{"id":"https://openalex.org/W4413947072","doi":"https://doi.org/10.1109/icra55743.2025.11127464","title":"IRef-VLA: A Benchmark for Interactive Referential Grounding with Imperfect Language in 3D Scenes","display_name":"IRef-VLA: A Benchmark for Interactive Referential Grounding with Imperfect Language in 3D Scenes","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413947072","doi":"https://doi.org/10.1109/icra55743.2025.11127464"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127464","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127464","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":"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/A5073361709","display_name":"Haochen Zhang","orcid":"https://orcid.org/0009-0008-2933-2240"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Haochen Zhang","raw_affiliation_strings":["Carnegie Mellon University, Robotics Institute,Pittsburgh,PA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Robotics Institute,Pittsburgh,PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114638248","display_name":"Nader Zantout","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nader Zantout","raw_affiliation_strings":["Carnegie Mellon University, Robotics Institute,Pittsburgh,PA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Robotics Institute,Pittsburgh,PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093192252","display_name":"Pujith Kachana","orcid":"https://orcid.org/0009-0000-0671-5902"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pujith Kachana","raw_affiliation_strings":["Carnegie Mellon University, Robotics Institute,Pittsburgh,PA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Robotics Institute,Pittsburgh,PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101787171","display_name":"Ji Zhang","orcid":"https://orcid.org/0000-0001-6141-239X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ji Zhang","raw_affiliation_strings":["Carnegie Mellon University, Robotics Institute,Pittsburgh,PA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Robotics Institute,Pittsburgh,PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101634791","display_name":"Wenshan Wang","orcid":"https://orcid.org/0000-0001-7801-3803"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenshan Wang","raw_affiliation_strings":["Carnegie Mellon University, Robotics Institute,Pittsburgh,PA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Robotics Institute,Pittsburgh,PA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5073361709"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":2.671,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.91661473,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1677","last_page":"1683"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9988999962806702,"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/T12031","display_name":"Speech and dialogue systems","score":0.9929999709129333,"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/imperfect","display_name":"Imperfect","score":0.7599244713783264},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.7300713658332825},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6969555020332336},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6861916184425354},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42807719111442566},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3952326774597168},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19050627946853638},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1375865340232849},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.12925022840499878},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.11015009880065918},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.06029161810874939}],"concepts":[{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.7599244713783264},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.7300713658332825},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6969555020332336},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6861916184425354},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42807719111442566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3952326774597168},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19050627946853638},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1375865340232849},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.12925022840499878},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.11015009880065918},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06029161810874939},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11127464","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127464","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W1933349210","https://openalex.org/W2067912884","https://openalex.org/W2277195237","https://openalex.org/W2594519801","https://openalex.org/W2963244312","https://openalex.org/W2963800628","https://openalex.org/W2964339842","https://openalex.org/W2981422075","https://openalex.org/W3035154952","https://openalex.org/W3095974555","https://openalex.org/W3100923070","https://openalex.org/W3107521863","https://openalex.org/W3174510143","https://openalex.org/W3176641147","https://openalex.org/W3216418166","https://openalex.org/W4283332944","https://openalex.org/W4283788970","https://openalex.org/W4312852845","https://openalex.org/W4313162371","https://openalex.org/W4390872495","https://openalex.org/W4402354022","https://openalex.org/W4403600470"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2374250903","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/W2121910908","https://openalex.org/W3204019825"],"abstract_inverted_index":{"With":[0,195],"the":[1,53,62,71,75,102,107,154,162,185,210],"recent":[2,45],"rise":[3],"of":[4,112,164,190,212],"large":[5],"language":[6,31,41,63,155],"models,":[7,9,14],"vision-language":[8],"and":[10,57,91,128,139,148,177,188,219],"other":[11],"general":[12],"foundation":[13],"there":[15],"is":[16,36,101,149,223],"growing":[17],"potential":[18],"for":[19,87,106,204],"multimodal,":[20],"multi-task":[21],"robotics":[22],"that":[23,208],"can":[24],"operate":[25],"in":[26,94],"diverse":[27],"environments":[28],"given":[29],"natural":[30,40],"input.":[32],"One":[33],"such":[34],"application":[35],"indoor":[37],"navigation":[38,215],"using":[39,192],"instructions.":[42],"However,":[43],"despite":[44],"progress,":[46],"this":[47,79,196],"problem":[48],"remains":[49],"challenging":[50],"due":[51],"to":[52,172,183,200],"3D":[54,95,117,205],"spatial":[55],"reasoning":[56],"semantic":[58,126,137],"understanding":[59,207],"required.":[60],"Additionally,":[61],"used":[64],"may":[65],"be":[66],"imperfect":[67,98],"or":[68,158],"misaligned":[69],"with":[70,97,151,169],"scene,":[72],"further":[73],"complicating":[74],"task.":[76],"To":[77],"address":[78],"challenge,":[80],"we":[81,198],"curate":[82],"a":[83,174,180,202],"benchmark":[84],"dataset,":[85],"IRef-VLA,":[86],"Interactive":[88],"Referential":[89],"Vision":[90],"Language-guided":[92],"Action":[93],"Scenes":[96],"references.":[99],"IRef-VLA":[100],"largest":[103],"real-world":[104],"dataset":[105,134,166,218],"referential":[108,131],"grounding":[109],"task,":[110],"consisting":[111],"over":[113],"11.5":[114],"K":[115],"scanned":[116],"rooms":[118],"from":[119],"existing":[120],"datasets,":[121],"7.6":[122],"M":[123,130],"heuristically":[124],"generated":[125],"relations,":[127],"4.7":[129],"statements.":[132],"Our":[133],"also":[135,178],"contains":[136],"object":[138],"room":[140],"annotations,":[141,147],"scene":[142,206],"graphs,":[143],"navigable":[144],"free":[145],"space":[146],"augmented":[150],"statements":[152],"where":[153],"has":[156],"imperfections":[157],"ambiguities.":[159],"We":[160],"verify":[161],"generalizability":[163],"our":[165],"by":[167],"evaluating":[168],"state-of-the-art":[170],"models":[171],"obtain":[173],"performance":[175,186],"baseline":[176,182],"develop":[179],"graphsearch":[181],"demonstrate":[184],"bound":[187],"generation":[189],"alternatives":[191],"scene-graph":[193],"knowledge.":[194],"benchmark,":[197],"aim":[199],"provide":[201],"resource":[203],"aids":[209],"development":[211],"robust,":[213],"interactive":[214],"systems.":[216],"The":[217],"all":[220],"source":[221],"code":[222],"publicly":[224],"released<sup":[225],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[226,228],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup><sup":[227],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>https://github.com/HaochenZ11/IRef-VLA.":[229]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}