{"id":"https://openalex.org/W7213675649","doi":null,"title":"AVTrace: Diagnosing Audio-Visual Temporal Reasoning in Omni Models","display_name":"AVTrace: Diagnosing Audio-Visual Temporal Reasoning in Omni Models","publication_year":2026,"publication_date":"2026-09-17","ids":{"openalex":"https://openalex.org/W7213675649"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.19991","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.19991","pdf_url":"https://arxiv.org/pdf/2609.19991","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.19991","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5152195289","display_name":"Longyin Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I4405277092","display_name":"Institute of Advanced Intelligence and Computing","ror":"https://ror.org/01eczt548","country_code":"SG","type":"facility","lineage":["https://openalex.org/I4405277092"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhang, Longyin","raw_affiliation_strings":["Institute of Advanced Intelligence and Computing (IAIC) , A *STAR , Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Advanced Intelligence and Computing (IAIC) , A *STAR , Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I4405277092"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152232038","display_name":"Parth Sakhare Mahendra","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I4405277092","display_name":"Institute of Advanced Intelligence and Computing","ror":"https://ror.org/01eczt548","country_code":"SG","type":"facility","lineage":["https://openalex.org/I4405277092"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mahendra, Parth Sakhare","raw_affiliation_strings":["Institute of Advanced Intelligence and Computing (IAIC) , A *STAR , Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Advanced Intelligence and Computing (IAIC) , A *STAR , Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I4405277092"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152197161","display_name":"Chengwei Wei","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I4405277092","display_name":"Institute of Advanced Intelligence and Computing","ror":"https://ror.org/01eczt548","country_code":"SG","type":"facility","lineage":["https://openalex.org/I4405277092"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wei, Chengwei","raw_affiliation_strings":["Centre for Frontier AI Research (CFAR) , A","Institute of Advanced Intelligence and Computing (IAIC) , A *STAR , Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Frontier AI Research (CFAR) , A","institution_ids":[]},{"raw_affiliation_string":"Institute of Advanced Intelligence and Computing (IAIC) , A *STAR , Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I4405277092"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152240102","display_name":"Ning Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I4405277092","display_name":"Institute of Advanced Intelligence and Computing","ror":"https://ror.org/01eczt548","country_code":"SG","type":"facility","lineage":["https://openalex.org/I4405277092"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhang, Ning","raw_affiliation_strings":["Institute of Advanced Intelligence and Computing (IAIC) , A *STAR , Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Advanced Intelligence and Computing (IAIC) , A *STAR , Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I4405277092"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044029733","display_name":"Lim Ming Chong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chong, Lim Ming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114171859","display_name":"Sirui He","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I4405277092","display_name":"Institute of Advanced Intelligence and Computing","ror":"https://ror.org/01eczt548","country_code":"SG","type":"facility","lineage":["https://openalex.org/I4405277092"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"He, Sirui","raw_affiliation_strings":["Institute of Advanced Intelligence and Computing (IAIC) , A *STAR , Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Advanced Intelligence and Computing (IAIC) , A *STAR , Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I4405277092"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109309570","display_name":"Ai Ti Aw","orcid":"https://orcid.org/0000-0002-2347-0879","observed_orcids":["https://orcid.org/0000-0002-2347-0879"]},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I4405277092","display_name":"Institute of Advanced Intelligence and Computing","ror":"https://ror.org/01eczt548","country_code":"SG","type":"facility","lineage":["https://openalex.org/I4405277092"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Aw, Ai Ti","raw_affiliation_strings":["Institute of Advanced Intelligence and Computing (IAIC) , A *STAR , Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Advanced Intelligence and Computing (IAIC) , A *STAR , Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I4405277092"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T12720","display_name":"Multimedia Communication and Technology","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.0,"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/temporal-grounding","display_name":"temporal