{"id":"https://openalex.org/W4403116255","doi":"https://doi.org/10.1109/icra55743.2025.11127315","title":"Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-Guided 3D Policy","display_name":"Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-Guided 3D Policy","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4403116255","doi":"https://doi.org/10.1109/icra55743.2025.11127315"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127315","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.01345","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036727505","display_name":"Ricardo Garc\u0131\u0301a","orcid":"https://orcid.org/0000-0002-7115-1928"},"institutions":[{"id":"https://openalex.org/I2746051580","display_name":"Universit\u00e9 Paris Sciences et Lettres","ror":"https://ror.org/013cjyk83","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580"]},{"id":"https://openalex.org/I4210103330","display_name":"\u00c9cole Normale Sup\u00e9rieure","ror":"https://ror.org/01dp7jr64","country_code":"BI","type":"education","lineage":["https://openalex.org/I4210103330"]}],"countries":["BI","FR"],"is_corresponding":false,"raw_author_name":"Ricardo Garcia","raw_affiliation_strings":["Inria, École normale supérieure, CNRS, PSL Research University","WILLOW - Models of visual object recognition and scene understanding (48 Rue Barrault, 75013 Paris - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria, École normale supérieure, CNRS, PSL Research University","institution_ids":["https://openalex.org/I2746051580","https://openalex.org/I4210103330"]},{"raw_affiliation_string":"WILLOW - Models of visual object recognition and scene understanding (48 Rue Barrault, 75013 Paris - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101776086","display_name":"Shizhe Chen","orcid":"https://orcid.org/0000-0002-7313-9703"},"institutions":[{"id":"https://openalex.org/I2746051580","display_name":"Universit\u00e9 Paris Sciences et Lettres","ror":"https://ror.org/013cjyk83","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580"]},{"id":"https://openalex.org/I4210103330","display_name":"\u00c9cole Normale Sup\u00e9rieure","ror":"https://ror.org/01dp7jr64","country_code":"BI","type":"education","lineage":["https://openalex.org/I4210103330"]}],"countries":["BI","FR"],"is_corresponding":false,"raw_author_name":"Shizhe Chen","raw_affiliation_strings":["Inria, École normale supérieure, CNRS, PSL Research University","WILLOW - Models of visual object recognition and scene understanding (48 Rue Barrault, 75013 Paris - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria, École normale supérieure, CNRS, PSL Research University","institution_ids":["https://openalex.org/I2746051580","https://openalex.org/I4210103330"]},{"raw_affiliation_string":"WILLOW - Models of visual object recognition and scene understanding (48 Rue Barrault, 75013 Paris - France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109890544","display_name":"Cordelia Schmid","orcid":null},"institutions":[{"id":"https://openalex.org/I2746051580","display_name":"Universit\u00e9 Paris Sciences et Lettres","ror":"https://ror.org/013cjyk83","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580"]},{"id":"https://openalex.org/I4210103330","display_name":"\u00c9cole Normale Sup\u00e9rieure","ror":"https://ror.org/01dp7jr64","country_code":"BI","type":"education","lineage":["https://openalex.org/I4210103330"]}],"countries":["BI","FR"],"is_corresponding":false,"raw_author_name":"Cordelia Schmid","raw_affiliation_strings":["Inria, École normale supérieure, CNRS, PSL Research University","WILLOW - Models of visual object recognition and scene understanding (48 Rue Barrault, 75013 Paris - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria, École normale supérieure, CNRS, PSL Research University","institution_ids":["https://openalex.org/I2746051580","https://openalex.org/I4210103330"]},{"raw_affiliation_string":"WILLOW - Models of visual object recognition and scene understanding (48 Rue Barrault, 75013 Paris - France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.309,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.98450063,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8996","last_page":"9002"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9939000010490417,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.984499990940094,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7610821723937988},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7532635927200317},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6312946677207947},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5637063384056091},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.545014500617981},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4962976574897766},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4657275080680847},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4452141225337982},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4213799834251404},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3781971335411072