{"id":"https://openalex.org/W7225623647","doi":"https://doi.org/10.5281/zenodo.24078218","title":"PerceptionExperienceGPT: A General-Purpose Multimodal Artificial Intelligence Framework for Embodied, Spatial, Visual, Contextual, and Experiential Understanding","display_name":"PerceptionExperienceGPT: A General-Purpose Multimodal Artificial Intelligence Framework for Embodied, Spatial, Visual, Contextual, and Experiential Understanding","publication_year":2026,"publication_date":"2026-11-09","ids":{"openalex":"https://openalex.org/W7225623647","doi":"https://doi.org/10.5281/zenodo.24078218"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24078218","doi":"https://doi.org/10.5281/zenodo.24078218","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24078218","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.24078218","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100638045","display_name":"Jincheng Zhang","orcid":"https://orcid.org/0000-0001-7332-6704","observed_orcids":["https://orcid.org/0000-0001-7332-6704","https://orcid.org/0009-0005-1860-0009"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhang, Jincheng","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0005-1860-0009","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5100638045"],"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8804000020027161,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8804000020027161,"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/T14381","display_name":"Psychiatry, Mental Health, Neuroscience","score":0.10379999876022339,"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/T13062","display_name":"Cognitive Computing and Networks","score":0.004800000227987766,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/multimodal-artificial-intelligence","display_name":"multimodal AI","score":0.902999997138977},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"embodied cognition","score":0.8529999852180481},{"id":"https://openalex.org/keywords/spatial-representation","display_name":"spatial representation","score":0.6259999871253967},{"id":"https://openalex.org/keywords/visual-perception","display_name":"visual perception","score":0.8119999766349792},{"id":"https://openalex.org/keywords/contextual-understanding","display_name":"contextual understanding","score":0.7710000276565552},{"id":"https://openalex.org/keywords/episodic-memory","display_name":"episodic memory","score":0.9610000252723694},{"id":"https://openalex.org/keywords/emotion-understanding","display_name":"emotional understanding","score":0.6069999933242798},{"id":"https://openalex.org/keywords/narrative-comprehension","display_name":"narrative comprehension","score":0.847000002861023},{"id":"https://openalex.org/keywords/mental-simulation","display_name":"mental simulation","score":0.9909999966621399},{"id":"https://openalex.org/keywords/cross-modal-integration","display_name":"cross-modal integration","score":0.8259999752044678},{"id":"https://openalex.org/keywords/human-ai-interaction","display_name":"human-AI interaction","score":0.7639999985694885}],"concepts":[{"id":"https://openalex.org/C37228920","wikidata":"https://www.wikidata.org/wiki/Q1307600","display_name":"Experiential learning","level":2,"score":0.6952999830245972},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5307999849319458},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.49720001220703125},{"id":"https://openalex.org/C20854674","wikidata":"https://www.wikidata.org/wiki/Q4386060","display_name":"Cognitive architecture","level":3,"score":0.4848000109195709},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4731999933719635},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.47099998593330383},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.46380001306533813},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.45410001277923584},{"id":"https://openalex.org/C96199812","wikidata":"https://www.wikidata.org/wiki/Q2145290","display_name":"Mental representation","level":3,"score":0.4016000032424927},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3882000148296356},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C87868495","wikidata":"https://www.wikidata.org/wiki/Q750843","display_name":"Information processing","level":2,"score":0.365200012922287},{"id":"https://openalex.org/C105409693","wikidata":"https://www.wikidata.org/wiki/Q5937824","display_name":"Human intelligence","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C9114305","wikidata":"https://www.wikidata.org/wiki/Q1428317","display_name":"Situational ethics","level":2,"score":0.36039999127388},{"id":"https://openalex.org/C161407221","wikidata":"https://www.wikidata.org/wiki/Q4382939","display_name":"Cognitive model","level":3,"score":0.3582000136375427},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3580999970436096},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C4051589","wikidata":"https://www.wikidata.org/wiki/Q860959","display_name":"Mental image","level":3,"score":0.3562999963760376},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3377000093460083},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C123353603","wikidata":"https://www.wikidata.org/wiki/Q5421070","display_name":"Experiential