{"id":"https://openalex.org/W7163185428","doi":"https://doi.org/10.48550/arxiv.2606.00664","title":"SKIP: Sparse Keyframe Interpolation Paradigm for Efficient Embodied World Models","display_name":"SKIP: Sparse Keyframe Interpolation Paradigm for Efficient Embodied World Models","publication_year":2026,"publication_date":"2026-05-30","ids":{"openalex":"https://openalex.org/W7163185428","doi":"https://doi.org/10.48550/arxiv.2606.00664"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.00664","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00664","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.2606.00664","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021760799","display_name":"Ziheng He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Ziheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137691494","display_name":"Yixiang Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yixiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137697006","display_name":"Ning Yang","orcid":"https://orcid.org/0009-0006-9665-0850"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Ning","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076782213","display_name":"Zhanqian Wu","orcid":"https://orcid.org/0000-0002-6556-657X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Zhanqian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137650314","display_name":"Qisen Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Qisen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137702066","display_name":"Yuan Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137625442","display_name":"Jiabing Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Jiabing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137689373","display_name":"Peiyan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Peiyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022649370","display_name":"Xinhai Wu","orcid":"https://orcid.org/0000-0001-6123-0350"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Xiangnan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137675287","display_name":"Xiaofeng Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xiaofeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137650405","display_name":"Zheng Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137658916","display_name":"Jing Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074100803","display_name":"Nianfeng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Nianfeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137646669","display_name":"Yan Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Yan","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/T10653","display_name":"Robot Manipulation and Learning","score":0.49230000376701355,"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":0.49230000376701355,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.23839999735355377,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.05590000003576279,"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/interpolation","display_name":"Interpolation (computer graphics)","score":0.6486999988555908},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6212000250816345},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5371000170707703},{"id":"https://openalex.org/keywords/frame-rate","display_name":"Frame rate","score":0.5063999891281128},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.47609999775886536},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.47040000557899475},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.44589999318122864},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.4041999876499176}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7908999919891357},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6904000043869019},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.6486999988555908},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6212000250816345},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5371000170707703},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5342000126838684},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.5063999891281128},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.47609999775886536},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.47040000557899475},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.44589999318122864},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.4041999876499176},{"id":"https://openalex.org/C205203396","wikidata":"https://www.wikidata.org/wiki/Q612143","display_name":"Bilinear interpolation","level":2,"score":0.38850000500679016},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3846000134944916},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2854999899864197},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.2687999904155731}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.00664","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00664","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.2606.00664","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00664","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":[{"id":"https://metadata.un.org/sdg/10","score":0.5626564025878906,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Embodied":[0],"world":[1],"models":[2],"have":[3,35],"emerged":[4],"as":[5,30,64],"a":[6,107,139],"promising":[7],"paradigm":[8],"in":[9,27,172],"robotics":[10],"by":[11,40,48,95,150,188],"predicting":[12],"how":[13],"robot":[14,128],"actions":[15],"affect":[16],"the":[17,21,122,127,179],"surrounding":[18],"scene.":[19],"However,":[20],"rollout":[22],"inference":[23],"remains":[24],"computationally":[25],"expensive":[26],"pixel":[28],"space,":[29],"long-horizon":[31],"manipulation":[32],"videos":[33,154],"typically":[34],"to":[36,126,190],"be":[37,45],"generated":[38],"frame":[39],"frame.":[41],"This":[42],"cost":[43],"cannot":[44],"easily":[46],"reduced":[47],"indiscriminately":[49],"dropping":[50],"frames,":[51],"since":[52],"downstream":[53],"policies":[54],"rely":[55],"on":[56,178],"complete":[57],"preservation":[58],"of":[59],"sparse":[60,108],"task-relevant":[61,93],"events":[62],"such":[63],"approach,":[65],"contact,":[66],"grasp,":[67],"and":[68,116,146,175],"release.":[69],"To":[70],"address":[71],"this":[72],"challenge,":[73],"we":[74],"propose":[75],"Sparse":[76],"Keyframe":[77],"Interpolation":[78],"Paradigm":[79],"(SKIP),":[80],"an":[81,117],"event-preserving":[82],"sparse-to-dense":[83],"framework":[84],"that":[85],"avoids":[86],"dense":[87,134,140,184],"frame-by-frame":[88,185],"generation.":[89],"SKIP":[90,132],"first":[91],"identifies":[92],"keyframes":[94,105],"leveraging":[96],"robot-aware":[97],"multimodal":[98],"features.":[99],"It":[100],"then":[101],"synthesizes":[102],"only":[103,169],"these":[104],"with":[106],"video":[109],"diffusion":[110],"model.":[111],"A":[112],"learned":[113],"gap":[114],"predictor":[115],"action-conditioned":[118],"interpolator":[119],"subsequently":[120],"reconstruct":[121],"missing":[123],"intervals":[124],"according":[125],"actions.":[129],"On":[130],"LIBERO,":[131],"generates":[133],"rollouts":[135],"$4.16\\times$":[136],"faster":[137],"than":[138],"baseline":[141],"while":[142],"improving":[143],"visual":[144],"fidelity":[145],"reducing":[147],"aggregate":[148],"FVD":[149],"$89.0\\%$.":[151],"Importantly,":[152],"SKIP-generated":[153],"are":[155],"effective":[156],"policy-training":[157],"data.":[158],"Even":[159],"when":[160],"they":[161],"fully":[162,183],"replace":[163],"real":[164,180],"demonstrations,":[165],"$\u03c0_{0.5}$":[166],"success":[167],"drops":[168],"$1.3$":[170],"pp":[171,177],"LIBERO":[173],"simulation":[174],"$6.7$":[176],"robot,":[181],"whereas":[182],"generation":[186],"collapses":[187],"$48$":[189],"$58$":[191],"pp.":[192]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-03T00:00:00"}