{"id":"https://openalex.org/W4405253300","doi":"https://doi.org/10.1109/iccv51701.2025.00731","title":"SAME: Learning Generic Language-Guided Visual Navigation with State-Adaptive Mixture of Experts","display_name":"SAME: Learning Generic Language-Guided Visual Navigation with State-Adaptive Mixture of Experts","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405253300","doi":"https://doi.org/10.1109/iccv51701.2025.00731"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00731","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00731","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.05552","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045879629","display_name":"Gengze Zhou","orcid":"https://orcid.org/0000-0003-0279-9277"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Gengze Zhou","raw_affiliation_strings":["The University of Adelaide"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Adelaide","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036105537","display_name":"Yicong Hong","orcid":"https://orcid.org/0000-0002-5068-1508"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yicong Hong","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101452807","display_name":"Zun Wang","orcid":"https://orcid.org/0009-0006-1478-5963"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]},{"id":"https://openalex.org/I1333535994","display_name":"University of North Carolina Health Care","ror":"https://ror.org/00qz24g20","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1333535994"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zun Wang","raw_affiliation_strings":["UNC, Chapel Hill"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNC, Chapel Hill","institution_ids":["https://openalex.org/I1333535994","https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110807146","display_name":"Chongyang Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chongyang Zhao","raw_affiliation_strings":["UNSW Sydney"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNSW Sydney","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001987532","display_name":"Mohit Bansal","orcid":"https://orcid.org/0000-0001-5522-1351"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]},{"id":"https://openalex.org/I1333535994","display_name":"University of North Carolina Health Care","ror":"https://ror.org/00qz24g20","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1333535994"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohit Bansal","raw_affiliation_strings":["UNC, Chapel Hill"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNC, Chapel Hill","institution_ids":["https://openalex.org/I1333535994","https://openalex.org/I114027177"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060958969","display_name":"Qi Wu","orcid":"https://orcid.org/0000-0003-3631-256X"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qi Wu","raw_affiliation_strings":["The University of Adelaide"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Adelaide","institution_ids":["https://openalex.org/I5681781"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5045879629"],"corresponding_institution_ids":["https://openalex.org/I5681781"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00114339,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7794","last_page":"7807"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9990000128746033,"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":0.9990000128746033,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9915000200271606,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9768999814987183,"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/computer-science","display_name":"Computer science","score":0.673032820224762},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.6269243955612183},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5045942068099976},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37570667266845703},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3612906038761139},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35158801078796387},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.21184751391410828}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.673032820224762},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.6269243955612183},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5045942068099976},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37570667266845703},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3612906038761139},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35158801078796387},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.21184751391410828}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00731","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00731","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:2412.05552","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.05552","pdf_url":"https://arxiv.org/pdf/2412.05552","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.05552","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.05552","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.05552","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.05552","pdf_url":"https://arxiv.org/pdf/2412.05552","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4405253300.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"The":[0],"academic":[1],"field":[2],"of":[3,24,48,54,84,101,129],"learning":[4,93],"instruction-guided":[5],"visual":[6],"navigation":[7,70,94,132],"can":[8],"be":[9],"generally":[10],"categorized":[11],"into":[12,72],"high-level":[13],"category-specific":[14],"search":[15],"and":[16,60,75,88,95,117],"low-level":[17],"language-guided":[18],"navigation,":[19],"depending":[20],"on":[21,39,114],"the":[22,29,32,36,45,51,58,81],"granularity":[23],"language":[25,116],"instruction,":[26],"in":[27,92],"which":[28],"former":[30],"emphasizes":[31],"exploration":[33],"process,":[34],"while":[35],"latter":[37],"concentrates":[38],"following":[40],"detailed":[41],"textual":[42],"commands.":[43],"Despite":[44],"differing":[46],"focuses":[47],"these":[49],"tasks,":[50],"underlying":[52],"requirements":[53],"interpreting":[55],"instructions,":[56],"comprehending":[57],"surroundings,":[59],"inferring":[61],"action":[62],"decisions":[63,112],"remain":[64],"consistent.":[65],"This":[66],"paper":[67],"consolidates":[68],"diverse":[69],"tasks":[71,133],"a":[73,97,125],"unified":[74],"generic":[76],"framework":[77],"--":[78],"we":[79,123],"investigate":[80],"core":[82],"difficulties":[83],"sharing":[85],"general":[86],"knowledge":[87],"exploiting":[89],"task-specific":[90,143],"capabilities":[91],"propose":[96],"novel":[98],"State-Adaptive":[99],"Mixture":[100],"Experts":[102],"(SAME)":[103],"model":[104],"that":[105,135],"effectively":[106],"enables":[107],"an":[108],"agent":[109,127],"to":[110,142],"infer":[111],"based":[113],"different-granularity":[115],"dynamic":[118],"observations.":[119],"Powered":[120],"by":[121],"SAME,":[122],"present":[124],"versatile":[126],"capable":[128],"addressing":[130],"seven":[131],"simultaneously":[134],"outperforms":[136],"or":[137],"achieves":[138],"highly":[139],"comparable":[140],"performance":[141],"agents.":[144]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}