grounding","score":0.6959999799728394},{"id":"https://openalex.org/keywords/audio-visual-synchronization","display_name":"audio-video synchronization","score":0.9150000214576721},{"id":"https://openalex.org/keywords/one-step-ahead-forecasting","display_name":"one-step-ahead prediction","score":0.7210000157356262},{"id":"https://openalex.org/keywords/temporal-localization","display_name":"temporal localization","score":0.35899999737739563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7752000093460083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6455000042915344},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.6134999990463257},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4401000142097473},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.43560001254081726},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.37790000438690186},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.37400001287460327},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.3711000084877014},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3637000024318695},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.35659998655319214},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.30160000920295715},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C80519477","wikidata":"https://www.wikidata.org/wiki/Q3532236","display_name":"Scenario testing","level":3,"score":0.2971999943256378},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29010000824928284},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2621999979019165},{"id":"https://openalex.org/C119666444","wikidata":"https://www.wikidata.org/wiki/Q5977280","display_name":"Temporal resolution","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2524999976158142},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:arXiv.org:2609.19991","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.19991","pdf_url":"https://arxiv.org/pdf/2609.19991","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.19991","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.19991","pdf_url":"https://arxiv.org/pdf/2609.19991","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213675649.pdf","grobid_xml":"https://content.openalex.org/works/W7213675649.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4417292606","https://openalex.org/W7223025785","https://openalex.org/W7214770017","https://openalex.org/W7215776564","https://openalex.org/W7160857276","https://openalex.org/W7223110555","https://openalex.org/W4403577568","https://openalex.org/W7154624702","https://openalex.org/W7223057995","https://openalex.org/W7170095331"],"abstract_inverted_index":{"Omni":[0],"models":[1,70],"can":[2,7,179],"describe":[3],"video":[4],"content,":[5],"but":[6],"they":[8],"locate":[9],"events":[10],"in":[11,117,124],"time,":[12],"preserve":[13],"event":[14],"order,":[15],"and":[16,27,36,46,54,57,62,100,107,110,122,176],"judge":[17],"audio-visual":[18],"synchronization?":[19],"We":[20,65],"introduce":[21],"AVTrace":[22,178],"(Audio-Visual":[23],"Temporal":[24],"Reasoning":[25],"Assessment":[26],"Capability":[28],"Evaluation),":[29],"a":[30,171,185],"silver-standard":[31],"diagnostic":[32],"suite":[33],"spanning":[34],"onset":[35],"span":[37],"grounding,":[38],"synchronization,":[39],"next-step":[40],"prediction,":[41],"cross-modal":[42],"localization,":[43,175],"chain":[44,105],"parsing,":[45],"event-conditioned":[47,108],"comprehension.":[48,111],"It":[49],"contains":[50],"34,114":[51],"training":[52],"examples":[53],"category-balanced":[55],"development":[56],"test":[58,91],"splits":[59],"of":[60,95],"3,500":[61],"7,000":[63],"examples.":[64],"evaluate":[66],"five":[67,85],"open":[68],"omni":[69],"under":[71],"their":[72,130],"respective":[73],"input":[74,126],"configurations":[75],"using":[76],"reference-blind":[77],"response":[78],"normalization":[79],"followed":[80],"by":[81],"deterministic":[82],"scoring.":[83],"All":[84],"off-the-shelf":[86],"systems":[87],"score":[88],"below":[89],"the":[90],"split's":[92],"majority-label":[93],"baseline":[94],"0.556":[96],"on":[97,104,138],"synchronization":[98],"verification,":[99],"obtain":[101],"low":[102],"scores":[103],"parsing":[106],"grounding":[109],"Development-set":[112],"perturbations":[113],"reveal":[114],"task-dependent":[115],"sensitivity":[116],"Qwen3-Omni-30B":[118],"to":[119],"modality":[120],"removal":[121],"changes":[123],"visual":[125],"processing,":[127],"without":[128],"isolating":[129],"underlying":[131],"causes.":[132],"Parameter-efficient":[133],"temporal":[134,174,188],"post-training":[135],"improves":[136],"Gemma4-E4B-it":[137],"several":[139],"benchmark":[140],"metrics.":[141],"On":[142],"three":[143],"external":[144],"image":[145],"benchmarks,":[146],"task":[147],"metrics":[148],"change":[149],"modestly,":[150],"including":[151],"some":[152],"degradations,":[153],"while":[154,183],"teacher-forcing":[155],"perplexity":[156],"decreases.":[157],"Together,":[158],"these":[159],"findings":[160],"show":[161],"that":[162,177],"semantic":[163],"reference-text":[164],"overlap":[165],"should":[166],"not":[167],"be":[168],"treated":[169],"as":[170],"proxy":[172],"for":[173,187],"identify":[180],"task-specific":[181],"weaknesses":[182],"providing":[184],"testbed":[186],"post-training.":[189]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-20T00:00:00"}
