{"id":"https://openalex.org/W4415163232","doi":"https://doi.org/10.1109/iccv51701.2025.00761","title":"Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation","display_name":"Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415163232","doi":"https://doi.org/10.1109/iccv51701.2025.00761"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.04047","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101999331","display_name":"Ziyu Zhu","orcid":"https://orcid.org/0009-0003-6180-5881"},"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":"Ziyu Zhu","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011464832","display_name":"Xilin Wang","orcid":"https://orcid.org/0009-0009-4770-7082"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xilin Wang","raw_affiliation_strings":["BIGAI,State Key Laboratory of General Artificial Intelligence,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BIGAI,State Key Laboratory of General Artificial Intelligence,China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010232516","display_name":"Yixuan Li","orcid":"https://orcid.org/0000-0003-0333-9838"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixuan Li","raw_affiliation_strings":["BIGAI,State Key Laboratory of General Artificial Intelligence,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BIGAI,State Key Laboratory of General Artificial Intelligence,China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033685364","display_name":"Zhuofan Zhang","orcid":"https://orcid.org/0009-0000-4581-0718"},"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":"Zhuofan Zhang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100689683","display_name":"Xiaojian Ma","orcid":"https://orcid.org/0000-0002-2611-6568"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojian Ma","raw_affiliation_strings":["BIGAI,State Key Laboratory of General Artificial Intelligence,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BIGAI,State Key Laboratory of General Artificial Intelligence,China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100393445","display_name":"Yixin Chen","orcid":"https://orcid.org/0000-0002-3704-4432"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixin Chen","raw_affiliation_strings":["BIGAI,State Key Laboratory of General Artificial Intelligence,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BIGAI,State Key Laboratory of General Artificial Intelligence,China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067007325","display_name":"Baoxiong Jia","orcid":"https://orcid.org/0000-0002-4968-3290"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baoxiong Jia","raw_affiliation_strings":["BIGAI,State Key Laboratory of General Artificial Intelligence,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BIGAI,State Key Laboratory of General Artificial Intelligence,China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109703694","display_name":"Wei Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Liang","raw_affiliation_strings":["Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029636169","display_name":"Qian Yu","orcid":"https://orcid.org/0000-0001-9981-3738"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Yu","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102011846","display_name":"Zhidong Deng","orcid":"https://orcid.org/0000-0001-9970-1023"},"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":"Zhidong Deng","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101529673","display_name":"Siyuan Huang","orcid":"https://orcid.org/0000-0002-1107-2312"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Huang","raw_affiliation_strings":["BIGAI,State Key Laboratory of General Artificial Intelligence,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BIGAI,State Key Laboratory of General Artificial Intelligence,China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100404155","display_name":"Qing Li","orcid":"https://orcid.org/0000-0003-0297-4346"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Li","raw_affiliation_strings":["BIGAI,State Key Laboratory of General Artificial Intelligence,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BIGAI,State Key Laboratory of General Artificial Intelligence,China","institution_ids":["https://openalex.org/I4210100255"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"8120","last_page":"8132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9860000014305115,"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":0.9860000014305115,"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":0.9835000038146973,"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/T12290","display_name":"Human Motion and Animation","score":0.9781000018119812,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.8353999853134155},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.7301999926567078},{"id":"https://openalex.org/keywords/embodied-agent","display_name":"Embodied