{"id":"https://openalex.org/W4417068938","doi":"https://doi.org/10.1109/iccv51701.2025.02126","title":"Aurelia: Test-Time Reasoning Distillation in Audio-Visual LLMs","display_name":"Aurelia: Test-Time Reasoning Distillation in Audio-Visual LLMs","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417068938","doi":"https://doi.org/10.1109/iccv51701.2025.02126"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02126","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.23219","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101778650","display_name":"Sanjoy Chowdhury","orcid":"https://orcid.org/0000-0003-4256-4720"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjoy Chowdhury","raw_affiliation_strings":["University of Maryland, College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043165192","display_name":"Hanan Gani","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Hanan Gani","raw_affiliation_strings":["MBZUAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MBZUAI","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076391965","display_name":"Nishit Anand","orcid":"https://orcid.org/0000-0001-9391-1871"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nishit Anand","raw_affiliation_strings":["University of Maryland, College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101977185","display_name":"Sayan Nag","orcid":"https://orcid.org/0000-0001-5652-125X"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sayan Nag","raw_affiliation_strings":["University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102907601","display_name":"Ruohan Gao","orcid":"https://orcid.org/0000-0002-8346-1114"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruohan Gao","raw_affiliation_strings":["University of Maryland, College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085089542","display_name":"Mohamed Elhoseiny","orcid":"https://orcid.org/0000-0001-9659-1551"},"institutions":[{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]},{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["CA","SA"],"is_corresponding":false,"raw_author_name":"Mohamed Elhoseiny","raw_affiliation_strings":["KAUST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAUST","institution_ids":["https://openalex.org/I4210099236","https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101483979","display_name":"Salman Khan","orcid":"https://orcid.org/0000-0002-2905-1755"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Salman Khan","raw_affiliation_strings":["MBZUAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MBZUAI","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004194238","display_name":"Dinesh Manocha","orcid":"https://orcid.org/0000-0001-7047-9801"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dinesh Manocha","raw_affiliation_strings":["University of Maryland, College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42597788,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22899","last_page":"22910"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9606999754905701,"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":0.9606999754905701,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.00419999985024333,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.003000000026077032,"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/benchmark","display_name":"Benchmark (surveying)","score":0.6717000007629395},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.517799973487854},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.4999000132083893},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.3894999921321869},{"id":"https://openalex.org/keywords/reasoning-system","display_name":"Reasoning system","score":0.3813999891281128},{"id":"https://openalex.org/keywords/deductive-reasoning","display_name":"Deductive reasoning","score":0.3693999946117401},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3490000069141388}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6717000007629395},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6298999786376953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5473999977111816},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.517799973487854},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.4999000132083893},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.454800009727478},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3894999921321869},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.3813999891281128},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3490000069141388},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.3028999865055084},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.25940001010894775}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02126","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.23219","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.23219","pdf_url":"https://arxiv.org/pdf/2503.23219","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.23219","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.23219","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.23219","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.23219","pdf_url":"https://arxiv.org/pdf/2503.23219","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,117,148],"reasoning":[3,44,50,73,102,120],"optimization":[4],"have":[5],"greatly":[6],"enhanced":[7],"the":[8,21,27,139],"performance":[9,136],"of":[10,23,141],"large":[11],"language":[12],"models":[13],"(LLMs).":[14],"However,":[15],"existing":[16],"work":[17],"fails":[18],"to":[19,59,127],"address":[20],"complexities":[22],"audio-visual":[24,42,83],"scenarios,":[25],"underscoring":[26],"need":[28],"for":[29,145],"further":[30,70],"research.":[31],"In":[32],"this":[33],"paper,":[34],"we":[35,75,124],"introduce":[36],"AURELIA,":[37,123],"a":[38,78,128],"novel":[39],"actor-critic":[40],"based":[41],"(AV)":[43],"framework":[45],"that":[46],"distills":[47],"structured,":[48],"step-by-step":[49,89],"into":[51],"AVLLMs":[52,111,147],"at":[53],"test":[54],"time,":[55],"improving":[56],"their":[57,118],"ability":[58],"process":[60],"complex":[61],"multi-modal":[62,119],"inputs":[63],"without":[64],"additional":[65],"training":[66],"or":[67],"fine-tuning.":[68],"To":[69],"advance":[71],"AVLLM":[72],"skills,":[74],"present":[76],"AVReasonBench,":[77],"challenging":[79],"benchmark":[80,92],"comprising":[81],"4500":[82],"questions,":[84],"each":[85],"paired":[86],"with":[87,104],"detailed":[88],"reasoning.":[90],"Our":[91,151],"spans":[93],"six":[94],"distinct":[95],"tasks,":[96],"including":[97],"AV-GeoIQ,":[98],"which":[99],"evaluates":[100],"AV":[101],"combined":[103],"geographical":[105],"and":[106,153],"cultural":[107],"knowledge.":[108],"Evaluating":[109],"18":[110],"on":[112],"AVReasonBench":[113],"reveals":[114],"significant":[115],"limitations":[116],"capabilities.":[121],"Using":[122],"achieve":[125],"up":[126],"100%":[129],"relative":[130],"improvement,":[131],"demonstrating":[132],"its":[133],"effectiveness.":[134],"This":[135],"gain":[137],"highlights":[138],"potential":[140],"reasoning-enhanced":[142],"data":[143,154],"generation":[144],"advancing":[146],"real-world":[149],"applications.":[150],"code":[152],"will":[155],"be":[156],"publicly":[157],"released":[158],"at:":[159],"https:":[160],"//github.com/schowdhury671/aurelia.":[161]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}