{"id":"https://openalex.org/W4407574886","doi":"https://doi.org/10.1109/lra.2025.3542317","title":"VILP: Imitation Learning With Latent Video Planning","display_name":"VILP: Imitation Learning With Latent Video Planning","publication_year":2025,"publication_date":"2025-02-14","ids":{"openalex":"https://openalex.org/W4407574886","doi":"https://doi.org/10.1109/lra.2025.3542317"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3542317","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3542317","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5100583938","display_name":"Zhengtong Xu","orcid":"https://orcid.org/0000-0002-2789-1910"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengtong Xu","raw_affiliation_strings":["School of Industrial Engineering, Purdue University, West Lafayette, IN, USA","School of Industrial Engineering, Purdue University, West Lafayette, USA"],"raw_orcid":"https://orcid.org/0000-0002-2789-1910","affiliations":[{"raw_affiliation_string":"School of Industrial Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"School of Industrial Engineering, Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101992408","display_name":"Qiang Qiu","orcid":"https://orcid.org/0000-0003-2610-3502"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiang Qiu","raw_affiliation_strings":["Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, USA"],"raw_orcid":"https://orcid.org/0000-0003-2610-3502","affiliations":[{"raw_affiliation_string":"Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018653973","display_name":"Yu She","orcid":"https://orcid.org/0000-0001-5914-3573"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu She","raw_affiliation_strings":["School of Industrial Engineering, Purdue University, West Lafayette, IN, USA","School of Industrial Engineering, Purdue University, West Lafayette, USA"],"raw_orcid":"https://orcid.org/0000-0001-5914-3573","affiliations":[{"raw_affiliation_string":"School of Industrial Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"School of Industrial Engineering, Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.01632951,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":"4","first_page":"3350","last_page":"3357"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.996999979019165,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.996999979019165,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9930999875068665,"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/T12290","display_name":"Human Motion and Animation","score":0.9900000095367432,"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/imitation","display_name":"Imitation","score":0.7315576076507568},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4803146719932556},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3708048462867737},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35403668880462646},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.337287962436676},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.09023764729499817}],"concepts":[{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.7315576076507568},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4803146719932556},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3708048462867737},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35403668880462646},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.337287962436676},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.09023764729499817}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3542317","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3542317","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5578531746","display_name":null,"funder_award_id":"2023-67021-39072","funder_id":"https://openalex.org/F4320306114","funder_display_name":"U.S. Department of Agriculture"},{"id":"https://openalex.org/G6754731134","display_name":null,"funder_award_id":"2024-67021-42878","funder_id":"https://openalex.org/F4320306114","funder_display_name":"U.S. Department of Agriculture"}],"funders":[{"id":"https://openalex.org/F4320306114","display_name":"U.S. Department of Agriculture","ror":"https://ror.org/01na82s61"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2962785568","https://openalex.org/W3180355996","https://openalex.org/W4224903718","https://openalex.org/W4312633146","https://openalex.org/W4312933868","https://openalex.org/W4385245566","https://openalex.org/W4385403811","https://openalex.org/W4386076280","https://openalex.org/W4403936678","https://openalex.org/W6679045638","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6785308759","https://openalex.org/W6790830454","https://openalex.org/W6793801364","https://openalex.org/W6795288823","https://openalex.org/W6799150178","https://openalex.org/W6800425027","https://openalex.org/W6802517614","https://openalex.org/W6848903804","https://openalex.org/W6850701985","https://openalex.org/W6857274923","https://openalex.org/W6857711900","https://openalex.org/W6862222871","https://openalex.org/W6869662890","https://openalex.org/W6871977329","https://openalex.org/W6875083129"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2899084033","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W2748952813","https://openalex.org/W1531601525"],"abstract_inverted_index":{"In":[0,106,168],"the":[1,16,107,114,133,136],"era":[2],"of":[3,89,95,103,129,135,185],"generative":[4],"AI,":[5],"integrating":[6],"video":[7,27,34,71,116,190],"generation":[8,72,117,191],"models":[9,192],"into":[10,193],"robotics":[11],"opens":[12],"new":[13],"possibilities":[14],"for":[15,66,199],"general-purpose":[17],"robot":[18,40,67,118,160,194],"agent.":[19],"This":[20],"letter":[21],"introduces":[22],"imitation":[23,145],"learning":[24,146],"with":[25,92,143],"latent":[26,33],"planning":[28],"(VILP).":[29],"We":[30,138],"propose":[31],"a":[32,48,93,101,182],"diffusion":[35],"model":[36,73],"to":[37,44,47,55,187],"generate":[38,56,81],"predictive":[39],"videos":[41,59,82],"that":[42,111,151],"adhere":[43],"temporal":[45,127],"consistency":[46,128],"good":[49],"degree.":[50],"Our":[51,70,148,179],"method":[52,142],"is":[53,64,74],"able":[54],"highly":[57,75],"time-aligned":[58],"from":[60,83],"multiple":[61],"views,":[62],"which":[63],"crucial":[65],"policy":[68,119],"learning.":[69],"time-efficient.":[76],"For":[77],"example,":[78],"it":[79],"can":[80,153],"two":[84],"distinct":[85],"perspectives,":[86],"each":[87],"consisting":[88],"six":[90],"frames":[91],"resolution":[94],"96":[96],"\u00d7":[97],"160":[98],"pixels,":[99],"at":[100],"rate":[102],"5":[104],"Hz.":[105],"experiments,":[108],"we":[109],"demonstrate":[110],"VILP":[112,152,170],"outperforms":[113],"existing":[115],"across":[120],"several":[121],"metrics:":[122],"training":[123],"costs,":[124],"inference":[125],"speed,":[126],"generated":[130],"videos,":[131],"and":[132,202],"performance":[134],"policy.":[137],"also":[139],"compared":[140],"our":[141],"other":[144],"methods.":[147],"findings":[149],"indicate":[150],"rely":[154],"less":[155],"on":[156],"extensive":[157],"high-quality":[158],"task-specific":[159],"action":[161,177],"data":[162],"while":[163],"still":[164],"maintaining":[165],"robust":[166,172],"performance.":[167],"addition,":[169],"possesses":[171],"capabilities":[173],"in":[174],"representing":[175],"multi-modal":[176],"distributions.":[178],"paper":[180],"provides":[181],"practical":[183],"example":[184],"how":[186],"effectively":[188],"integrate":[189],"policies,":[195],"potentially":[196],"offering":[197],"insights":[198],"related":[200],"fields":[201],"directions.":[203]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}