{"id":"https://openalex.org/W4400104329","doi":"https://doi.org/10.1109/iccv51701.2025.01040","title":"Human-Object Interaction from Human-level Instructions","display_name":"Human-Object Interaction from Human-level Instructions","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4400104329","doi":"https://doi.org/10.1109/iccv51701.2025.01040"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.17840","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064963854","display_name":"Zhen Wu","orcid":"https://orcid.org/0000-0003-0758-9463"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhen Wu","raw_affiliation_strings":["Stanford University,Stanford,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University,Stanford,USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009234134","display_name":"Jiaman Li","orcid":"https://orcid.org/0000-0002-1261-3248"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaman Li","raw_affiliation_strings":["Stanford University,Stanford,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University,Stanford,USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Pei Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pei Xu","raw_affiliation_strings":["Stanford University,Stanford,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University,Stanford,USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":null,"display_name":"C. Karen Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Karen Liu","raw_affiliation_strings":["Stanford University,Stanford,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University,Stanford,USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11176","last_page":"11186"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.957099974155426,"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":0.957099974155426,"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/T12031","display_name":"Speech and dialogue systems","score":0.9277999997138977,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9272000193595886,"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":0.6380701065063477},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5495742559432983},{"id":"https://openalex.org/keywords/human-interaction","display_name":"Human interaction","score":0.42104610800743103},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3699970841407776},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23654240369796753}],"concepts":[{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6380701065063477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5495742559432983},{"id":"https://openalex.org/C2987082051","wikidata":"https://www.wikidata.org/wiki/Q223642","display_name":"Human interaction","level":2,"score":0.42104610800743103},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3699970841407776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23654240369796753}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2406.17840","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.17840","pdf_url":"https://arxiv.org/pdf/2406.17840","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2406.17840","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.17840","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":"pmh:oai:arXiv.org:2406.17840","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.17840","pdf_url":"https://arxiv.org/pdf/2406.17840","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400104329.pdf","grobid_xml":"https://content.openalex.org/works/W4400104329.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2312482766","https://openalex.org/W4212985936","https://openalex.org/W2515846482","https://openalex.org/W2015283959","https://openalex.org/W1505673007","https://openalex.org/W3020385185","https://openalex.org/W4252833941","https://openalex.org/W2974871515","https://openalex.org/W3042490037","https://openalex.org/W4296784403"],"abstract_inverted_index":{"Intelligent":[0],"agents":[1],"must":[2],"autonomously":[3],"interact":[4],"with":[5,30,98,136],"the":[6,22,39,47,76,122,127],"environments":[7],"to":[8,24,37,74,106,117],"perform":[9],"daily":[10],"tasks":[11],"based":[12],"on":[13],"human-level":[14,66],"instructions.":[15,67],"They":[16],"need":[17],"a":[18,104],"foundational":[19],"understanding":[20],"of":[21,90,121,129],"world":[23],"accurately":[25],"interpret":[26,75],"these":[27],"instructions,":[28],"along":[29],"precise":[31],"low-level":[32],"movement":[33],"and":[34],"interaction":[35],"skills":[36],"execute":[38],"derived":[40],"actions.":[41],"In":[42],"this":[43],"work,":[44,85],"we":[45],"propose":[46],"first":[48],"complete":[49],"system":[50,87,131],"for":[51,58,145],"synthesizing":[52,133],"physically":[53],"plausible,":[54],"long-horizon":[55],"human-object":[56],"interactions":[57,135],"object":[59],"manipulation":[60],"in":[61,95,110,132,139],"contextual":[62],"environments,":[63,141],"driven":[64],"by":[65],"We":[68,101],"leverage":[69],"large":[70],"language":[71],"models":[72],"(LLMs)":[73],"input":[77],"instructions":[78],"into":[79],"detailed":[80,92],"execution":[81],"plans.":[82],"Unlike":[83],"prior":[84],"our":[86,130],"is":[88],"capable":[89],"generating":[91],"finger-object":[93],"interactions,":[94],"seamless":[96],"coordination":[97],"full-body":[99],"movements.":[100],"also":[102],"train":[103],"policy":[105],"track":[107],"generated":[108],"motions":[109],"physics":[111],"simulation":[112],"via":[113],"reinforcement":[114],"learning":[115],"(RL)":[116],"ensure":[118],"physical":[119],"plausibility":[120],"motion.":[123],"Our":[124],"experiments":[125],"demonstrate":[126],"effectiveness":[128],"realistic":[134],"diverse":[137],"objects":[138],"complex":[140],"highlighting":[142],"its":[143],"potential":[144],"real-world":[146],"applications.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-21T08:15:58.654021","created_date":"2025-10-10T00:00:00"}