{"id":"https://openalex.org/W7164844281","doi":"https://doi.org/10.1145/3805622.3810752","title":"Learning Physics from Pretrained Video Models: A Multimodal Continuous and Sequential World Interaction Models for Robotic Manipulation","display_name":"Learning Physics from Pretrained Video Models: A Multimodal Continuous and Sequential World Interaction Models for Robotic Manipulation","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164844281","doi":"https://doi.org/10.1145/3805622.3810752"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810752","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810752","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810752","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023514509","display_name":"Zijian Song","orcid":"https://orcid.org/0000-0003-0627-753X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijian Song","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0627-753X","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100350268","display_name":"Qi Li","orcid":"https://orcid.org/0000-0003-2004-6885"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qichang Li","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-5131-9286","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127990318","display_name":"Sihan Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sihan Qin","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-8162-7802","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100321260","display_name":"Yuhao Chen","orcid":"https://orcid.org/0000-0001-6094-0545"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Chen","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-4799-638X","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052027147","display_name":"Tianshui Chen","orcid":"https://orcid.org/0000-0002-5848-5624"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]},{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianshui Chen","raw_affiliation_strings":["Guangdong University of Technology, Guangzhou, China and X-Era AI Lab, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5848-5624","affiliations":[{"raw_affiliation_string":"Guangdong University of Technology, Guangzhou, China and X-Era AI Lab, Guangzhou, China","institution_ids":["https://openalex.org/I139024713","https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412937","display_name":"Liang Lin","orcid":"https://orcid.org/0000-0003-2248-3755"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Lin","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China and X-Era AI Lab, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2248-3755","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China and X-Era AI Lab, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052611320","display_name":"Guangrun Wang","orcid":"https://orcid.org/0000-0001-7760-1339"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangrun Wang","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China and X-Era AI Lab, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-7760-1339","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China and X-Era AI Lab, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"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":0.93848715,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"758","last_page":"767"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.5728999972343445,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.5728999972343445,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.2257000058889389,"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":0.0617000013589859,"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/robot","display_name":"Robot","score":0.4275999963283539},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.4246000051498413},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4108000099658966},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3644999861717224},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.33000001311302185},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.32679998874664307},{"id":"https://openalex.org/keywords/physics-engine","display_name":"Physics engine","score":0.32199999690055847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6811000108718872},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6068999767303467},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4666999876499176},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4275999963283539},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.4246000051498413},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4108000099658966},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3644999861717224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3580000102519989},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.33000001311302185},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C190390380","wikidata":"https://www.wikidata.org/wiki/Q62505","display_name":"Physics engine","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.3012000024318695},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2806999981403351},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C519536355","wikidata":"https://www.wikidata.org/wiki/Q21021151","display_name":"Repurposing","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810752","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810752","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810752","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810752","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W4385403811","https://openalex.org/W4385430674","https://openalex.org/W4388979610","https://openalex.org/W4390874575","https://openalex.org/W4393156145","https://openalex.org/W4402753568","https://openalex.org/W4413156213","https://openalex.org/W4414050916","https://openalex.org/W4414051084","https://openalex.org/W4414079054","https://openalex.org/W4414197453","https://openalex.org/W4415796345","https://openalex.org/W4415797571","https://openalex.org/W4416749798","https://openalex.org/W4417125193","https://openalex.org/W7133220882","https://openalex.org/W7138128974"],"related_works":[],"abstract_inverted_index":{"The":[0],"scarcity":[1],"of":[2,10,107,159,172,200],"large-scale":[3,173],"robotic":[4,47,99,211],"data":[5],"has":[6],"motivated":[7],"the":[8,52,65,69,91,104,141,170,198],"repurposing":[9],"foundation":[11],"models":[12,64,175],"from":[13,27,204],"other":[14],"modalities":[15],"for":[16,59],"policy":[17],"learning.":[18],"In":[19],"this":[20],"work,":[21],"we":[22,124],"introduce":[23,76],"PhysGen":[24,63,148,168],"(Learning":[25],"Physics":[26],"Pretrained":[28],"Video":[29],"Generation":[30],"Models),":[31],"a":[32,57,60,77],"scalable":[33],"continuous":[34,79,98],"and":[35,72,84,97,114,134,143,155,161],"sequential":[36],"world":[37],"interaction":[38],"framework":[39],"that":[40,81,147],"leverages":[41],"autoregressive":[42],"video":[43,54,83,95,116,206],"generation":[44,96],"to":[45,118,208],"solve":[46],"manipulation":[48],"tasks.":[49],"By":[50],"treating":[51],"pretrained":[53,205],"model":[55],"as":[56,111,191],"proxy":[58],"physics":[61],"simulator,":[62],"dynamic":[66],"interplay":[67],"between":[68,93],"external":[70],"environment":[71],"robot":[73],"actions.":[74],"We":[75],"multimodal":[78],"representation":[80],"unifies":[82],"action":[85],"into":[86],"shared":[87],"physical":[88,109,202],"tokens,":[89],"bridging":[90],"gap":[92],"discrete":[94],"control.":[100],"This":[101],"approach":[102],"enables":[103],"seamless":[105],"transfer":[106],"implicit":[108],"knowledge\u2014such":[110],"object":[112],"permanence":[113],"dynamics\u2014from":[115],"pretraining":[117],"downstream":[119],"manipulation.To":[120],"ensure":[121],"efficient":[122],"convergence,":[123],"incorporate":[125],"causal":[126],"masking,":[127],"inverse":[128],"kinematics,":[129],"Lookahead":[130],"Multi-Token":[131],"Prediction":[132],"(L-MTP),":[133],"key-value":[135],"(KV)":[136],"caching.":[137],"Experimental":[138],"results":[139],"on":[140],"Libero":[142],"ManiSkill":[144],"benchmarks":[145],"demonstrate":[146],"consistently":[149],"outperforms":[150],"robust":[151],"baselines,":[152],"surpassing":[153],"OpenVLA":[154],"WorldVLA":[156],"by":[157],"margins":[158],"13.8%":[160],"8.8%,":[162],"respectively.":[163],"Notably,":[164],"in":[165,186],"real-world":[166],"scenarios,":[167],"matches":[169],"performance":[171],"action-pretrained":[174],"like":[176],"\u03c00":[177],"without":[178],"requiring":[179],"prior":[180],"action-specific":[181],"pretraining,":[182],"demonstrating":[183],"superior":[184],"capability":[185],"physically":[187],"complex":[188],"tasks":[189],"such":[190],"grasping":[192],"transparent":[193],"objects.":[194],"These":[195],"findings":[196],"validate":[197],"potential":[199],"extracting":[201],"intuition":[203],"generators":[207],"facilitate":[209],"generalizable":[210],"manipulation.":[212]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}