editing":[145],"denoising,":[146],"using":[147],"them":[148],"as":[149,201],"compact":[151],"world-action":[152,207],"context.":[153],"outperforms":[155],"standard":[156],"VLA":[157],"baselines":[158],"matching":[160],"competitive":[161],"without":[163],"additional":[164],"policy":[165],"pretraining":[166],"across":[167],"different":[168],"simulator":[169],"real-world":[171],"experiments.":[172],"It":[173],"also":[174],"reduces":[175],"FLOPs":[176],"1/6":[178],"latency":[180],"1/4":[182],"of":[183],"WAMs.":[185],"Attention":[186],"analysis":[187],"further":[188],"shows":[189],"focus":[193],"task-relevant":[195],"change":[196],"regions,":[197],"supporting":[198],"an":[202],"effective":[203],"alternative":[204],"modeling.":[208]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-20T00:00:00"}