{"id":"https://openalex.org/W4415428216","doi":"https://doi.org/10.3233/faia251125","title":"Representing Positional Information in Generative World Models for Object Manipulation","display_name":"Representing Positional Information in Generative World Models for Object Manipulation","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428216","doi":"https://doi.org/10.3233/faia251125"},"language":"en","primary_location":{"id":"doi:10.3233/faia251125","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251125","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia251125","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033728828","display_name":"Stefano Ferraro","orcid":"https://orcid.org/0000-0001-7193-0668"},"institutions":[{"id":"https://openalex.org/I2801227569","display_name":"Ghent University Hospital","ror":"https://ror.org/00xmkp704","country_code":"BE","type":"healthcare","lineage":["https://openalex.org/I2801227569"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Stefano Ferraro","raw_affiliation_strings":["Ghent University, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University, Belgium","institution_ids":["https://openalex.org/I2801227569"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008371078","display_name":"Pietro Mazzaglia","orcid":"https://orcid.org/0000-0003-3319-5986"},"institutions":[{"id":"https://openalex.org/I2801227569","display_name":"Ghent University Hospital","ror":"https://ror.org/00xmkp704","country_code":"BE","type":"healthcare","lineage":["https://openalex.org/I2801227569"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Pietro Mazzaglia","raw_affiliation_strings":["Ghent University, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University, Belgium","institution_ids":["https://openalex.org/I2801227569"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071221406","display_name":"Tim Verbelen","orcid":"https://orcid.org/0000-0003-2731-7262"},"institutions":[{"id":"https://openalex.org/I4210164577","display_name":"Veralase (United States)","ror":"https://ror.org/058gnjg35","country_code":"US","type":"company","lineage":["https://openalex.org/I4210164577"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tim Verbelen","raw_affiliation_strings":["VERSES, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VERSES, United States","institution_ids":["https://openalex.org/I4210164577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032558375","display_name":"Bart Dhoedt","orcid":"https://orcid.org/0000-0002-7271-7479"},"institutions":[{"id":"https://openalex.org/I2801227569","display_name":"Ghent University Hospital","ror":"https://ror.org/00xmkp704","country_code":"BE","type":"healthcare","lineage":["https://openalex.org/I2801227569"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Bart Dhoedt","raw_affiliation_strings":["Ghent University, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University, Belgium","institution_ids":["https://openalex.org/I2801227569"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041629023","display_name":"Sai Rajeswar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099137","display_name":"Research Canada","ror":"https://ror.org/0103eqz62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210099137"]},{"id":"https://openalex.org/I4210167196","display_name":"Minnow Environmental (Canada)","ror":"https://ror.org/05petyd50","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210167196"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sai Rajeswar","raw_affiliation_strings":["ServiceNow Research, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ServiceNow Research, Canada","institution_ids":["https://openalex.org/I4210167196","https://openalex.org/I4210099137"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.71445463,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T13382","display_name":"Robotics and Automated Systems","score":0.9625999927520752,"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/T13382","display_name":"Robotics and Automated Systems","score":0.9625999927520752,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9588000178337097,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9269999861717224,"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/object","display_name":"Object (grammar)","score":0.7558000087738037},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5867999792098999},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5584999918937683},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.49380001425743103},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.42890000343322754},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.37310001254081726}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7734000086784363},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7558000087738037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6473000049591064},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5867999792098999},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5584999918937683},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.49380001425743103},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.42890000343322754},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42170000076293945},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3644999861717224},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.34599998593330383},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.273499995470047},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2687000036239624},{"id":"https://openalex.org/C2778757428","wikidata":"https://www.wikidata.org/wiki/Q1250464","display_name":"Realm","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.2531999945640564}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/faia251125","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251125","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"pmh:oai:archive.ugent.be:01K94W6Y5BQGFHV4KZ17AKG749","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01K94W6Y5BQGFHV4KZ17AKG749","pdf_url":"https://biblio.ugent.be/publication/01K94W6Y5BQGFHV4KZ17AKG749/file/01K94WAMA1SZCASV3P73VX0D83.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9781643686318","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.3233/faia251125","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251125","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321730","display_name":"Fonds Wetenschappelijk Onderzoek","ror":"https://ror.org/03qtxy027"},{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Object":[0],"manipulation":[1,46,168],"capabilities":[2],"are":[3,163],"essential":[4],"skills":[5],"that":[6,95,131],"set":[7],"apart":[8],"embodied":[9],"agents":[10,99],"engaging":[11],"with":[12,28],"the":[13,17,59,66,71,82,144,150],"world,":[14],"especially":[15,80],"in":[16,32,52,70],"realm":[18],"of":[19,26,61,68,110,146,152],"robotics.":[20],"The":[21],"ability":[22],"to":[23,41,44,100,143,174],"predict":[24],"outcomes":[25],"interactions":[27],"objects":[29],"is":[30],"paramount":[31],"this":[33,62,111],"setting.":[34],"Although":[35],"model-based":[36,98,176],"control":[37,177],"methods":[38,162],"have":[39,49],"started":[40],"be":[42],"employed":[43],"tackle":[45],"tasks,":[47],"they":[48],"faced":[50],"challenges":[51],"accurately":[53],"manipulating":[54],"objects.":[55],"As":[56],"we":[57,64],"analyze":[58],"causes":[60],"limitation,":[63],"identify":[65],"cause":[67],"underperformance":[69],"way":[72],"current":[73,175],"world":[74,97,115],"models":[75],"represent":[76],"crucial":[77],"positional":[78,135],"information,":[79],"about":[81],"target\u2019s":[83],"goal":[84,138],"specification":[85,151],"for":[86,113,137],"object":[87,103,134],"positioning":[88,104],"tasks.":[89,105],"We":[90,106],"introduce":[91],"a":[92,158],"general":[93],"approach":[94,112],"empowers":[96],"effectively":[101],"solve":[102],"propose":[107],"two":[108],"declinations":[109],"generative":[114],"models:":[116],"position-conditioned":[117],"(PCP)":[118],"and":[119],"latent-conditioned":[120],"(LCP)":[121],"policy":[122],"learning.":[123],"In":[124],"particular,":[125],"LCP":[126],"employs":[127],"object-centric":[128],"latent":[129],"representations":[130],"explicitly":[132],"capture":[133],"information":[136],"specification.":[139],"This":[140],"naturally":[141],"leads":[142],"emergence":[145],"multimodal":[147],"capabilities,":[148],"enabling":[149],"goals":[153],"through":[154],"spatial":[155],"coordinates":[156],"or":[157],"visual":[159],"goal.":[160],"Our":[161],"rigorously":[164],"evaluated":[165],"across":[166],"several":[167],"environments,":[169],"showing":[170],"favorable":[171],"performance":[172],"compared":[173],"approaches.":[178]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-24T00:00:00"}