{"id":"https://openalex.org/W4416034861","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.513","title":"DivScene: Towards Open-Vocabulary Object Navigation with Large Vision Language Models in Diverse Scenes","display_name":"DivScene: Towards Open-Vocabulary Object Navigation with Large Vision Language Models in Diverse Scenes","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034861","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.513"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.513","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.513","pdf_url":"https://aclanthology.org/2025.findings-emnlp.513.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.513.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100655132","display_name":"Zhaowei Wang","orcid":"https://orcid.org/0000-0002-7797-3316"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaowei Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068034382","display_name":"Hongming Zhang","orcid":"https://orcid.org/0000-0003-0976-1458"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongming Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046409172","display_name":"Tianqing Fang","orcid":"https://orcid.org/0000-0002-0186-8253"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianqing Fang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051209390","display_name":"Ye Tian","orcid":"https://orcid.org/0000-0001-9955-3438"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100369313","display_name":"Yue Yang","orcid":"https://orcid.org/0009-0003-5641-2899"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038055180","display_name":"Kaixin Ma","orcid":"https://orcid.org/0000-0001-7414-5673"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaixin Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022703491","display_name":"Xiaoman Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoman Pan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020880385","display_name":"Yangqiu Song","orcid":"https://orcid.org/0000-0002-7818-6090"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yangqiu Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":"9666","last_page":"9686"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9611999988555908,"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":0.9611999988555908,"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":0.007199999876320362,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.004999999888241291,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6998000144958496},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6549999713897705},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5967000126838684},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.4925000071525574},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.3889000117778778},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.373199999332428}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7558000087738037},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6998000144958496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6740999817848206},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6549999713897705},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5967000126838684},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5167999863624573},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.4925000071525574},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.3889000117778778},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.373199999332428},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.34790000319480896},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3287000060081482},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.31690001487731934},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2639999985694885}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.513","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.513","pdf_url":"https://aclanthology.org/2025.findings-emnlp.513.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-169139","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-169139","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.513","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.513","pdf_url":"https://aclanthology.org/2025.findings-emnlp.513.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034861.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Vision-Language":[1],"Models":[2],"(LVLMs)":[3],"have":[4],"achieved":[5],"significant":[6],"progress":[7],"in":[8,142],"tasks":[9],"like":[10],"visual":[11],"question":[12],"answering":[13],"and":[14,24,55,71,88,93],"document":[15],"understanding.":[16],"However,":[17],"their":[18],"potential":[19],"to":[20,110],"comprehend":[21],"embodied":[22],"environments":[23],"navigate":[25],"within":[26],"them":[27],"remains":[28],"underexplored.":[29],"In":[30],"this":[31],"work,":[32],"we":[33,107],"first":[34],"study":[35],"the":[36,112],"challenge":[37],"of":[38,58,68,101],"open-vocabulary":[39],"object":[40,103],"navigation":[41,104,122],"by":[42,139],"introducing":[43],"DIVSCENE,":[44],"a":[45,64,78],"large-scale":[46],"dataset":[47,62,92],"with":[48,86,115,128],"4,614":[49],"houses":[50],"across":[51],"81":[52],"scene":[53,72],"types":[54,73],"5,707":[56],"kinds":[57],"target":[59,69],"objects.":[60],"Our":[61],"provides":[63],"much":[65],"greater":[66],"diversity":[67],"objects":[70],"than":[74],"existing":[75],"datasets,":[76],"enabling":[77],"comprehensive":[79],"task":[80],"evaluation.":[81],"We":[82,118],"evaluated":[83],"various":[84],"methods":[85],"LVLMs":[87],"LLMs":[89],"on":[90],"our":[91],"found":[94],"that":[95,120],"current":[96],"models":[97],"still":[98],"fall":[99],"short":[100],"open-vocab":[102],"ability.":[105],"Then,":[106],"fine-tuned":[108],"LVLMs1":[109],"predict":[111],"next":[113],"action":[114],"CoT":[116],"explanations.":[117],"observe":[119],"LVLM\u2019s":[121],"ability":[123],"can":[124],"be":[125],"improved":[126],"substantially":[127],"only":[129],"BFS-generated":[130],"shortest":[131],"paths":[132],"without":[133],"any":[134],"human":[135],"supervision,":[136],"surpassing":[137],"GPT-4o":[138],"over":[140],"20%":[141],"success":[143],"rates.<p/>":[144]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}