{"id":"https://openalex.org/W4417151026","doi":"https://doi.org/10.1109/iccv51701.2025.01029","title":"DyWA: Dynamics-Adaptive World Action Model for Generalizable Non-Prehensile Manipulation","display_name":"DyWA: Dynamics-Adaptive World Action Model for Generalizable Non-Prehensile Manipulation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417151026","doi":"https://doi.org/10.1109/iccv51701.2025.01029"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01029","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":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.16806","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113430864","display_name":"Jiangran Lyu","orcid":"https://orcid.org/0009-0000-8883-2159"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangran Lyu","raw_affiliation_strings":["Center on Frontiers of Computing Studies, School of Computer Science, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center on Frontiers of Computing Studies, School of Computer Science, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101651748","display_name":"Ziming Li","orcid":"https://orcid.org/0009-0004-7529-7176"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziming Li","raw_affiliation_strings":["Center on Frontiers of Computing Studies, School of Computer Science, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center on Frontiers of Computing Studies, School of Computer Science, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101472910","display_name":"Xuesong Shi","orcid":"https://orcid.org/0000-0002-2679-2267"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuesong Shi","raw_affiliation_strings":["Galbot"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Galbot","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090850096","display_name":"Chaoyi Xu","orcid":"https://orcid.org/0000-0002-9870-4297"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chaoyi Xu","raw_affiliation_strings":["Galbot"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Galbot","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100602395","display_name":"Yizhou Wang","orcid":"https://orcid.org/0000-0001-9888-6409"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhou Wang","raw_affiliation_strings":["Center on Frontiers of Computing Studies, School of Computer Science, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center on Frontiers of Computing Studies, School of Computer Science, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351705","display_name":"He Wang","orcid":"https://orcid.org/0000-0003-2987-8362"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Wang","raw_affiliation_strings":["Center on Frontiers of Computing Studies, School of Computer Science, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center on Frontiers of Computing Studies, School of Computer Science, Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42449823,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11058","last_page":"11068"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9747999906539917,"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":0.9747999906539917,"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/T10868","display_name":"Soft Robotics and Applications","score":0.008799999952316284,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.004000000189989805,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6132000088691711},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4952999949455261},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.42260000109672546},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4221999943256378},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.40299999713897705},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.39489999413490295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.692300021648407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6428999900817871},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6132000088691711},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4952999949455261},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4221999943256378},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4194999933242798},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.40299999713897705},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.39489999413490295},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2782000005245209},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.2671999931335449},{"id":"https://openalex.org/C183759332","wikidata":"https://www.wikidata.org/wiki/Q343680","display_name":"Action learning","level":4,"score":0.25110000371932983}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01029","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:2503.16806","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.16806","pdf_url":"https://arxiv.org/pdf/2503.16806","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.2503.16806","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.16806","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:2503.16806","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.16806","pdf_url":"https://arxiv.org/pdf/2503.16806","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Nonprehensile":[0],"manipulation":[1],"is":[2],"crucial":[3],"for":[4],"handling":[5],"objects":[6],"that":[7,87],"are":[8],"too":[9],"thin,":[10],"large,":[11],"or":[12],"otherwise":[13],"ungraspable":[14],"in":[15,66,142,154,173],"unstructured":[16],"environments.":[17],"While":[18],"conventional":[19],"planning-based":[20],"approaches":[21,39],"struggle":[22],"with":[23],"complex":[24],"contact":[25],"modeling,":[26],"learning-based":[27,38],"methods":[28],"have":[29],"recently":[30],"emerged":[31],"as":[32,64,177],"a":[33,84],"promising":[34],"alternative.":[35],"However,":[36],"existing":[37],"face":[40],"two":[41],"major":[42],"limitations:":[43],"they":[44,55],"heavily":[45],"rely":[46],"on":[47,102],"multi-view":[48],"cameras":[49],"and":[50,54,69,113,171,181],"precise":[51],"pose":[52],"tracking,":[53],"fail":[56],"to":[57,98,126,160,167],"generalize":[58,161],"across":[59,162],"varying":[60,168],"physical":[61],"conditions,":[62],"such":[63,176],"changes":[65],"object":[67,164],"mass":[68],"table":[70,169],"friction.":[71],"To":[72],"address":[73],"these":[74],"challenges,":[75],"we":[76],"propose":[77],"the":[78,107,131,143],"Dynamics-Adaptive":[79],"World":[80],"Action":[81],"Model":[82],"(DyWA),":[83],"novel":[85],"framework":[86],"enhances":[88],"action":[89],"learning":[90,121],"by":[91,134],"jointly":[92],"predicting":[93],"future":[94],"states":[95],"while":[96],"adapting":[97],"dynamics":[99],"variations":[100],"based":[101],"historical":[103],"trajectories.":[104],"By":[105],"unifying":[106],"modeling":[108],"of":[109,152],"geometry,":[110],"state,":[111],"physics,":[112],"robot":[114],"actions,":[115],"DyWA":[116,146],"enables":[117],"more":[118],"robust":[119],"policy":[120],"under":[122],"partial":[123],"observability.":[124],"Compared":[125],"baselines,":[127],"our":[128],"method":[129],"improves":[130],"success":[132,150],"rate":[133,151],"31.5%":[135],"using":[136],"only":[137],"single-view":[138],"point":[139],"cloud":[140],"observations":[141],"simulation.":[144],"Furthermore,":[145],"achieves":[147],"an":[148],"average":[149],"68%":[153],"real-world":[155],"experiments,":[156],"demonstrating":[157],"its":[158],"ability":[159],"diverse":[163],"geometries,":[165],"adapt":[166],"friction,":[170],"robustness":[172],"challenging":[174],"scenarios":[175],"half-filled":[178],"water":[179],"bottles":[180],"slippery":[182],"surfaces.":[183]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}