{"id":"https://openalex.org/W7166799373","doi":"https://doi.org/10.18653/v1/2026.findings-acl.2101","title":"PolyAudio: Advancing Multi-Audio Reasoning in Large Audio Language Models with Interleaved Multi-Audio Contexts","display_name":"PolyAudio: Advancing Multi-Audio Reasoning in Large Audio Language Models with Interleaved Multi-Audio Contexts","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166799373","doi":"https://doi.org/10.18653/v1/2026.findings-acl.2101"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.2101","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.2101","pdf_url":"https://aclanthology.org/2026.findings-acl.2101.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.2101.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139778603","display_name":"Sonal Kumar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sonal Kumar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139784465","display_name":"Sreyan Ghosh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sreyan Ghosh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100768194","display_name":"Yueqian Lin","orcid":"https://orcid.org/0000-0003-1473-8981"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yueqian Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139759561","display_name":"S Sakshi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S Sakshi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139748485","display_name":"Ashish Seth","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ashish Seth","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139760804","display_name":"Yiran Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiran Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013222310","display_name":"Ramani Duraiswami","orcid":"https://orcid.org/0000-0002-5596-8460"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramani Duraiswami","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139751556","display_name":"Dinesh Manocha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dinesh Manocha","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":0.8518756,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"42335","last_page":"42353"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.4122999906539917,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.4122999906539917,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.1436000019311905,"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/T10860","display_name":"Speech and Audio Processing","score":0.10660000145435333,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/natural-language","display_name":"Natural language","score":0.3100000023841858},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.30869999527931213},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.29510000348091125},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.2808000147342682},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2766000032424927}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6783000230789185},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4521999955177307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4025000035762787},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.33820000290870667},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2754000127315521},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.25679999589920044},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.2101","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.2101","pdf_url":"https://aclanthology.org/2026.findings-acl.2101.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.2101","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.2101","pdf_url":"https://aclanthology.org/2026.findings-acl.2101.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5311858654022217}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166799373.pdf","grobid_xml":"https://content.openalex.org/works/W7166799373.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Audio":[1,47],"Language":[2],"Models":[3],"have":[4],"demonstrated":[5],"impressive":[6],"performance":[7,117],"on":[8,46,104,118],"single-clip":[9,140],"audio":[10,38,135,156],"understanding":[11,53,81],"tasks,":[12],"including":[13],"automatic":[14],"speech":[15],"recognition,":[16,20],"captioning,":[17],"sound":[18],"event":[19],"etc.However,":[21],"their":[22],"ability":[23],"to":[24,78,92,129,133],"reason":[25],"over":[26,74,131],"interleaved":[27,87],"audio-language":[28],"contexts-where":[29],"answering":[30],"a":[31,64,105],"query":[32],"requires":[33],"relating":[34],"information":[35],"across":[36],"multiple":[37],"clipsremains":[39],"limited.We":[40],"present":[41],"PolyAudio,":[42,59],"an":[43,85],"LALM":[44],"built":[45],"Flamingo":[48],"3":[49],"that":[50,124,145],"targets":[51],"multi-audio":[52,80,109,119,148],"via":[54],"post-training":[55],"instruction":[56,149],"tuning.To":[57],"train":[58],"we":[60],"also":[61,126],"propose":[62],"PolyAudio-Instruct,":[63],"high-quality":[65],"instruction-tuning":[66],"dataset":[67],"consisting":[68],"of":[69,108],"1.3M+":[70],"QA":[71],"pairs,":[72],"spanning":[73],"14":[75],"diverse":[76,106],"tasks":[77],"learn":[79],"and":[82,96],"reasoning.PolyAudio":[83],"uses":[84],"explicit":[86],"representation":[88],"with":[89],"clip":[90],"indexing":[91],"encourage":[93],"faithful":[94],"grounding":[95],"reduce":[97],"ambiguity":[98],"in":[99],"multi-clip":[100],"references.We":[101],"evaluate":[102],"PolyAudio":[103],"suite":[107],"benchmarks":[110],"alongside":[111],"standard":[112],"single-audio":[113],"tasks.PolyAudio":[114],"achieves":[115],"strong":[116],"reasoning,":[120],"outperforming":[121],"competitive":[122],"baselines":[123],"are":[125],"often":[127],"limited":[128],"reasoning":[130,157],"up":[132],"2":[134],"clips,":[136],"while":[137],"preserving":[138],"robust":[139],"performance.Overall,":[141],"our":[142],"results":[143],"suggest":[144],"precise,":[146],"academicscale":[147],"tuning":[150],"can":[151],"unlock":[152],"advanced":[153],"multi-and":[154],"cross-clip":[155],"capabilities,":[158],"enabling":[159],"more":[160],"capable":[161],"audiocentric":[162],"assistants.":[163]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}