knowledge","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2842999994754791},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.27869999408721924},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.25609999895095825},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24078218","doi":"https://doi.org/10.5281/zenodo.24078218","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24078218","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},{"id":"doi:10.5281/zenodo.24078219","doi":"https://doi.org/10.5281/zenodo.24078219","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24078219","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"}],"best_oa_location":{"id":"doi:10.5281/zenodo.24078218","doi":"https://doi.org/10.5281/zenodo.24078218","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24078218","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7225621912","https://openalex.org/W7212023571","https://openalex.org/W7225656289","https://openalex.org/W7220673741","https://openalex.org/W2397501176","https://openalex.org/W7019339918","https://openalex.org/W7166707947","https://openalex.org/W7225621054","https://openalex.org/W7108654851","https://openalex.org/W7117970439"],"abstract_inverted_index":{"Contemporary":[0],"generative":[1],"artificial":[2,100,181,301],"intelligence":[3,101,182],"systems":[4,261],"have":[5],"achieved":[6],"substantial":[7],"progress":[8],"in":[9,73,274],"language":[10],"understanding,":[11],"visual":[12,50],"recognition,":[13],"multimodal":[14,99,161],"interaction,":[15],"and":[16,58,82,109,149,173,206,223,284,293,299,306,309,312],"complex":[17],"reasoning.":[18],"Nevertheless,":[19],"a":[20,93,97,157,234,291],"fundamental":[21],"challenge":[22],"remains:":[23],"understanding":[24],"the":[25,59,113,127,252],"world":[26],"requires":[27],"more":[28],"than":[29],"processing":[30],"symbolic":[31],"information":[32,72,185],"or":[33,318],"identifying":[34],"statistical":[35],"relationships":[36],"between":[37],"input":[38],"tokens.":[39],"Human":[40],"cognition":[41],"is":[42,179,211,269,321],"deeply":[43],"associated":[44],"with":[45],"bodily":[46],"experience,":[47],"spatial":[48,198],"representations,":[49],"perception,":[51,162],"situational":[52],"awareness,":[53],"emotional":[54],"information,":[55,226],"narrative":[56],"structures,":[57],"mental":[60],"simulation":[61],"of":[62,112,254],"possible":[63],"events.":[64],"These":[65,152],"cognitive":[66,133,169],"processes":[67],"allow":[68],"individuals":[69],"to":[70,75,104,189,196,213,231,233],"interpret":[71,184],"relation":[74],"their":[76],"surroundings,":[77],"previous":[78],"experiences,":[79],"physical":[80],"constraints,":[81],"anticipated":[83],"consequences.":[84,208],"Inspired":[85],"by":[86],"these":[87],"characteristics,":[88],"this":[89,324],"paper":[90,289],"proposes":[91,303],"PerceptionExperienceGPT,":[92],"conceptual":[94,292,325],"framework":[95,129,210],"for":[96,271,297],"general-purpose":[98,272],"system":[102],"designed":[103,212],"develop":[105],"richer":[106],"perceptual,":[107],"experiential,":[108],"context-sensitive":[110],"representations":[111],"world.":[114],"Unlike":[115],"conventional":[116],"question\u2013response":[117],"architectures":[118],"that":[119,180,259],"primarily":[120],"transform":[121],"user":[122],"inputs":[123],"into":[124],"linguistic":[125],"outputs,":[126],"proposed":[128,267],"integrates":[130],"eight":[131],"interconnected":[132],"capabilities:":[134],"Embodied":[135],"Thinking,":[136,138,140,142,144,146,148],"Spatial":[137],"Visual":[139],"Contextual":[141],"Experiential":[143],"Emotional":[145],"Narrative":[147],"Mental":[150],"Simulation.":[151],"capabilities":[153],"are":[154],"organized":[155],"within":[156],"unified":[158],"architecture":[159,268],"comprising":[160],"perceptual":[163,229],"representation,":[164],"experiential":[165,204,242],"memory,":[166],"contextual":[167],"interpretation,":[168],"simulation,":[170],"cross-modal":[171],"integration,":[172],"response":[174],"generation.":[175],"A":[176],"central":[177],"proposition":[178],"should":[183],"not":[186],"only":[187],"according":[188,195],"its":[190,197],"semantic":[191],"content":[192],"but":[193],"also":[194],"configuration,":[199],"temporal":[200],"development,":[201],"environmental":[202],"circumstances,":[203],"associations,":[205],"potential":[207],"The":[209,266],"process":[214],"multiple":[215],"modalities,":[216],"including":[217],"text,":[218],"images,":[219],"video,":[220],"audio,":[221],"speech,":[222],"other":[224],"sensor-derived":[225],"allowing":[227],"different":[228],"channels":[230],"contribute":[232],"shared":[235],"internal":[236],"representation.":[237],"Furthermore,":[238],"it":[239],"introduces":[240],"an":[241],"modeling":[243],"mechanism":[244],"through":[245],"which":[246],"previously":[247],"encountered":[248],"situations":[249,256],"can":[250],"inform":[251],"interpretation":[253],"new":[255],"without":[257],"assuming":[258],"computational":[260],"possess":[262],"human":[263],"subjective":[264],"experience.":[265],"intended":[270],"applications":[273],"education,":[275],"robotics,":[276],"scientific":[277],"research,":[278],"healthcare":[279],"support,":[280],"intelligent":[281],"assistants,":[282],"engineering,":[283],"everyday":[285],"human\u2013AI":[286],"interaction.":[287],"This":[288],"establishes":[290],"technically":[294],"oriented":[295],"foundation":[296],"perception-":[298],"experience-oriented":[300],"intelligence,":[302],"mathematical":[304],"formulations":[305],"research":[307],"hypotheses,":[308],"identifies":[310],"implementation":[311],"evaluation":[313],"directions.":[314],"No":[315],"experimental":[316],"performance":[317],"demonstrated":[319],"superiority":[320],"claimed":[322],"at":[323],"stage.":[326]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-10T00:00:00"}
