{"id":"https://openalex.org/W4415538122","doi":"https://doi.org/10.1145/3746027.3754495","title":"Uni-Sight: An E2E Vision-Language-Action System Unifying Multi-View Alignment and Multi-Modal Fusion","display_name":"Uni-Sight: An E2E Vision-Language-Action System Unifying Multi-View Alignment and Multi-Modal Fusion","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538122","doi":"https://doi.org/10.1145/3746027.3754495"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754495","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754495","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":"article","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":"https://openalex.org/A5057418761","display_name":"Daixun Li","orcid":"https://orcid.org/0009-0006-8689-6929"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daixun Li","raw_affiliation_strings":["Xidian University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0006-8689-6929","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sibo He","orcid":"https://orcid.org/0009-0001-9704-1209"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sibo He","raw_affiliation_strings":["Xidian University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0001-9704-1209","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101295851","display_name":"Jiayun Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayun Tian","raw_affiliation_strings":["Xidian University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0001-7394-1851","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yusi Zhang","orcid":"https://orcid.org/0009-0004-2179-2665"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yusi Zhang","raw_affiliation_strings":["Xidian University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0004-2179-2665","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052163069","display_name":"Weiying Xie","orcid":"https://orcid.org/0000-0001-8310-024X"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiying Xie","raw_affiliation_strings":["Xidian University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0001-8310-024X","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041651389","display_name":"Mingxiang Cao","orcid":"https://orcid.org/0009-0000-1892-3645"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingxiang Cao","raw_affiliation_strings":["Xidian University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0000-1892-3645","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112318142","display_name":"Liu Donglai","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Donglai Liu","raw_affiliation_strings":["Xidian University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0004-7047-5762","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zirui Li","orcid":"https://orcid.org/0009-0004-6589-0478"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zirui Li","raw_affiliation_strings":["Xidian University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0004-6589-0478","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109386208","display_name":"Tianlin Hui","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianlin Hui","raw_affiliation_strings":["Xidian University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0005-5178-9309","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rui Huang","orcid":"https://orcid.org/0009-0001-3368-1688"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Huang","raw_affiliation_strings":["Xidian University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0001-3368-1688","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067798266","display_name":"Yunsong Li","orcid":"https://orcid.org/0000-0002-0234-6270"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunsong Li","raw_affiliation_strings":["Xidian University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0002-0234-6270","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25338854,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7142","last_page":"7151"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9959999918937683,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9958999752998352,"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/task","display_name":"Task (project management)","score":0.5795000195503235},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5271000266075134},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5133000016212463},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49729999899864197},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42980000376701355},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.41620001196861267},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4050000011920929},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.3921000063419342},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3447999954223633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8079000115394592},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5795000195503235},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5271000266075134},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5133000016212463},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49729999899864197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48399999737739563},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42980000376701355},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.41620001196861267},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4050000011920929},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.3921000063419342},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.35280001163482666},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3379000127315521},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3073999881744385},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.29269999265670776},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2838999927043915},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.28029999136924744},{"id":"https://openalex.org/C144543869","wikidata":"https://www.wikidata.org/wiki/Q2738570","display_name":"Mobile computing","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.26030001044273376},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.25920000672340393},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754495","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754495","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W3176368002","https://openalex.org/W4312933868","https://openalex.org/W4385430679","https://openalex.org/W4392172801","https://openalex.org/W4402716288","https://openalex.org/W4402727574"],"related_works":[],"abstract_inverted_index":{"Vision-Language-Action":[0],"(VLA)":[1],"systems":[2,13],"are":[3,149],"crucial":[4],"for":[5,28,46],"autonomous":[6],"decision-making":[7],"in":[8,32,140],"embodied":[9],"intelligence.":[10],"While":[11],"current":[12],"have":[14],"advanced":[15],"the":[16,64,114,130],"instruction-following":[17],"capabilities,":[18],"their":[19],"limited":[20,102],"spatial":[21,94,99],"perception":[22],"often":[23],"leads":[24],"to":[25],"suboptimal":[26],"performance":[27,122],"mobile":[29,48,110],"manipulation":[30,111],"tasks":[31,112],"unstructured":[33],"environments.":[34],"To":[35],"address":[36],"this":[37],"challenge,":[38],"we":[39,66,82],"propose":[40],"Uni-Sight,":[41],"an":[42],"end-to-end":[43],"VLA":[44],"system":[45],"robust":[47,120],"manipulation.":[49],"Uni-Sight":[50,126],"unifies":[51],"decision-making,":[52],"perception,":[53],"and":[54,119,136,143,147],"control":[55],"through":[56],"joint":[57],"training,":[58],"enabling":[59],"synchronized":[60],"cross-component":[61],"optimization.":[62],"Within":[63],"system,":[65],"introduce":[67],"Latent":[68],"Feature":[69],"Aligner":[70],"(LFA)":[71],"that":[72],"ensures":[73,97],"accurate":[74],"target":[75],"localization":[76],"by":[77,92],"aligning":[78],"multi-view":[79],"data.":[80],"Specifically,":[81],"develop":[83],"Domain":[84],"Transfer":[85],"Policy":[86],"(DTP),":[87],"a":[88,128],"hierarchical":[89],"policy":[90],"constrained":[91],"LiDAR-guided":[93],"priors,":[95],"which":[96],"3D":[98],"understanding":[100],"with":[101],"visual":[103],"coverage.":[104],"Extensive":[105],"experiments":[106],"on":[107],"20":[108],"real-world":[109],"demonstrate":[113],"high":[115],"task":[116],"success":[117,131],"rate":[118,132],"execution":[121],"of":[123,133],"Uni-Sight.":[124],"Our":[125],"achieves":[127],"3.04\u00d7":[129],"existing":[134],"methods,":[135],"exhibits":[137],"superior":[138],"generalization":[139],"both":[141],"long-horizon":[142],"zero-shot":[144],"scenes.":[145],"Code":[146],"dataset":[148],"publicly":[150],"available":[151],"at":[152],"https://github.com/trantor2nd/Uni-Sight.":[153]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-25T00:00:00"}
