{"id":"https://openalex.org/W4415540500","doi":"https://doi.org/10.1145/3746027.3755232","title":"Ali-UI: Enhancing Complex Vision-Language Navigation with Alignment of Unified Map and Instruction Parsing","display_name":"Ali-UI: Enhancing Complex Vision-Language Navigation with Alignment of Unified Map and Instruction Parsing","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540500","doi":"https://doi.org/10.1145/3746027.3755232"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755232","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shanshan Li","orcid":"https://orcid.org/0009-0002-8003-5977"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanshan Li","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-8003-5977","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiawei Hou","orcid":"https://orcid.org/0000-0001-5830-6510"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Hou","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5830-6510","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111997249","display_name":"Da Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Da Huang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China and Shanghai Innovation Institution, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-5139-1191","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China and Shanghai Innovation Institution, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084959430","display_name":"Yanwei Fu","orcid":"https://orcid.org/0000-0002-6595-6893"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanwei Fu","raw_affiliation_strings":["Fudan University, Shanghai, China and Shanghai Innovation Institution, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6595-6893","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China and Shanghai Innovation Institution, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003418019","display_name":"Xiangyang Xue","orcid":"https://orcid.org/0000-0002-4897-9209"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyang Xue","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4897-9209","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"3913","last_page":"3922"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9873999953269958,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/leverage","display_name":"Leverage (statistics)","score":0.7171000242233276},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5666999816894531},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5652999877929688},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.5552999973297119},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4884999990463257},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.46320000290870667},{"id":"https://openalex.org/keywords/semantic-mapping","display_name":"Semantic mapping","score":0.43470001220703125},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.39969998598098755}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.817799985408783},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7171000242233276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6535000205039978},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5666999816894531},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5652999877929688},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5552999973297119},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4884999990463257},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46380001306533813},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.46320000290870667},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.43470001220703125},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.39969998598098755},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.38370001316070557},{"id":"https://openalex.org/C57077369","wikidata":"https://www.wikidata.org/wiki/Q7075747","display_name":"Occupancy grid mapping","level":4,"score":0.37130001187324524},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.35600000619888306},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.33239999413490295},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3287999927997589},{"id":"https://openalex.org/C2983008078","wikidata":"https://www.wikidata.org/wiki/Q863495","display_name":"Grid cell","level":3,"score":0.314300000667572},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3019999861717224},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.288100004196167},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2849000096321106}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755232","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2593841437","https://openalex.org/W2964287316","https://openalex.org/W2964339842","https://openalex.org/W3034578524","https://openalex.org/W3086207594","https://openalex.org/W3105521436","https://openalex.org/W3169884222","https://openalex.org/W3201759799","https://openalex.org/W4225675121","https://openalex.org/W4382362889","https://openalex.org/W4386072289","https://openalex.org/W4390204337","https://openalex.org/W4394627367","https://openalex.org/W4401210454","https://openalex.org/W4401417236","https://openalex.org/W4408841099"],"related_works":[],"abstract_inverted_index":{"Visual":[0],"language":[1,15,37],"navigation":[2,84],"(VLN)":[3],"poses":[4],"challenges":[5],"in":[6,63,95,148,163,173,195],"guiding":[7],"agents":[8,88],"through":[9],"unseen":[10],"environments":[11,165],"based":[12],"on":[13,21],"natural":[14],"instructions.":[16,74,102],"Existing":[17],"methods":[18,60,172],"either":[19],"rely":[20],"imitation":[22],"learning,":[23],"for":[24,40,48,156],"which":[25],"training":[26],"across":[27],"various":[28],"complex":[29,100],"scenarios":[30],"remains":[31],"challenging,":[32],"or":[33],"leverage":[34],"large":[35],"visual":[36],"models":[38],"(LVLMs)":[39],"zero-shot":[41],"object":[42],"recognition":[43],"and":[44,68,98,111,134,141,151,179,189],"expert":[45],"iterative":[46],"reasoning":[47],"improved":[49,186],"scene":[50,116,180],"understanding.":[51],"Although":[52],"LVLMs":[53],"enhance":[54],"target":[55],"detection":[56],"generalization,":[57,181],"current":[58],"VLN":[59],"lack":[61],"robustness":[62],"terms":[64,174],"of":[65,132,175],"environmental":[66],"generalization":[67],"struggle":[69],"with":[70,129,136,182],"multi-step,":[71],"coarsely":[72,123],"directed":[73,124],"Addressing":[75],"these":[76],"challenges,":[77],"we":[78,104],"introduce":[79],"Ali-UI,":[80],"a":[81],"novel":[82],"vision-language":[83],"approach":[85],"that":[86,167],"enables":[87],"to":[89],"navigate":[90],"from":[91],"random":[92],"starting":[93],"points":[94],"unvisited":[96],"scenes":[97],"handle":[99],"multi-step":[101],"Specifically,":[103],"incorporate":[105],"continuously":[106],"accumulating":[107],"global":[108],"grid":[109],"maps":[110,114],"local":[112],"semantic":[113],"as":[115],"memory":[117],"by":[118,153,187,193],"employing":[119],"frontier-based":[120],"exploration.":[121],"Multi-step":[122],"commands":[125],"are":[126,146],"broken":[127],"down":[128],"the":[130,137,183,190],"assistance":[131],"LLaVA":[133],"matched":[135],"scene,":[138],"considering":[139],"temporal":[140],"spatial":[142],"alignment.":[143],"Panoramic":[144],"data":[145],"saved":[147],"topological":[149],"form":[150],"queried":[152],"instruction":[154],"segments":[155],"sequential":[157],"navigation.":[158],"Extensive":[159],"experiments":[160],"carried":[161],"out":[162],"simulated":[164],"demonstrate":[166],"Ali-UI":[168],"outperforms":[169],"existing":[170],"state-of-the-art":[171],"flexible":[176],"human":[177],"instructions":[178],"success":[184],"rate":[185],"23.37%":[188],"SPL":[191],"increased":[192],"19.27%":[194],"R2R":[196],"dataset.":[197]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}