{"id":"https://openalex.org/W7164153965","doi":"https://doi.org/10.48550/arxiv.2606.10040","title":"Efficient-WAM: A 1B-Parameter World-Action Model with Low-Cost Future Imagination","display_name":"Efficient-WAM: A 1B-Parameter World-Action Model with Low-Cost Future Imagination","publication_year":2026,"publication_date":"2026-06-08","ids":{"openalex":"https://openalex.org/W7164153965","doi":"https://doi.org/10.48550/arxiv.2606.10040"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.10040","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.10040","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.10040","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138386088","display_name":"Jiajun Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jiajun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138332034","display_name":"Tiecheng Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Tiecheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133493109","display_name":"Yifan Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Yifan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138346265","display_name":"Rongyu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Rongyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138327674","display_name":"Xiaowei Chi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chi, Xiaowei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138296653","display_name":"Qianpu Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Qianpu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138315538","display_name":"Ying Wai Li","orcid":"https://orcid.org/0009-0006-4905-6605"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Ying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128886746","display_name":"Yunfan Lou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lou, Yunfan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138316772","display_name":"Yan Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057760050","display_name":"Zhihe Lu","orcid":"https://orcid.org/0000-0002-6917-8654"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Zhihe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138348172","display_name":"Meng Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138350539","display_name":"Shanghang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Shanghang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"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":0.35199999809265137,"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":0.35199999809265137,"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":0.10270000249147415,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.10249999910593033,"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/inference","display_name":"Inference","score":0.7461000084877014},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6660000085830688},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5598000288009644},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.5135999917984009},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.43970000743865967},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.43779999017715454},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3822999894618988}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7461000084877014},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6916000247001648},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6660000085830688},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5598000288009644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5303999781608582},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.5135999917984009},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.43970000743865967},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.43779999017715454},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.43230000138282776},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3822999894618988},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.3601999878883362},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3400999903678894},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33730000257492065},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.29330000281333923},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C199776023","wikidata":"https://www.wikidata.org/wiki/Q202875","display_name":"Negotiation","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.27399998903274536},{"id":"https://openalex.org/C147297375","wikidata":"https://www.wikidata.org/wiki/Q6674930","display_name":"Look-ahead","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.2587999999523163},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.10040","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.10040","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":"doi:10.48550/arxiv.2606.10040","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.10040","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":false,"raw_source_name":null,"raw_type":"Preprint"},"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":{"World-Action":[0,65],"Models":[1],"(WAMs)":[2],"have":[3],"emerged":[4],"as":[5,122],"a":[6,42,64,84,123,171],"promising":[7],"paradigm":[8],"for":[9,114,127],"embodied":[10],"control":[11,50,77,154],"by":[12],"coupling":[13],"future":[14,27,53,72,112,119,149],"visual":[15,54,115],"prediction":[16,55,121],"with":[17],"action":[18,128,144],"generation.":[19,129],"However,":[20],"most":[21],"existing":[22,175],"WAMs":[23],"rely":[24],"on":[25,132],"photorealistic":[26],"prediction,":[28],"which":[29],"incurs":[30],"high":[31],"inference":[32,59,81],"latency":[33,162],"and":[34,94,135],"makes":[35],"real-time":[36],"robot":[37],"deployment":[38],"difficult.":[39],"This":[40],"motivates":[41],"more":[43],"efficient":[44],"WAM":[45],"design":[46],"that":[47,67,98,140],"preserves":[48],"the":[49,69,111],"benefits":[51],"of":[52,71,109],"while":[56,74],"reducing":[57],"its":[58,76],"cost.":[60],"We":[61],"introduce":[62],"Efficient-WAM,":[63],"Model":[66],"reduces":[68],"cost":[70],"imagination":[73],"preserving":[75],"benefit.":[78],"Efficient-WAM":[79,117,141],"improves":[80],"efficiency":[82],"via":[83],"compact":[85,124],"video":[86,92,104,120],"expert":[87],"transferred":[88],"from":[89],"WAN-2.2-5B,":[90],"token-sparse":[91],"latents,":[93],"asymmetric":[95],"video-action":[96],"denoising":[97],"allocates":[99],"fewer":[100],"sampling":[101],"steps":[102],"to":[103,106,163],"than":[105],"actions.":[107],"Instead":[108],"optimizing":[110],"branch":[113],"fidelity,":[116],"treats":[118],"guidance":[125],"signal":[126],"Comprehensive":[130],"experiments":[131],"RoboTwin":[133],"2.0":[134],"real-world":[136],"manipulation":[137],"tasks":[138],"show":[139],"maintains":[142],"strong":[143],"performance":[145],"despite":[146],"visibly":[147],"coarse":[148],"predictions.":[150],"While":[151],"maintaining":[152],"competitive":[153],"capabilities,":[155],"our":[156],"1B-parameter":[157],"model":[158],"can":[159],"reduce":[160],"per-chunk":[161],"around":[164],"100":[165],"ms":[166],"during":[167],"physical":[168],"deployment,":[169],"achieving":[170],"30x":[172],"speedup":[173],"over":[174],"WAMs.":[176]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-11T00:00:00"}