{"id":"https://openalex.org/W4414008389","doi":"https://doi.org/10.1109/tnnls.2025.3594117","title":"Surfer: A World Model-Based Framework for Vision-Language Robot Manipulation","display_name":"Surfer: A World Model-Based Framework for Vision-Language Robot Manipulation","publication_year":2025,"publication_date":"2025-09-05","ids":{"openalex":"https://openalex.org/W4414008389","doi":"https://doi.org/10.1109/tnnls.2025.3594117","pmid":"https://pubmed.ncbi.nlm.nih.gov/40911446"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3594117","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3594117","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043155550","display_name":"Pengzhen Ren","orcid":"https://orcid.org/0000-0001-9965-8088"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengzhen Ren","raw_affiliation_strings":["PengCheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-9965-8088","affiliations":[{"raw_affiliation_string":"PengCheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kaidong Zhang","orcid":"https://orcid.org/0009-0009-8678-6895"},"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":"Kaidong Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-8678-6895","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108845611","display_name":"Hetao Zheng","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":"Hetao Zheng","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zixuan Li","orcid":"https://orcid.org/0009-0000-1553-3748"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixuan Li","raw_affiliation_strings":["School of Automation Science and Engineering, Xi’an Jiaotong University, Xi’an, China"],"raw_orcid":"https://orcid.org/0009-0000-1553-3748","affiliations":[{"raw_affiliation_string":"School of Automation Science and Engineering, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074489530","display_name":"Yuhang Wen","orcid":"https://orcid.org/0000-0001-6644-4075"},"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":"Yuhang Wen","raw_affiliation_strings":["School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-6644-4075","affiliations":[{"raw_affiliation_string":"School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027233873","display_name":"Fengda Zhu","orcid":"https://orcid.org/0000-0003-1834-5018"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fengda Zhu","raw_affiliation_strings":["ByteDance Ltd., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Ltd., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100594712","display_name":"Shikui Ma","orcid":"https://orcid.org/0000-0002-8340-9762"},"institutions":[{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shikui Ma","raw_affiliation_strings":["Hunan Artificial Intelligence and Robotics Institute Company Ltd., Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-8340-9762","affiliations":[{"raw_affiliation_string":"Hunan Artificial Intelligence and Robotics Institute Company Ltd., Changsha, China","institution_ids":["https://openalex.org/I4210121405"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047878798","display_name":"Xiaodan Liang","orcid":"https://orcid.org/0000-0003-3213-3062"},"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":"Xiaodan Liang","raw_affiliation_strings":["School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-3213-3062","affiliations":[{"raw_affiliation_string":"School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":0.24986436,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"12","first_page":"20092","last_page":"20104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.9312999844551086,"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/T13382","display_name":"Robotics and Automated Systems","score":0.9312999844551086,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6091750264167786},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5155634880065918},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5015196800231934},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4591497778892517},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.44144585728645325}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6091750264167786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5155634880065918},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5015196800231934},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4591497778892517},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.44144585728645325}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2025.3594117","