{"id":"https://openalex.org/W7161815015","doi":"https://doi.org/10.48550/arxiv.2605.19319","title":"SWEET: Sparse World Modeling with Image Editing for Embodied Task Execution","display_name":"SWEET: Sparse World Modeling with Image Editing for Embodied Task Execution","publication_year":2026,"publication_date":"2026-05-19","ids":{"openalex":"https://openalex.org/W7161815015","doi":"https://doi.org/10.48550/arxiv.2605.19319"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.19319","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19319","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.2605.19319","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136575498","display_name":"Yiren Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Yiren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136521211","display_name":"Yihan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yihan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136520413","display_name":"Xiyao Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng, Xiyao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136517567","display_name":"Zhuoran Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Zhuoran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136506546","display_name":"Mike Zheng Shou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shou, Mike Zheng","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/T10653","display_name":"Robot Manipulation and Learning","score":0.7166000008583069,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.7166000008583069,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.05790000036358833,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.050700001418590546,"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/executable","display_name":"Executable","score":0.7242000102996826},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6686999797821045},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.6675999760627747},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.59170001745224},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5257999897003174},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.48980000615119934},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4602999985218048},{"id":"https://openalex.org/keywords/video-editing","display_name":"Video editing","score":0.4528999924659729},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4481000006198883}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8277999758720398},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.7242000102996826},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6686999797821045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6682000160217285},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.6675999760627747},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6132000088691711},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.59170001745224},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5257999897003174},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.48980000615119934},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4602999985218048},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.4528999924659729},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4481000006198883},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4431999921798706},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.3887999951839447},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.37929999828338623},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.35929998755455017},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.31279999017715454},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.31049999594688416},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.31049999594688416},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.26669999957084656},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.2655999958515167},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C99740376","wikidata":"https://www.wikidata.org/wiki/Q17092520","display_name":"Interactive visual analysis","level":4,"score":0.2590000033378601},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.258899986743927},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.19319","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19319","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.2605.19319","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19319","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":{"Visual":[0],"prediction":[1,198],"has":[2],"emerged":[3],"as":[4,59],"a":[5,41,79,126,135,181,206,222],"promising":[6,223],"paradigm":[7],"for":[8,31,64,227],"embodied":[9,228],"control,":[10],"where":[11],"future":[12,70],"observations":[13],"are":[14],"generated":[15],"and":[16,28,88,100,114,149,174,191,201,204,224],"then":[17,159],"translated":[18],"into":[19,164],"actions.":[20],"However,":[21],"dense":[22,73],"video":[23,74,84],"generation":[24,85],"is":[25,221],"computationally":[26],"expensive":[27],"often":[29],"unnecessary":[30],"many":[32],"manipulation":[33,66,139],"tasks,":[34],"whose":[35],"progress":[36],"can":[37,57],"be":[38],"summarized":[39],"by":[40,67,120],"small":[42],"number":[43],"of":[44,137],"task-relevant":[45,138],"visual":[46,61,112,129,176,229],"states.":[47],"In":[48],"this":[49,121],"work,":[50],"we":[51,123,178],"study":[52],"whether":[53],"image":[54,90,103,143,219],"editing":[55,91,104,220],"models":[56,63],"serve":[58],"sparse":[60,128],"world":[62],"robot":[65,215],"predicting":[68],"task-level":[69,108],"states":[71],"without":[72],"rollout.":[75],"We":[76],"first":[77],"conduct":[78],"controlled":[80],"comparison":[81],"between":[82,172],"the":[83,89,95,170],"model":[86,92],"Wan2.2":[87],"FLUX-Kontext":[93],"under":[94],"same":[96],"robotic":[97],"data":[98],"setting,":[99],"find":[101],"that":[102,132,194,218],"produces":[105],"more":[106],"reliable":[107],"keyframes":[109,140,163],"with":[110,184],"better":[111],"fidelity":[113],"substantially":[115],"lower":[116],"inference":[117],"cost.":[118],"Motivated":[119],"observation,":[122],"propose":[124],"SWEET,":[125],"one-shot":[127],"planning":[130,212],"framework":[131],"progressively":[133],"generates":[134],"sequence":[136],"through":[141],"successive":[142],"editing,":[144],"conditioned":[145],"on":[146,189],"language":[147],"instructions":[148],"optional":[150],"arrow-based":[151],"spatial":[152],"guidance.":[153],"A":[154],"goal-conditioned":[155],"diffusion":[156],"action":[157,166],"predictor":[158],"converts":[160],"adjacent":[161],"imagined":[162],"executable":[165,214],"chunks.":[167],"To":[168],"reduce":[169],"mismatch":[171],"real":[173],"edited":[175,186],"subgoals,":[177],"further":[179],"introduce":[180],"mixed-training":[182],"strategy":[183],"filtered":[185],"targets.":[187],"Experiments":[188],"DROID":[190],"RoboMimic":[192],"show":[193],"SWEET":[195],"improves":[196],"keyframe":[197,211],"across":[199],"seen":[200],"unseen":[202],"scenes":[203],"enables":[205],"full":[207],"pipeline":[208],"from":[209],"sequential":[210],"to":[213],"actions,":[216],"suggesting":[217],"underexplored":[225],"direction":[226],"prediction.":[230]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-21T00:00:00"}