{"id":"https://openalex.org/W4417449754","doi":"https://doi.org/10.48550/arxiv.2512.12622","title":"D3D-VLP: Dynamic 3D Vision-Language-Planning Model for Embodied Grounding and Navigation","display_name":"D3D-VLP: Dynamic 3D Vision-Language-Planning Model for Embodied Grounding and Navigation","publication_year":2025,"publication_date":"2025-12-14","ids":{"openalex":"https://openalex.org/W4417449754","doi":"https://doi.org/10.48550/arxiv.2512.12622"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2512.12622","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.12622","pdf_url":"https://arxiv.org/pdf/2512.12622","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,"listed_in":[],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.12622","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092276634","display_name":"Zihan Wang","orcid":"https://orcid.org/0000-0001-7527-5955","observed_orcids":["https://orcid.org/0000-0001-7527-5955"]},"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":"Wang, Zihan","raw_affiliation_strings":["School of Computing , National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing , National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100334444","display_name":"Seungjun Lee","orcid":"https://orcid.org/0009-0005-7556-4868","observed_orcids":["https://orcid.org/0009-0005-7556-4868"]},"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":"Lee, Seungjun","raw_affiliation_strings":["School of Computing , National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing , National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016663057","display_name":"Guangzhao Dai","orcid":"https://orcid.org/0000-0003-4111-9334","observed_orcids":["https://orcid.org/0000-0003-4111-9334"]},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dai, Guangzhao","raw_affiliation_strings":["Nanjing University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071967339","display_name":"Gim Hee Lee","orcid":"https://orcid.org/0000-0002-1583-0475","observed_orcids":["https://orcid.org/0000-0002-1583-0475"]},"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":"Lee, Gim Hee","raw_affiliation_strings":["School of Computing , National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing , National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8906000256538391,"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":0.8906000256538391,"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":0.06129999831318855,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.014800000004470348,"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/embodied-agents","display_name":"embodied agents","score":0.7310000061988831},{"id":"https://openalex.org/keywords/chain-of-thought","display_name":"chain-of-thought","score":0.6669999957084656},{"id":"https://openalex.org/keywords/3d-reasoning","display_name":"3D reasoning","score":0.6729999780654907},{"id":"https://openalex.org/keywords/object-goal-navigation","display_name":"object-goal navigation","score":0.6880000233650208},{"id":"https://openalex.org/keywords/vision-and-language-navigation","display_name":"vision-and-language navigation","score":0.6980000138282776},{"id":"https://openalex.org/keywords/e-learning","display_name":"online learning","score":0.4269999861717224},{"id":"https://openalex.org/keywords/mobile-manipulation","display_name":"mobile manipulation","score":0.7300000190734863},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.5370000004768372}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8820000290870667},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6995000243186951},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6650999784469604},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.607699990272522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.593999981880188},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5604000091552734},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5443000197410583},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4652999937534332},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.4569000005722046},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.43689998984336853},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.41769999265670776},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4171000123023987},{"id":"https://openalex.org/C185874996","wikidata":"https://www.wikidata.org/wiki/Q269699","display_name":"Interdependence","level":2,"score":0.398499995470047},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.351500004529953},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.31839999556541443},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30379998683929443},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2867000102996826},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2512.12622","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.12622","pdf_url":"https://arxiv.org/pdf/2512.12622","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,"listed_in":[],"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.2512.12622","doi":"https://doi.org/10.48550/arxiv.2512.12622","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.12622","pdf_url":null,"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,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.12622","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.12622","pdf_url":"https://arxiv.org/pdf/2512.12622","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,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417449754.pdf","grobid_xml":"https://content.openalex.org/works/W4417449754.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2776202271","https://openalex.org/W4393946417","https://openalex.org/W4398156429","https://openalex.org/W4403966354","https://openalex.org/W4406033487","https://openalex.org/W4407764269","https://openalex.org/W4408841099","https://openalex.org/W4412888464","https://openalex.org/W4413145659","https://openalex.org/W4413146466","https://openalex.org/W4414050622","https://openalex.org/W4414858116","https://openalex.org/W4415016638","https://openalex.org/W4415087953","https://openalex.org/W4417105317","https://openalex.org/W7081975628","https://openalex.org/W7160122410","https://openalex.org/W7160158679","https://openalex.org/W7220847659"],"related_works":["https://openalex.org/W4417094373","https://openalex.org/W4415163232","https://openalex.org/W4415329687","https://openalex.org/W7213505171","https://openalex.org/W7135237305","https://openalex.org/W7140327909","https://openalex.org/W7154057780","https://openalex.org/W7128789090","https://openalex.org/W4392972344","https://openalex.org/W4392886475"],"abstract_inverted_index":{"Embodied":[0],"agents":[1],"face":[2],"a":[3,57,74,104],"critical":[4],"dilemma":[5],"that":[6,48,119],"end-to-end":[7],"models":[8],"lack":[9],"interpretability":[10],"and":[11,21,53,60,82,94,115,129,148,152],"explicit":[12],"3D":[13,31,44],"reasoning,":[14],"while":[15],"modular":[16],"systems":[17],"ignore":[18],"cross-component":[19],"interdependencies":[20],"synergies.":[22],"To":[23,99],"bridge":[24],"this":[25,100],"gap,":[26],"we":[27,102],"propose":[28],"the":[29,161],"Dynamic":[30,43],"Vision-Language-Planning":[32],"Model":[33],"(D3D-VLP).":[34],"Our":[35,131],"model":[36],"introduces":[37],"two":[38],"key":[39],"innovations:":[40],"1)":[41],"A":[42,64],"Chain-of-Thought":[45],"(3D":[46],"CoT)":[47],"unifies":[49],"planning,":[50],"grounding,":[51],"navigation,":[52],"question":[54],"answering":[55],"within":[56],"single":[58],"3D-VLM":[59],"CoT":[61,89],"pipeline;":[62],"2)":[63],"Synergistic":[65],"Learning":[66],"from":[67,80,111],"Fragmented":[68],"Supervision":[69],"(SLFS)":[70],"strategy,":[71],"which":[72],"uses":[73],"masked":[75],"autoregressive":[76],"loss":[77],"to":[78,91],"learn":[79],"massive":[81],"partially-annotated":[83],"hybrid":[84,109],"data.":[85],"This":[86],"allows":[87],"different":[88],"components":[90],"mutually":[92],"reinforce":[93],"implicitly":[95],"supervise":[96],"each":[97],"other.":[98],"end,":[101],"construct":[103],"large-scale":[105],"dataset":[106],"with":[107,122],"10M":[108],"samples":[110],"5K":[112],"real":[113],"scans":[114],"20K":[116],"synthetic":[117],"scenes":[118],"are":[120],"compatible":[121],"online":[123],"learning":[124],"methods":[125],"such":[126],"as":[127],"RL":[128],"DAgger.":[130],"D3D-VLP":[132],"achieves":[133],"state-of-the-art":[134],"results":[135],"on":[136],"multiple":[137],"benchmarks,":[138],"including":[139],"Vision-and-Language":[140],"Navigation":[141,146,153],"(R2R-CE,":[142],"REVERIE-CE,":[143],"NavRAG-CE),":[144],"Object-goal":[145],"(HM3D-OVON),":[147],"Task-oriented":[149],"Sequential":[150],"Grounding":[151],"(SG3D).":[154],"Real-world":[155],"mobile":[156],"manipulation":[157],"experiments":[158],"further":[159],"validate":[160],"effectiveness.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":5}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-12-17T00:00:00"}