{"id":"https://openalex.org/W4412836782","doi":"https://doi.org/10.1109/lra.2025.3595034","title":"DISCO: Language-Guided Manipulation With Diffusion Policies and Constrained Inpainting","display_name":"DISCO: Language-Guided Manipulation With Diffusion Policies and Constrained Inpainting","publication_year":2025,"publication_date":"2025-08-01","ids":{"openalex":"https://openalex.org/W4412836782","doi":"https://doi.org/10.1109/lra.2025.3595034"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3595034","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3595034","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/A5100309186","display_name":"Hao Ce","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ce Hao","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0000-7653-9713","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072170012","display_name":"Kelvin Lin","orcid":"https://orcid.org/0000-0002-1494-1464"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kelvin Lin","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062829885","display_name":"Zhi Xue","orcid":"https://orcid.org/0000-0003-2875-304X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhiwei Xue","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091414010","display_name":"Siyuan Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Siyuan Luo","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0001-6696-5513","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066073375","display_name":"Harold Soh","orcid":"https://orcid.org/0000-0002-3278-0035"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Harold Soh","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-3278-0035","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":1.6994,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.85238084,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"10","issue":"10","first_page":"9726","last_page":"9733"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.8546000123023987,"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":0.8546000123023987,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.8398000001907349,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.748199999332428,"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/inpainting","display_name":"Inpainting","score":0.8122665882110596},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5344853401184082},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.38654521107673645},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3843417465686798},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.36222025752067566},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29524004459381104},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.19667428731918335},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.19359496235847473},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09148743748664856}],"concepts":[{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.8122665882110596},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5344853401184082},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.38654521107673645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3843417465686798},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.36222025752067566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29524004459381104},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.19667428731918335},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.19359496235847473},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09148743748664856},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3595034","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3595034","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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2992838650","https://openalex.org/W4285218426","https://openalex.org/W4312497550","https://openalex.org/W4383097638","https://openalex.org/W4383109488","https://openalex.org/W4385403811","https://openalex.org/W4385430679","https://openalex.org/W4388660746","https://openalex.org/W4402354045","https://openalex.org/W4402354164","https://openalex.org/W4402727730"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2380775572","https://openalex.org/W2213520135","https://openalex.org/W2244018504","https://openalex.org/W4242046654","https://openalex.org/W3174923100","https://openalex.org/W3134074939","https://openalex.org/W2117562399"],"abstract_inverted_index":{"Diffusion":[0],"policies":[1,24],"have":[2],"demonstrated":[3],"strong":[4],"performance":[5,95],"in":[6,28,124,141],"generative":[7],"modeling,":[8],"making":[9],"them":[10],"promising":[11],"for":[12],"robotic":[13],"manipulation":[14,144],"guided":[15],"by":[16],"natural":[17,59],"language":[18,60],"instructions.":[19],"However,":[20,86],"generalizing":[21],"language-conditioned":[22,136],"diffusion":[23,64,81],"to":[25,34,57,90],"open-vocabulary":[26,143],"instructions":[27],"everyday":[29],"scenarios":[30],"remains":[31],"challenging":[32],"due":[33],"the":[35,80,97],"scarcity":[36],"and":[37,127],"cost":[38],"of":[39],"robot":[40],"demonstration":[41],"datasets.":[42],"To":[43,102],"address":[44],"this,":[45,104],"we":[46,105],"propose":[47],"DISCO,":[48],"a":[49],"framework":[50],"that":[51,111,131],"leverages":[52],"off-the-shelf":[53],"vision-language":[54],"models":[55],"(VLMs)":[56],"bridge":[58],"understanding":[61],"with":[62,115],"high-performance":[63],"policies.":[65],"DISCO":[66,132],"translates":[67],"linguistic":[68],"task":[69],"descriptions":[70],"into":[71],"actionable":[72],"3D":[73],"keyframes":[74,92,99],"using":[75],"VLMs,":[76],"which":[77],"then":[78],"guide":[79],"process":[82],"through":[83],"constrained":[84],"inpainting.":[85],"enforcing":[87],"strict":[88],"adherence":[89,114],"these":[91],"can":[93],"degrade":[94],"when":[96],"VLM-generated":[98],"are":[100],"inaccurate.":[101],"mitigate":[103],"introduce":[106],"an":[107],"inpainting":[108],"optimization":[109],"strategy":[110],"balances":[112],"keyframe":[113],"learned":[116],"motion":[117],"priors":[118],"from":[119],"training":[120],"data.":[121],"Experimental":[122],"results":[123],"both":[125],"simulated":[126],"real-world":[128],"settings":[129],"demonstrate":[130],"outperforms":[133],"conventional":[134],"fine-tuned":[135],"policies,":[137],"achieving":[138],"superior":[139],"generalization":[140],"zero-shot,":[142],"tasks.":[145],"Videos":[146],"see":[147],"website:":[148],"<uri":[149],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[150],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">sites.google.com/view/disco2025</uri>.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