},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13157272338867188},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.0845436155796051}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7610821723937988},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7532635927200317},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6312946677207947},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5637063384056091},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.545014500617981},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4962976574897766},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4657275080680847},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4452141225337982},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4213799834251404},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3781971335411072},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13157272338867188},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0845436155796051},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icra55743.2025.11127315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127315","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2410.01345","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.01345","pdf_url":"https://arxiv.org/pdf/2410.01345","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-04721101v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04721101","pdf_url":"https://hal.science/hal-04721101v1/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2024","raw_type":"info:eu-repo/semantics/preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.01345","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.01345","pdf_url":"https://arxiv.org/pdf/2410.01345","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2439744834","display_name":"PR[AI]RIE-PSAI - Paris School of Artificial Intelligence","funder_award_id":"ANR-23-IACL-0008","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G4842108258","display_name":"Predicting future video content","funder_award_id":"ANR-21-FAI1-0002","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320326256","display_name":"Grand \u00c9quipement National De Calcul Intensif","ror":"https://ror.org/0010d1q40"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4403116255.pdf"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W3007769740","https://openalex.org/W3034758614","https://openalex.org/W3174849255","https://openalex.org/W4285218426","https://openalex.org/W4319300153","https://openalex.org/W4383097638","https://openalex.org/W4385403811","https://openalex.org/W4385430538","https://openalex.org/W4385431288","https://openalex.org/W4390873239","https://openalex.org/W4390874575","https://openalex.org/W4402354093","https://openalex.org/W4402354166","https://openalex.org/W4402667891","https://openalex.org/W4402702968"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W3213722473","https://openalex.org/W2110944602","https://openalex.org/W3098003361"],"abstract_inverted_index":{"Generalizing":[0],"language-conditioned":[1],"robotic":[2,38,149],"policies":[3],"to":[4,32],"new":[5,73,144],"tasks":[6,139],"remains":[7],"a":[8,29,72,111,143],"significant":[9],"challenge,":[10],"hampered":[11],"by":[12,26],"the":[13,120,127],"lack":[14],"of":[15,36,50,124,131,140],"suitable":[16],"simulation":[17],"benchmarks.":[18],"In":[19],"this":[20,24],"paper,":[21],"we":[22,108],"address":[23,106],"gap":[25],"introducing":[27],"GemBench,":[28,141],"novel":[30,53,103,138],"benchmark":[31],"assess":[33],"generalization":[34,147],"capabilities":[35,118,123],"vision-language":[37],"manipulation":[39],"policies.":[40],"GemBench":[41,68],"incorporates":[42],"seven":[43],"general":[44],"action":[45,84],"primitives":[46],"and":[47,56,59,69,95,126,156],"four":[48],"levels":[49],"generalization,":[51],"spanning":[52],"placements,":[54],"rigid":[55],"articulated":[57],"objects,":[58],"complex":[60],"long-horizon":[61],"tasks.":[62,104],"We":[63],"evaluate":[64],"state-of-the-art":[65,135],"approaches":[66],"on":[67,87,97,137],"also":[70],"introduce":[71],"method.":[74],"Our":[75],"approach":[76],"3D-":[77],"LOTUS":[78],"leverages":[79],"rich":[80],"3D":[81],"information":[82],"for":[83,146],"prediction":[85],"conditioned":[86],"language.":[88],"While":[89],"3D-LOTUS":[90],"excels":[91],"in":[92,148],"both":[93],"efficiency":[94],"performance":[96],"seen":[98],"tasks,":[99],"it":[100],"struggles":[101],"with":[102,119],"To":[105],"this,":[107],"present":[109],"3D-LOTUS++,":[110],"framework":[112],"that":[113],"integrates":[114],"3D-LOTUS's":[115],"motion":[116],"planning":[117,122],"task":[121],"LLMs":[125],"object":[128],"grounding":[129],"accuracy":[130],"VLMs.":[132],"3D-LOTUS++":[133],"achieves":[134],"per-formance":[136],"setting":[142],"standard":[145],"manipulation.":[150],"Code,":[151],"dataset,":[152],"real":[153],"robot":[154],"videos":[155],"trained":[157],"models":[158],"are":[159],"available":[160],"at":[161],"https://www.di.ens.fr/willow/research/gembench/.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}