{"id":"https://openalex.org/W4415003123","doi":"https://doi.org/10.1109/lra.2025.3619835","title":"ImitDiff: Transferring Foundation-Model Priors for Distraction-Robust Visuomotor Policy","display_name":"ImitDiff: Transferring Foundation-Model Priors for Distraction-Robust Visuomotor Policy","publication_year":2025,"publication_date":"2025-10-09","ids":{"openalex":"https://openalex.org/W4415003123","doi":"https://doi.org/10.1109/lra.2025.3619835"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3619835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3619835","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":null,"display_name":"Yuhang Dong","orcid":"https://orcid.org/0000-0002-9740-5834"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhang Dong","raw_affiliation_strings":["Ningbo Global Innovation Center, Zhejiang University, Ningbo, China"],"raw_orcid":"https://orcid.org/0000-0002-9740-5834","affiliations":[{"raw_affiliation_string":"Ningbo Global Innovation Center, Zhejiang University, Ningbo, China","institution_ids":["https://openalex.org/I109935558","https://openalex.org/I13591777"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haizhou Ge","orcid":"https://orcid.org/0000-0001-8388-7193"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haizhou Ge","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8388-7193","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yupei Zeng","orcid":"https://orcid.org/0009-0009-0580-1951"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yupei Zeng","raw_affiliation_strings":["Ningbo Global Innovation Center, Zhejiang University, Ningbo, China"],"raw_orcid":"https://orcid.org/0009-0009-0580-1951","affiliations":[{"raw_affiliation_string":"Ningbo Global Innovation Center, Zhejiang University, Ningbo, China","institution_ids":["https://openalex.org/I109935558","https://openalex.org/I13591777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021861529","display_name":"Jiangning Zhang","orcid":"https://orcid.org/0000-0001-8891-6766"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangning Zhang","raw_affiliation_strings":["Youtu, Tencent, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8891-6766","affiliations":[{"raw_affiliation_string":"Youtu, Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077011386","display_name":"Beiwen Tian","orcid":"https://orcid.org/0000-0002-2651-913X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Beiwen Tian","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2651-913X","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057639266","display_name":"Hongrui Zhu","orcid":"https://orcid.org/0000-0003-3405-7032"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongrui Zhu","raw_affiliation_strings":["Ningbo Global Innovation Center, Zhejiang University, Ningbo, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ningbo Global Innovation Center, Zhejiang University, Ningbo, China","institution_ids":["https://openalex.org/I109935558","https://openalex.org/I13591777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010719310","display_name":"Yufei Jia","orcid":"https://orcid.org/0000-0002-1510-2638"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufei Jia","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101968565","display_name":"Ruixiang Wang","orcid":"https://orcid.org/0000-0003-4666-9917"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruixiang Wang","raw_affiliation_strings":["Chinese University of Hong Kong, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068890959","display_name":"Zhucun Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhucun Xue","raw_affiliation_strings":["College of Control Science and Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-2627-4397","affiliations":[{"raw_affiliation_string":"College of Control Science and Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Guyue Zhou","orcid":"https://orcid.org/0000-0002-3894-9858"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guyue Zhou","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3894-9858","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101699384","display_name":"Longhua Ma","orcid":"https://orcid.org/0000-0001-7802-0675"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longhua Ma","raw_affiliation_strings":["Ningbo Global Innovation Center, Zhejiang University, Ningbo, China"],"raw_orcid":"https://orcid.org/0000-0001-7802-0675","affiliations":[{"raw_affiliation_string":"Ningbo Global Innovation Center, Zhejiang University, Ningbo, China","institution_ids":["https://openalex.org/I109935558","https://openalex.org/I13591777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014432572","display_name":"Guanzhong Tian","orcid":"https://orcid.org/0000-0002-7292-4056"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanzhong Tian","raw_affiliation_strings":["Ningbo Global Innovation Center, Zhejiang University, Ningbo, China"],"raw_orcid":"https://orcid.org/0000-0002-7292-4056","affiliations":[{"raw_affiliation_string":"Ningbo Global Innovation Center, Zhejiang University, Ningbo, China","institution_ids":["https://openalex.org/I109935558","https://openalex.org/I13591777"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.067,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.80595007,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"10","issue":"11","first_page":"12125","last_page":"12132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9869999885559082,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9869999885559082,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9729999899864197,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10919","display_name":"Neurological