{"id":"https://openalex.org/W4413945175","doi":"https://doi.org/10.1109/icra55743.2025.11128559","title":"3D Spatial Understanding in MLLMs: Disambiguation and Evaluation","display_name":"3D Spatial Understanding in MLLMs: Disambiguation and Evaluation","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413945175","doi":"https://doi.org/10.1109/icra55743.2025.11128559"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128559","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":["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/A5113135621","display_name":"Chun-Peng Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Chun-Peng Chang","raw_affiliation_strings":["DFKI Augmented Vision, (German Research Center for Artificial Intelligence)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DFKI Augmented Vision, (German Research Center for Artificial Intelligence)","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046969927","display_name":"Alain Pagani","orcid":"https://orcid.org/0000-0002-5136-0837"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alain Pagani","raw_affiliation_strings":["DFKI Augmented Vision, (German Research Center for Artificial Intelligence)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DFKI Augmented Vision, (German Research Center for Artificial Intelligence)","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051650277","display_name":"Didier Stricker","orcid":"https://orcid.org/0009-0004-8794-6858"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Didier Stricker","raw_affiliation_strings":["DFKI Augmented Vision, (German Research Center for Artificial Intelligence)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DFKI Augmented Vision, (German Research Center for Artificial Intelligence)","institution_ids":["https://openalex.org/I33256026"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I33256026"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13537","last_page":"13544"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.8858000040054321,"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"}},"topics":[{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.8858000040054321,"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/computer-science","display_name":"Computer science","score":0.664020299911499},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.413274347782135},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4059414863586426},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33098334074020386}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.664020299911499},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.413274347782135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4059414863586426},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33098334074020386}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128559","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":19,"referenced_works":["https://openalex.org/W2963121255","https://openalex.org/W3095974555","https://openalex.org/W3107521863","https://openalex.org/W3175234951","https://openalex.org/W3182910454","https://openalex.org/W3203949114","https://openalex.org/W4212872366","https://openalex.org/W4214684415","https://openalex.org/W4226376247","https://openalex.org/W4312385518","https://openalex.org/W4312852845","https://openalex.org/W4385245566","https://openalex.org/W4386076628","https://openalex.org/W4389524500","https://openalex.org/W4390871962","https://openalex.org/W4394773594","https://openalex.org/W4402716380","https://openalex.org/W4402727764","https://openalex.org/W4409263159"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"have":[5],"made":[6],"significant":[7],"progress":[8],"in":[9,42],"tasks":[10],"such":[11],"as":[12,50,86],"image":[13],"captioning":[14],"and":[15,39,90,121],"question":[16],"answering.":[17],"However,":[18],"while":[19],"these":[20],"models":[21],"can":[22],"generate":[23],"realistic":[24],"captions,":[25],"they":[26],"often":[27],"struggle":[28],"with":[29,55],"providing":[30],"precise":[31],"instructions,":[32],"particularly":[33],"when":[34],"it":[35],"comes":[36],"to":[37,77,83,114,119],"localizing":[38],"disambiguating":[40],"objects":[41,69],"complex":[43],"3D":[44,98,143,147],"environments.":[45],"This":[46],"capability":[47],"is":[48,65],"critical":[49],"MLLMs":[51],"become":[52],"more":[53],"integrated":[54],"collaborative":[56],"robotic":[57],"systems.":[58],"In":[59,106],"scenarios":[60],"where":[61],"a":[62],"target":[63,104,123],"object":[64,88],"surrounded":[66],"by":[67],"similar":[68],"(distractors),":[70],"robots":[71],"must":[72],"deliver":[73],"clear,":[74],"spatially-aware":[75],"instructions":[76],"guide":[78],"humans":[79],"effectively.":[80],"We":[81],"refer":[82],"this":[84],"challenge":[85],"contextual":[87],"localization":[89],"disambiguation,":[91],"which":[92],"imposes":[93],"stricter":[94],"constraints":[95],"than":[96],"conventional":[97,133],"dense":[99],"captioning,":[100],"especially":[101],"regarding":[102],"ensuring":[103],"exclusivity.":[105],"response,":[107],"we":[108],"propose":[109],"simple":[110],"yet":[111],"effective":[112],"techniques":[113],"enhance":[115],"the":[116],"model's":[117],"ability":[118],"localize":[120],"disambiguate":[122],"objects.":[124],"Our":[125],"approach":[126],"not":[127],"only":[128],"achieves":[129],"state-of-the-art":[130],"performance":[131],"on":[132],"metrics":[134],"that":[135],"evaluate":[136],"sentence":[137],"similarity,":[138],"but":[139],"also":[140],"demonstrates":[141],"improved":[142],"spatial":[144],"understanding":[145],"through":[146],"visual":[148],"grounding":[149],"model.":[150],"https://birdy666.github.io/projects/3d_spatial_understanding_in_mllms/":[151]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}