{"id":"https://openalex.org/W4416036853","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.468","title":"VLASCD: A Visual Language Action Model for Simultaneous Chatting and Decision Making","display_name":"VLASCD: A Visual Language Action Model for Simultaneous Chatting and Decision Making","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036853","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.468"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.468","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.468","pdf_url":"https://aclanthology.org/2025.emnlp-main.468.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.468.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027891370","display_name":"Zuojin Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zuojin Tang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100380060","display_name":"Bin Hu","orcid":"https://orcid.org/0000-0002-2974-1166"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bin Hu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101669579","display_name":"Chenyang Zhao","orcid":"https://orcid.org/0000-0002-3739-8409"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenyang Zhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101655468","display_name":"De Ma","orcid":"https://orcid.org/0000-0001-8700-938X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"De Ma","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084291326","display_name":"Gang Pan","orcid":"https://orcid.org/0000-0002-4049-6181"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gang Pan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5081883041","display_name":"Bin Liu","orcid":"https://orcid.org/0000-0003-2291-7592"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bin Liu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5027891370"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35161918,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9223","last_page":"9243"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.525600016117096,"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":0.525600016117096,"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":0.12389999628067017,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.06889999657869339,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5192000269889832},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.35760000348091125},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3188000023365021},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3093000054359436},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.27900001406669617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5831000208854675},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5192000269889832},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3993000090122223},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3716000020503998},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37040001153945923},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.34700000286102295},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.3199999928474426},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3176000118255615},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.468","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.468","pdf_url":"https://aclanthology.org/2025.emnlp-main.468.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.468","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.468","pdf_url":"https://aclanthology.org/2025.emnlp-main.468.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036853.pdf","grobid_xml":"https://content.openalex.org/works/W4416036853.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"large":[1],"pretrained":[2],"models":[3],"such":[4],"as":[5],"LLMs":[6],"(e.g.,":[7,12],"GPT":[8],"series)":[9],"and":[10,66,90,100,122,133],"VLAs":[11,123],"OpenVLA)":[13],"have":[14],"achieved":[15],"notable":[16],"progress":[17],"on":[18,105],"multimodal":[19,132],"tasks,":[20],"yet":[21],"they":[22],"are":[23],"built":[24],"upon":[25],"a":[26,54,76,128],"multi-input":[27,39],"single-output":[28],"(MISO)":[29],"paradigm.We":[30],"show":[31],"that":[32,62,80,112],"this":[33,70],"paradigm":[34],"fundamentally":[35],"limits":[36],"performance":[37],"in":[38,124],"multi-output":[40],"(MIMO)":[41],"scenarios,":[42],"where":[43],"parallel":[44,103],"task":[45],"execution":[46],"is":[47,137],"required.In":[48],"MISO":[49],"architectures,":[50],"tasks":[51,99],"compete":[52],"for":[53,131],"shared":[55],"output":[56],"channel,":[57],"creating":[58],"mutual":[59],"exclusion":[60],"effects":[61],"cause":[63],"unbalanced":[64],"optimization":[65],"degraded":[67],"performance.To":[68],"address":[69],"gap,":[71],"we":[72],"introduce":[73],"MIMO-VLA":[74,95,113],"(VLASCD),":[75],"unified":[77],"training":[78],"framework":[79],"enables":[81],"concurrent":[82],"multi-task":[83],"outputs,":[84],"exemplified":[85],"by":[86,92],"simultaneous":[87],"dialogue":[88],"generation":[89],"decision-making.Inspired":[91],"human":[93],"cognition,":[94],"eliminates":[96],"interference":[97],"between":[98],"supports":[101],"efficient":[102],"processing.Experiments":[104],"the":[106],"CARLA":[107],"autonomous":[108],"driving":[109],"platform":[110],"demonstrate":[111],"substantially":[114],"outperforms":[115],"stateof-the-art":[116],"MISO-based":[117],"LLMs,":[118],"reinforcement":[119],"learning":[120],"models,":[121],"MIMO":[125],"settings,":[126],"establishing":[127],"new":[129],"direction":[130],"multitask":[134],"learning.Our":[135],"code":[136],"available":[138],"at:":[139]},"counts_by_year":[],"updated_date":"2026-03-13T14:20:09.374765","created_date":"2025-11-08T00:00:00"}