{"id":"https://openalex.org/W7166822250","doi":"https://doi.org/10.18653/v1/2026.acl-long.191","title":"Controlling Multimodal Conversational Agents with Coverage-Enhanced Latent Actions","display_name":"Controlling Multimodal Conversational Agents with Coverage-Enhanced Latent Actions","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166822250","doi":"https://doi.org/10.18653/v1/2026.acl-long.191"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.191","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.191","pdf_url":"https://aclanthology.org/2026.acl-long.191.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.191.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139716602","display_name":"Yongqi Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongqi Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139746985","display_name":"Hao Lang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Lang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139827298","display_name":"Tieyun Qian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tieyun Qian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139818983","display_name":"Yongbin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongbin Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81168209,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4160","last_page":"4180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.6552000045776367,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.6552000045776367,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.07800000160932541,"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/T10028","display_name":"Topic Modeling","score":0.07240000367164612,"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":0.42239999771118164},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.28850001096725464},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.2572000026702881},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2418999969959259}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5536999702453613},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.42239999771118164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38580000400543213},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.2989000082015991},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27230000495910645},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27059999108314514},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.259799987077713},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2418999969959259}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.191","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.191","pdf_url":"https://aclanthology.org/2026.acl-long.191.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.191","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.191","pdf_url":"https://aclanthology.org/2026.acl-long.191.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1443569201","display_name":null,"funder_award_id":"62576256","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8830422215","display_name":null,"funder_award_id":"2042022dx0001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166822250.pdf","grobid_xml":"https://content.openalex.org/works/W7166822250.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-language":[0],"models":[1],"are":[2,82],"increasingly":[3],"employed":[4],"as":[5],"multimodal":[6],"conversational":[7,12],"agents":[8],"(MCAs)":[9],"for":[10,21,59,74,130],"diverse":[11],"tasks.Recently,":[13],"reinforcement":[14],"learning":[15,66,105],"(RL)":[16],"has":[17],"been":[18],"widely":[19],"explored":[20],"adapting":[22],"MCAs":[23,36],"to":[24,70,84,94,120,159],"various":[25,178],"human-AI":[26],"interaction":[27],"scenarios.Despite":[28],"showing":[29],"great":[30],"enhancement":[31],"in":[32,42],"generalization":[33],"performance,":[34],"fine-tuning":[35,61],"via":[37],"RL":[38,60,179],"still":[39],"faces":[40],"challenges":[41],"handling":[43],"the":[44,65,72,75,98,122,138],"extremely":[45],"large":[46],"text":[47,132],"token":[48],"space.To":[49],"address":[50],"this,":[51],"we":[52,63,111],"learn":[53],"a":[54,106,127,154],"compact":[55],"latent":[56,76,87,123,166],"action":[57,77,124,167],"space":[58],"instead.Specifically,":[62],"adopt":[64],"from":[67],"observation":[68],"mechanism":[69],"construct":[71,121],"codebook":[73,107],"space,":[78,125],"where":[79],"future":[80,96],"observations":[81],"leveraged":[83],"estimate":[85],"current":[86],"actions":[88],"that":[89,164],"could":[90],"further":[91,146],"be":[92],"used":[93],"reconstruct":[95],"observations.However,":[97],"scarcity":[99],"of":[100],"paired":[101,114,142],"image-text":[102,115,135,143],"data":[103,116,119,152],"hinders":[104],"with":[108,153],"sufficient":[109],"coverage.Thus,":[110],"leverage":[112],"both":[113],"and":[117,145,181],"text-only":[118,151],"using":[126],"cross-modal":[128,139],"projector":[129,140],"transforming":[131],"embeddings":[133],"into":[134],"embeddings.We":[136],"initialize":[137],"on":[141,149,173],"data,":[144],"train":[147],"it":[148],"massive":[150],"novel":[155],"cycle":[156],"consistency":[157],"loss":[158],"enhance":[160],"its":[161],"robustness.We":[162],"show":[163],"our":[165],"based":[168],"method":[169],"outperforms":[170],"competitive":[171],"baselines":[172],"two":[174],"conversation":[175],"tasks":[176],"across":[177],"algorithms.Code":[180]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}