agent","score":0.524399995803833},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5200999975204468},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4927999973297119},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4803999960422516},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4717999994754791},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4456999897956848}],"concepts":[{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.8353999853134155},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7494000196456909},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.7301999926567078},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.59579998254776},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.524399995803833},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5200999975204468},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4927999973297119},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4803999960422516},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4717999994754791},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4456999897956848},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43849998712539673},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4212000072002411},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.38199999928474426},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3684999942779541},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C2776010242","wikidata":"https://www.wikidata.org/wiki/Q4677575","display_name":"Active perception","level":3,"score":0.2858000099658966},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2540000081062317}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.04047","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.04047","pdf_url":"https://arxiv.org/pdf/2507.04047","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"doi:10.48550/arxiv.2507.04047","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.04047","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.04047","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.04047","pdf_url":"https://arxiv.org/pdf/2507.04047","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[],"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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Embodied":[0],"scene":[1],"understanding":[2],"requires":[3],"not":[4],"only":[5],"comprehending":[6],"visual-spatial":[7],"information":[8],"that":[9,71,143,170],"has":[10],"been":[11],"observed":[12],"but":[13,47],"also":[14],"determining":[15],"where":[16],"to":[17,51,82],"explore":[18,55,84],"next":[19],"in":[20,35,186],"the":[21,49,110,214],"3D":[22,26,39,114],"physical":[23],"world.":[24],"Existing":[25],"Vision-Language":[27],"(3D-VL)":[28],"models":[29],"primarily":[30],"focus":[31],"on":[32,189],"grounding":[33,121,135,219],"objects":[34],"static":[36],"observations":[37],"from":[38,106,153],"reconstruction,":[40],"such":[41],"as":[42,128],"meshes":[43],"and":[44,54,85,122,131,136,156,166,176,184,193,208,220],"point":[45],"clouds,":[46],"lack":[48],"ability":[50],"actively":[52],"perceive":[53],"their":[56,87],"environment.":[57,88],"To":[58],"address":[59],"this":[60],"limitation,":[61],"we":[62],"introduce":[63],"\\underline{\\textbf{M}}ove":[64],"\\underline{\\textbf{t}}o":[65],"\\underline{\\textbf{U}}nderstand":[66],"(\\textbf{\\model}),":[67],"a":[68,148],"unified":[69,118],"framework":[70],"integrates":[72],"active":[73],"perception":[74],"with":[75],"\\underline{\\textbf{3D}}":[76],"vision-language":[77],"learning,":[78,100],"enabling":[79,101],"embodied":[80,164,223],"agents":[81],"effectively":[83],"understand":[86],"This":[89],"is":[90],"achieved":[91],"by":[92,180],"three":[93],"key":[94],"innovations:":[95],"1)":[96],"Online":[97],"query-based":[98],"representation":[99],"direct":[102],"spatial":[103],"memory":[104],"construction":[105],"RGB-D":[107,158],"frames,":[108],"eliminating":[109],"need":[111],"for":[112,120,222],"explicit":[113],"reconstruction.":[115],"2)":[116],"A":[117],"objective":[119],"exploring,":[123],"which":[124],"represents":[125],"unexplored":[126],"locations":[127],"frontier":[129,137],"queries":[130],"jointly":[132],"optimizes":[133],"object":[134],"selection.":[138],"3)":[139],"End-to-end":[140],"trajectory":[141],"learning":[142,175],"combines":[144],"\\textbf{V}ision-\\textbf{L}anguage-\\textbf{E}xploration":[145],"pre-training":[146],"over":[147],"million":[149],"diverse":[150,201],"trajectories":[151],"collected":[152],"both":[154],"simulated":[155],"real-world":[157],"sequences.":[159],"Extensive":[160],"evaluations":[161],"across":[162],"various":[163],"navigation":[165,178,199],"question-answering":[167],"benchmarks":[168],"show":[169],"MTU3D":[171],"outperforms":[172],"state-of-the-art":[173],"reinforcement":[174],"modular":[177],"approaches":[179],"14\\%,":[181],"23\\%,":[182],"9\\%,":[183],"2\\%":[185],"success":[187],"rate":[188],"HM3D-OVON,":[190],"GOAT-Bench,":[191],"SG3D,":[192],"A-EQA,":[194],"respectively.":[195],"\\model's":[196],"versatility":[197],"enables":[198],"using":[200],"input":[202],"modalities,":[203],"including":[204],"categories,":[205],"language":[206],"descriptions,":[207],"reference":[209],"images.":[210],"These":[211],"findings":[212],"highlight":[213],"importance":[215],"of":[216],"bridging":[217],"visual":[218],"exploration":[221],"intelligence.":[224]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-14T00:00:00"}