{"id":"https://openalex.org/W7225418128","doi":"https://doi.org/10.1145/3862336","title":"A Tutorial on Physical AI from a Multimedia Perspective: Part II Cosmos Foundation Model","display_name":"A Tutorial on Physical AI from a Multimedia Perspective: Part II Cosmos Foundation Model","publication_year":2026,"publication_date":"2026-11-06","ids":{"openalex":"https://openalex.org/W7225418128","doi":"https://doi.org/10.1145/3862336"},"language":"en","primary_location":{"id":"doi:10.1145/3862336","doi":"https://doi.org/10.1145/3862336","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3862336","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3862336?download=true","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","dongbi-b","jufo-2","ki-jl-2","norway-2","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3862336?download=true","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100355762","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0001-9982-9887","observed_orcids":["https://orcid.org/0000-0001-9982-9887","https://orcid.org/0000-0002-8798-3198"]},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["University of Ottawa, Canada"],"raw_orcid":"https://orcid.org/0000-0002-8798-3198","affiliations":[{"raw_affiliation_string":"University of Ottawa, Canada","institution_ids":["https://openalex.org/I153718931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011292213","display_name":"Haiwei Dong","orcid":"https://orcid.org/0000-0003-1437-7805","observed_orcids":["https://orcid.org/0000-0003-1437-7805"]},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Haiwei Dong","raw_affiliation_strings":["University of Ottawa and Dayan Technologies, Canada"],"raw_orcid":"https://orcid.org/0000-0003-1437-7805","affiliations":[{"raw_affiliation_string":"University of Ottawa and Dayan Technologies, Canada","institution_ids":["https://openalex.org/I153718931"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109797436","display_name":"Abdulmotaleb El Saddik","orcid":"https://orcid.org/0000-0002-7690-8547","observed_orcids":["https://orcid.org/0000-0002-7690-8547"]},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Abdulmotaleb El Saddik","raw_affiliation_strings":["University of Ottawa, Canada"],"raw_orcid":"https://orcid.org/0000-0002-7690-8547","affiliations":[{"raw_affiliation_string":"University of Ottawa, Canada","institution_ids":["https://openalex.org/I153718931"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I153718931"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6557999849319458,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6557999849319458,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.08579999953508377,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.03620000183582306,"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/physical-ai","display_name":"physical AI","score":0.8360000252723694},{"id":"https://openalex.org/keywords/data-driven-simulation","display_name":"data-driven simulation","score":0.5640000104904175},{"id":"https://openalex.org/keywords/multimodal-foundation-models","display_name":"multimodal foundation models","score":0.5920000076293945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8292999863624573},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6539000272750854},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6442999839782715},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.5213000178337097},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.4575999975204468},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.44679999351501465},{"id":"https://openalex.org/C116672817","wikidata":"https://www.wikidata.org/wiki/Q1454986","display_name":"Physical system","level":2,"score":0.3779999911785126},{"id":"https://openalex.org/C31107917","wikidata":"https://www.wikidata.org/wiki/Q183576","display_name":"Flywheel","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3181000053882599},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2840000092983246},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C2780307871","wikidata":"https://www.wikidata.org/wiki/Q476937","display_name":"Cosmos (plant)","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C179768478","wikidata":"https://www.wikidata.org/wiki/Q1120057","display_name":"Cyber-physical system","level":2,"score":0.25119999051094055},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3862336","doi":"https://doi.org/10.1145/3862336","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3862336","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3862336?download=true","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","dongbi-b","jufo-2","ki-jl-2","norway-2","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3862336","doi":"https://doi.org/10.1145/3862336","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3862336","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3862336?download=true","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","dongbi-b","jufo-2","ki-jl-2","norway-2","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225418128.pdf","grobid_xml":"https://content.openalex.org/works/W7225418128.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W2615547864","https://openalex.org/W3097999908","https://openalex.org/W3193576605","https://openalex.org/W4304195432","https://openalex.org/W4322718191","https://openalex.org/W4327810158","https://openalex.org/W4399424845","https://openalex.org/W4401307635","https://openalex.org/W4408555470","https://openalex.org/W4413155399","https://openalex.org/W4415273528","https://openalex.org/W4415935378","https://openalex.org/W4416078238","https://openalex.org/W4416780398","https://openalex.org/W4417261359","https://openalex.org/W6910652256","https://openalex.org/W6966680242","https://openalex.org/W7104607800","https://openalex.org/W7128357184","https://openalex.org/W7163380451"],"related_works":["https://openalex.org/W4406191642","https://openalex.org/W4415546042","https://openalex.org/W7225324369","https://openalex.org/W7163380451","https://openalex.org/W7214562325","https://openalex.org/W6966680242","https://openalex.org/W7214521047","https://openalex.org/W7168142037","https://openalex.org/W7164528053","https://openalex.org/W7214555236"],"abstract_inverted_index":{"Physical":[0,67],"AI":[1,68],"aims":[2],"to":[3,6,60],"enable":[4],"systems":[5],"perceive,":[7],"reason,":[8],"and":[9,24,42,79,95],"act":[10],"in":[11,91],"the":[12],"unstructured":[13],"physical":[14,92],"world,":[15],"yet":[16,34],"it":[17],"faces":[18],"bottlenecks":[19],"of":[20,39],"scarce":[21],"real-world":[22],"data":[23,64],"high":[25],"deployment":[26],"risks.":[27],"Traditional":[28],"hand-engineered":[29],"simulators":[30],"provide":[31],"controllable":[32],"environments":[33],"struggle":[35],"with":[36],"scalable":[37],"coverage":[38],"diverse":[40],"scenes":[41],"long-tail":[43],"scenarios.":[44],"Cosmos":[45],"addresses":[46],"these":[47],"challenges":[48],"as":[49],"a":[50,62,83],"data-driven":[51],"world":[52,89],"foundation":[53],"model":[54],"platform,":[55],"unifying":[56],"generation-":[57],"verification":[58],"loop":[59],"form":[61],"closed-loop":[63],"flywheel":[65],"for":[66,86],"development.":[69],"This":[70],"tutorial":[71],"systematically":[72],"introduces":[73],"Cosmos's":[74],"multi-modal":[75],"design,":[76],"core":[77],"components,":[78],"practical":[80],"deployment,":[81],"offering":[82],"comprehensive":[84],"guide":[85],"leveraging":[87],"learned":[88],"models":[90],"system":[93],"training":[94],"evaluation.":[96]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-11-07T00:00:00"}