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3594117","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:40911446","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40911446","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2236135741","display_name":null,"funder_award_id":"2024YFE0203100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6630003392","display_name":null,"funder_award_id":"62476293","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2760103357","https://openalex.org/W2963669336","https://openalex.org/W3007769740","https://openalex.org/W3034758614","https://openalex.org/W3035191209","https://openalex.org/W3035624836","https://openalex.org/W3100452485","https://openalex.org/W3203663566","https://openalex.org/W4200523064","https://openalex.org/W4225675121","https://openalex.org/W4252189904","https://openalex.org/W4281252704","https://openalex.org/W4285294723","https://openalex.org/W4313156423","https://openalex.org/W4385245566","https://openalex.org/W4385430679","https://openalex.org/W4386076428","https://openalex.org/W4389520747","https://openalex.org/W4402353985","https://openalex.org/W4413145391"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Considering":[0],"how":[1],"to":[2,49],"make":[3],"the":[4,35,41,47,100,111,124,128,142,165,191,198,246,274,282],"model":[5,50,129],"accurately":[6],"understand":[7],"and":[8,13,34,60,71,74,89,114,121,133,144,176,187,194,224,291],"follow":[9],"natural":[10],"language":[11,61,72],"instructions":[12,132],"perform":[14],"actions":[15],"consistent":[16],"with":[17,208],"world":[18,51,79,101],"knowledge":[19,52],"is":[20,97,136],"a":[21,87,107,154,185,204,227,268],"key":[22],"challenge":[23],"in":[24,67,147,235,245,260],"robot":[25,62,91,104,155],"manipulation.":[26],"This":[27],"mainly":[28,65],"includes":[29],"human":[30],"fuzzy":[31],"instruction":[32],"reasoning":[33],"following":[36],"of":[37,78,110,127,141,190,197,220,271,278,286],"physical":[38,195],"knowledge.":[39,80],"Therefore,":[40],"embodied":[42],"intelligence":[43],"agent":[44],"must":[45],"have":[46],"ability":[48,126],"from":[53],"training":[54,174],"data.":[55],"However,":[56],"most":[57],"existing":[58],"vision":[59],"manipulation":[63,92,105,156,199,206,218,262,279],"methods":[64],"operate":[66],"less":[68],"realistic":[69],"simulators":[70],"settings":[73],"lack":[75],"explicit":[76,139],"modeling":[77,140],"To":[81,183],"bridge":[82],"this":[83],"gap,":[84],"we":[85,152,201,239],"introduce":[86],"novel":[88],"simple":[90],"framework,":[93],"called":[94,212],"Surfer.":[95],"It":[96,169,214],"based":[98,163],"on":[99,130,164,273],"model,":[102,200],"treats":[103],"as":[106],"state":[108],"transfer":[109],"visual":[112],"scene,":[113],"decouples":[115],"it":[116],"into":[117],"two":[118],"parts:":[119],"action":[120,143],"scene.":[122],"Then,":[123],"generalization":[125],"new":[131,134],"scenes":[135],"enhanced":[137],"by":[138],"scene":[145],"prediction":[146],"multimodal":[148,236],"information.":[149],"In":[150],"addition,":[151],"built":[153],"simulation":[157],"platform":[158,230],"that":[159,253],"supports":[160],"physics":[161,167],"execution":[162,196],"MuJoCo":[166],"engine.":[168],"can":[170,225,242],"automatically":[171],"generate":[172],"demonstration":[173],"data":[175],"test":[177],"data,":[178],"effectively":[179],"reducing":[180],"labor":[181],"costs.":[182],"conduct":[184],"comprehensive":[186],"systematic":[188],"evaluation":[189],"visual-language":[192,217],"understanding":[193],"also":[202],"created":[203],"robotic":[205],"benchmark":[207],"different":[209,221],"difficulty":[210,222],"levels,":[211],"SeaWave.":[213],"contains":[215],"four":[216,276],"tasks":[219],"levels":[223,277],"provide":[226],"standardized":[228],"testing":[229],"for":[231],"embedded":[232],"AI":[233],"agents":[234],"environments.":[237],"Overall,":[238],"hope":[240],"Surfer":[241,254,266],"freely":[243],"surf":[244],"robot's":[247],"SeaWave":[248],"benchmark.":[249],"Extensive":[250],"experiments":[251],"show":[252],"consistently":[255],"outperforms":[256],"all":[257,261],"baselines":[258],"significantly":[259],"tasks.":[263],"On":[264],"average,":[265],"achieved":[267],"success":[269],"rate":[270],"54.74%":[272],"defined":[275],"tasks,":[280],"exceeding":[281],"best":[283],"baseline":[284],"performance":[285],"51.07%.":[287],"The":[288],"simulator,":[289],"code,":[290],"benchmarks":[292],"are":[293],"released":[294],"at":[295],"https://pzhren.github.io/Surfer.":[296]},"counts_by_year":[],"updated_date":"2025-12-03T23:09:05.601824","created_date":"2025-10-10T00:00:00"}