{"id":"https://openalex.org/W7127988094","doi":"https://doi.org/10.48550/arxiv.2602.05847","title":"OmniVideo-R1: Reinforcing Audio-visual Reasoning with Query Intention and Modality Attention","display_name":"OmniVideo-R1: Reinforcing Audio-visual Reasoning with Query Intention and Modality Attention","publication_year":2026,"publication_date":"2026-02-05","ids":{"openalex":"https://openalex.org/W7127988094","doi":"https://doi.org/10.48550/arxiv.2602.05847"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2602.05847","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.05847","pdf_url":"https://arxiv.org/pdf/2602.05847","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","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2602.05847","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109781353","display_name":"Zhangquan Chen","orcid":"https://orcid.org/0009-0006-2370-6120","observed_orcids":["https://orcid.org/0009-0006-2370-6120"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Zhangquan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082294247","display_name":"Jiale Tao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao, Jiale","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032651874","display_name":"Ruihuang Li","orcid":"https://orcid.org/0000-0001-8400-8947","observed_orcids":["https://orcid.org/0000-0001-8400-8947"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Ruihuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124922326","display_name":"Yihao Hu","orcid":"https://orcid.org/0009-0009-2566-1511","observed_orcids":["https://orcid.org/0009-0009-2566-1511"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Yihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125121435","display_name":"Ruitao Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Ruitao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125131926","display_name":"Zhantao Yang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Zhantao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074270978","display_name":"Xinlei Yu","orcid":"https://orcid.org/0000-0003-3404-5373","observed_orcids":["https://orcid.org/0000-0003-3404-5373","https://orcid.org/0000-0003-2620-8080"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Xinlei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000087835","display_name":"Haodong Jing","orcid":"https://orcid.org/0000-0001-6643-7588","observed_orcids":["https://orcid.org/0000-0001-6643-7588"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing, Haodong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012273415","display_name":"Manyuan Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Manyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144448633","display_name":"Shuai Shao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shao, Shuai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125129210","display_name":"Biao Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Biao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121228442","display_name":"Qinglin Lu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Qinglin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5086379651","display_name":"Ruqi Huang","orcid":"https://orcid.org/0000-0001-5942-3671","observed_orcids":["https://orcid.org/0000-0001-5942-3671"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Ruqi","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":null,"has_fulltext":false,"cited_by_count":1,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.0,"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/T12032","display_name":"Multisensory perception and integration","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/multimodal-grounding","display_name":"multimodal grounding","score":0.6439999938011169},{"id":"https://openalex.org/keywords/self-supervised-learning","display_name":"self-supervised learning","score":0.8289999961853027},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":1.0},{"id":"https://openalex.org/keywords/video-understanding","display_name":"video understanding","score":0.41999998688697815}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6880999803543091},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6845999956130981},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6032000184059143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5856999754905701},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5602999925613403},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5203999876976013},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.41909998655319214},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3443000018596649},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31139999628067017},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28519999980926514},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.265500009059906},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.26019999384880066},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.25859999656677246},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2583000063896179},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.05847","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.05847","pdf_url":"https://arxiv.org/pdf/2602.05847","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"},{"id":"doi:10.48550/arxiv.2602.05847","doi":"https://doi.org/10.48550/arxiv.2602.05847","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.05847","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,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2602.05847","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.05847","pdf_url":"https://arxiv.org/pdf/2602.05847","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7215096293","https://openalex.org/W4414588426","https://openalex.org/W7153055982","https://openalex.org/W7090995503","https://openalex.org/W7162072772","https://openalex.org/W7221765327","https://openalex.org/W7162634153","https://openalex.org/W4416497886","https://openalex.org/W7168252378","https://openalex.org/W7156896781"],"abstract_inverted_index":{"While":[0],"humans":[1],"perceive":[2],"the":[3],"world":[4],"through":[5],"diverse":[6],"modalities":[7],"that":[8,40,79],"operate":[9],"synergistically":[10],"to":[11,47],"support":[12],"a":[13,36],"holistic":[14],"understanding":[15,28],"of":[16],"their":[17],"surroundings,":[18],"existing":[19],"omnivideo":[20],"models":[21,46],"still":[22],"face":[23],"substantial":[24],"challenges":[25],"on":[26,60,75],"audio-visual":[27],"tasks.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33],"propose":[34],"OmniVideo-R1,":[35],"novel":[37],"reinforced":[38],"framework":[39],"improves":[41],"mixed-modality":[42],"reasoning.":[43],"OmniVideo-R1":[44,80],"empowers":[45],"\"think":[48],"with":[49],"omnimodal":[50],"cues\"":[51],"by":[52],"two":[53],"key":[54],"strategies:":[55],"(1)":[56],"query-intensive":[57],"grounding":[58],"based":[59],"self-supervised":[61],"learning":[62,71],"paradigms;":[63],"and":[64,88],"(2)":[65],"modality-attentive":[66],"fusion":[67],"built":[68],"upon":[69],"contrastive":[70],"paradigms.":[72],"Extensive":[73],"experiments":[74],"multiple":[76],"benchmarks":[77],"demonstrate":[78],"consistently":[81],"outperforms":[82],"strong":[83],"baselines,":[84],"highlighting":[85],"its":[86],"effectiveness":[87],"robust":[89],"generalization":[90],"capabilities.":[91]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-07T00:00:00"}
