{"id":"https://openalex.org/W7164803867","doi":"https://doi.org/10.1145/3805622.3810883","title":"PRISM: Preference-Guided Semantic Reasoning with Vision-Language Models for Object Goal Navigation","display_name":"PRISM: Preference-Guided Semantic Reasoning with Vision-Language Models for Object Goal Navigation","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164803867","doi":"https://doi.org/10.1145/3805622.3810883"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810883","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810883","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810883","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100776108","display_name":"Zijian Liu","orcid":"https://orcid.org/0000-0002-9481-8027"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijian Liu","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0009-2848-2332","affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011457041","display_name":"Cong Pan","orcid":"https://orcid.org/0000-0001-5959-4294"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Pan","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-5959-4294","affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123122352","display_name":"Chengjie Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengjie Fan","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0002-3574-4213","affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138676124","display_name":"Wanjie Cai","orcid":"https://orcid.org/0009-0002-7290-2081"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanjie Cai","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0002-7290-2081","affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080106267","display_name":"Xichen Ding","orcid":"https://orcid.org/0009-0003-5649-058X"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xichen Ding","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0002-5008-3986","affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061215231","display_name":"Jie Qin","orcid":"https://orcid.org/0000-0002-0306-534X"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Qin","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-0306-534X","affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93328541,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"865","last_page":"873"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9592000246047974,"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":0.9592000246047974,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0052999998442828655,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.004000000189989805,"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/interpretability","display_name":"Interpretability","score":0.8349000215530396},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5972999930381775},{"id":"https://openalex.org/keywords/semantic-mapping","display_name":"Semantic mapping","score":0.38040000200271606},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.36410000920295715},{"id":"https://openalex.org/keywords/semantic-memory","display_name":"Semantic memory","score":0.35530000925064087},{"id":"https://openalex.org/keywords/semantic-data-model","display_name":"Semantic data model","score":0.352400004863739},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.32850000262260437},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.3025999963283539}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8349000215530396},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7605999708175659},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6463000178337097},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5972999930381775},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4499000012874603},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3944000005722046},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.38040000200271606},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.35530000925064087},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29809999465942383},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.2667999863624573},{"id":"https://openalex.org/C193125573","wikidata":"https://www.wikidata.org/wiki/Q7449065","display_name":"Semantic interpretation","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2515999972820282},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810883","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810883","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810883","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810883","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1355211897","display_name":null,"funder_award_id":"BK20250082","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G2484764267","display_name":null,"funder_award_id":"GZC20252739","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G2711493907","display_name":null,"funder_award_id":"NE2025010","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G5334781880","display_name":null,"funder_award_id":"62506164","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7079202155","display_name":null,"funder_award_id":"2025ZD0122903","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2953127211","https://openalex.org/W2962732398","https://openalex.org/W2964339842","https://openalex.org/W3009928773","https://openalex.org/W3109001458","https://openalex.org/W3179552988","https://openalex.org/W3204469733","https://openalex.org/W3210395242","https://openalex.org/W3211462570","https://openalex.org/W4214643368","https://openalex.org/W4312386498","https://openalex.org/W4312618696","https://openalex.org/W4312647074","https://openalex.org/W4313156423","https://openalex.org/W4313180266","https://openalex.org/W4386066572","https://openalex.org/W4386071636","https://openalex.org/W4386083015","https://openalex.org/W4389666115","https://openalex.org/W4390871755","https://openalex.org/W4390872462","https://openalex.org/W4390873100","https://openalex.org/W4392939491","https://openalex.org/W4401417061","https://openalex.org/W4401417236","https://openalex.org/W4402754246","https://openalex.org/W4413145337","https://openalex.org/W4416749631","https://openalex.org/W7133197571","https://openalex.org/W7133210288","https://openalex.org/W7138042012"],"related_works":[],"abstract_inverted_index":{"Object":[0],"Goal":[1],"Navigation":[2],"(ObjectNav)":[3],"requires":[4],"an":[5],"agent":[6,107],"to":[7,32,80,108,129],"locate":[8],"a":[9,64,88],"target":[10,29,115],"object":[11,84],"in":[12,24,58],"unseen":[13],"environments":[14],"based":[15],"on":[16,47,118,144,170,174,179],"partial":[17],"visual":[18],"observations.":[19],"A":[20],"central":[21],"challenge":[22],"lies":[23],"reasoning":[25,67],"about":[26],"where":[27],"the":[28,77,106,119,145],"is":[30],"likely":[31,114],"appear":[33],"under":[34,140],"semantic":[35,52,66,83,103,135,141],"uncertainty,":[36],"sparse":[37],"observations,":[38],"and":[39,56,68,101,137,149,176],"ambiguous":[40],"scene":[41],"cues.":[42],"Existing":[43],"approaches":[44],"often":[45],"rely":[46],"extensive":[48],"training":[49],"or":[50],"static":[51],"priors,":[53],"limiting":[54],"adaptability":[55],"interpretability":[57],"unfamiliar":[59],"environments.":[60],"We":[61],"introduce":[62],"PRISM,":[63],"preference-guided":[65],"mapping":[69],"framework":[70],"that":[71,94,154],"integrates":[72],"vision-language":[73],"models":[74],"(VLMs)":[75],"into":[76],"navigation":[78],"loop":[79],"support":[81],"efficient":[82],"search.":[85],"PRISM":[86,121],"constructs":[87],"dynamic":[89],"Preference-guided":[90],"Semantic":[91],"Map":[92],"(PSM)":[93],"aggregates":[95],"observed":[96],"semantics,":[97],"predicted":[98],"unobserved":[99],"regions,":[100],"language-mediated":[102],"reasoning,":[104],"enabling":[105],"incrementally":[109],"refine":[110],"its":[111],"belief":[112],"over":[113,160],"locations.":[116],"Based":[117],"PSM,":[120],"further":[122],"employs":[123],"Adaptive":[124],"Preference":[125],"Exploration":[126],"Strategies":[127],"(APES)":[128],"adjust":[130],"exploration":[131],"behavior":[132],"using":[133],"contextual":[134],"cues":[136],"historical":[138],"feedback":[139],"ambiguity.":[142],"Experiments":[143],"Gibson,":[146,171],"Matterport3D":[147],"(MP3D),":[148],"Habitat-Matterport3D":[150],"(HM3D)":[151],"datasets":[152],"show":[153],"our":[155],"method":[156],"achieves":[157],"consistent":[158],"improvements":[159],"prior":[161],"training-free":[162],"approaches,":[163],"yielding":[164],"absolute":[165],"gains":[166],"of":[167],"+2.7%":[168],"SR":[169,173,178],"+2.8%":[172],"MP3D,":[175],"+3.2%":[177],"HM3D.":[180]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}