disorders and treatments","score":0.9593999981880188,"subfield":{"id":"https://openalex.org/subfields/2728","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5200999975204468},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5127000212669373},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5059999823570251},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4814999997615814},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4490000009536743},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.400299996137619},{"id":"https://openalex.org/keywords/visual-learning","display_name":"Visual learning","score":0.39730000495910645},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.3912000060081482},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.3871999979019165},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.3806000053882599}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7443000078201294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7010999917984009},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5200999975204468},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5127000212669373},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5059999823570251},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4814999997615814},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4611000120639801},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4490000009536743},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.400299996137619},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.39730000495910645},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3912000060081482},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3871999979019165},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.3806000053882599},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3650999963283539},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.3531000018119812},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3508000075817108},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C2776010242","wikidata":"https://www.wikidata.org/wiki/Q4677575","display_name":"Active perception","level":3,"score":0.3018999993801117},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C22033958","wikidata":"https://www.wikidata.org/wiki/Q7167036","display_name":"Perceptual learning","level":3,"score":0.3010999858379364},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27090001106262207},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C2778251979","wikidata":"https://www.wikidata.org/wiki/Q7936617","display_name":"Visual processing","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3619835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3619835","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/G1118240954","display_name":null,"funder_award_id":"62303405","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W3007769740","https://openalex.org/W4312314406","https://openalex.org/W4385403811","https://openalex.org/W4385430674","https://openalex.org/W4391128534","https://openalex.org/W4402354007","https://openalex.org/W4402354127","https://openalex.org/W4402726956","https://openalex.org/W4404612908","https://openalex.org/W4413924995"],"related_works":[],"abstract_inverted_index":{"Visuomotor":[0],"imitation":[1,43,139],"learning":[2,44,140],"policies":[3,22],"enable":[4],"robots":[5],"to":[6,102],"efficiently":[7],"acquire":[8],"manipulation":[9,133],"skills":[10],"from":[11,86,96],"visual":[12,19,68,118,148,162],"demonstrations.":[13],"However,":[14],"as":[15,135,137],"scene":[16,145],"complexity":[17,146],"and":[18,89,121,147,161],"distractions":[20],"increase,":[21],"that":[23,78,116,128],"perform":[24],"well":[25,136],"in":[26,155,173],"simple":[27],"settings":[28,157],"often":[29],"experience":[30],"substantial":[31],"performance":[32],"degradation.":[33],"To":[34],"address":[35],"this":[36],"challenge,":[37],"we":[38,108],"propose":[39],"ImitDiff,":[40],"a":[41,51,74,110],"diffusion-based":[42],"policy":[45,101],"guided":[46],"by":[47],"fine-grained":[48,90],"semantics":[49],"within":[50],"dual-resolution":[52,75],"workflow.":[53],"Leveraging":[54],"pretrained":[55],"priors":[56],"of":[57],"vision-language":[58,132],"foundation":[59],"models,":[60],"our":[61,165],"method":[62],"transforms":[63],"high-level":[64],"instructions":[65],"into":[66],"pixel-level":[67],"semantic":[69,119],"masks.":[70],"These":[71],"masks":[72],"guide":[73],"perception":[76],"pipeline":[77],"captures":[79],"both":[80],"global":[81],"context":[82],"(e.g.,":[83,93],"overall":[84],"layout)":[85],"low-resolution":[87],"observation":[88],"local":[91],"features":[92],"geometric":[94],"details)":[95],"high-resolution":[97],"observation,":[98],"enabling":[99],"the":[100],"focus":[103],"on":[104],"task-relevant":[105],"regions.":[106],"Additionally,":[107],"introduce":[109],"consistency-driven":[111,166],"diffusion":[112],"transformer":[113],"action":[114,123,167],"head":[115,168],"bridges":[117],"conditions":[120],"real-time":[122],"generation.":[124],"Extensive":[125],"experiments":[126],"demonstrate":[127],"ImitDiff":[129,151],"outperforms":[130],"state-of-the-art":[131],"frameworks,":[134],"visuomotor":[138],"policies,":[141],"particularly":[142],"under":[143],"increased":[144],"distractions.":[149,163],"Notably,":[150],"exhibits":[152],"strong":[153],"generalization":[154],"zero-shot":[156],"involving":[158],"novel":[159],"objects":[160],"Furthermore,":[164],"achieves":[169],"an":[170],"order-of-magnitude":[171],"improvement":[172],"inference":[174],"speed":[175],"while":[176],"maintaining":[177],"competitive":[178],"success":[179],"rates.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}