{"id":"https://openalex.org/W7220929017","doi":"https://doi.org/10.1109/cvprf71909.2026.00798","title":"Video-R4: Reinforcing Text-Rich Video Reasoning with Visual Rumination","display_name":"Video-R4: Reinforcing Text-Rich Video Reasoning with Visual Rumination","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W7220929017","doi":"https://doi.org/10.1109/cvprf71909.2026.00798"},"language":"en","primary_location":{"id":"doi:10.1109/cvprf71909.2026.00798","doi":"https://doi.org/10.1109/cvprf71909.2026.00798","is_oa":true,"landing_page_url":"https://doi.org/10.1109/cvprf71909.2026.00798","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition- FINDINGS Track (CVPRF)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/cvprf71909.2026.00798","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5159272043","display_name":"Yolo Yunlong Tang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yolo Yunlong Tang","raw_affiliation_strings":["University of Rochester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067600053","display_name":"Daiki Shimada","orcid":"https://orcid.org/0009-0001-5840-0192","observed_orcids":["https://orcid.org/0009-0001-5840-0192"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daiki Shimada","raw_affiliation_strings":["Sony Group Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102027020","display_name":"Hang Hua","orcid":"https://orcid.org/0000-0002-5441-5776","observed_orcids":["https://orcid.org/0000-0002-5441-5776"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hang Hua","raw_affiliation_strings":["MIT-IBM Watson AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT-IBM Watson AI Lab","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159258159","display_name":"Chao Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Huang","raw_affiliation_strings":["University of Rochester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130213318","display_name":"Jing Bi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Bi","raw_affiliation_strings":["University of Rochester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111930150","display_name":"Rogerio S. Feris","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rogerio Feris","raw_affiliation_strings":["MIT-IBM Watson AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT-IBM Watson AI Lab","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5159269225","display_name":"Chenliang Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenliang Xu","raw_affiliation_strings":["University of Rochester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.73281168,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"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/T11605","display_name":"Visual Attention and Saliency Detection","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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","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"}}],"keywords":[{"id":"https://openalex.org/keywords/video-question-answering","display_name":"video question answering","score":0.7120000123977661},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.5720000267028809},{"id":"https://openalex.org/keywords/reinforcement-learning-from-human-feedback","display_name":"reinforcement learning from human feedback","score":0.7110000252723694},{"id":"https://openalex.org/keywords/group-relative-policy-optimization","display_name":"Group Relative Policy Optimization","score":0.5109999775886536},{"id":"https://openalex.org/keywords/hallucination-mitigation","display_name":"hallucination mitigation","score":0.5550000071525574}],"concepts":[{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.6105999946594238},{"id":"https://openalex.org/C2776060345","wikidata":"https://www.wikidata.org/wiki/Q1411912","display_name":"Rumination","level":3,"score":0.5471000075340271},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.5069000124931335},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.32820001244544983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31220000982284546},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C138496976","wikidata":"https://www.wikidata.org/wiki/Q175002","display_name":"Developmental psychology","level":1,"score":0.2870999872684479},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.2728999853134155},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2639000117778778}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvprf71909.2026.00798","doi":"https://doi.org/10.1109/cvprf71909.2026.00798","is_oa":true,"landing_page_url":"https://doi.org/10.1109/cvprf71909.2026.00798","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition- FINDINGS Track (CVPRF)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1109/cvprf71909.2026.00798","doi":"https://doi.org/10.1109/cvprf71909.2026.00798","is_oa":true,"landing_page_url":"https://doi.org/10.1109/cvprf71909.2026.00798","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition- FINDINGS Track (CVPRF)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2781922022","https://openalex.org/W2889787757","https://openalex.org/W2947555604","https://openalex.org/W2963748441","https://openalex.org/W2997759614","https://openalex.org/W3034336960","https://openalex.org/W3039017601","https://openalex.org/W3107583115","https://openalex.org/W3173585224","https://openalex.org/W3182778088","https://openalex.org/W4304013646","https://openalex.org/W4319300063","https://openalex.org/W4382202558","https://openalex.org/W4385237494","https://openalex.org/W4385990855","https://openalex.org/W4386076661","https://openalex.org/W4386453561","https://openalex.org/W4389140516","https://openalex.org/W4402727142","https://openalex.org/W4403792164","https://openalex.org/W4404724811","https://openalex.org/W4404784276","https://openalex.org/W4405595839","https://openalex.org/W4409366302","https://openalex.org/W4410027467","https://openalex.org/W4413144375","https://openalex.org/W4413146171","https://openalex.org/W4413146322","https://openalex.org/W4413146669","https://openalex.org/W4413147769","https://openalex.org/W4414876400","https://openalex.org/W4415063999","https://openalex.org/W4415085924","https://openalex.org/W4415314070","https://openalex.org/W4415540532","https://openalex.org/W4416031380","https://openalex.org/W4417286533","https://openalex.org/W7108068597","https://openalex.org/W7133193597","https://openalex.org/W7133208734","https://openalex.org/W7133224126","https://openalex.org/W7196930822","https://openalex.org/W7196975992"],"related_works":["https://openalex.org/W7221012937","https://openalex.org/W7171043684","https://openalex.org/W7196924254","https://openalex.org/W7213278759","https://openalex.org/W7196993360","https://openalex.org/W7220909664","https://openalex.org/W7214126110","https://openalex.org/W4389523843","https://openalex.org/W7221008575","https://openalex.org/W4411119701"],"abstract_inverted_index":{"Understanding":[0],"text-rich":[1],"videos":[2],"requires":[3],"reading":[4],"small,":[5],"transient":[6],"textual":[7],"cues":[8],"that":[9,58,101,139],"often":[10],"demand":[11],"repeated":[12],"inspection.":[13],"Yet":[14],"most":[15],"video":[16,55,136],"QA":[17],"models":[18],"rely":[19],"on":[20,31,123],"single-pass":[21],"perception":[22],"over":[23],"fixed":[24],"frames,":[25,64],"leading":[26],"to":[27,107,128],"hallucinations":[28],"and":[29,40,72,89,110,116,125,134],"failures":[30],"finegrained":[32],"evidence.":[33],"Inspired":[34],"by":[35],"how":[36],"humans":[37],"pause,":[38],"zoom,":[39],"re-read":[41],"critical":[42],"regions,":[43,68],"we":[44],"introduce":[45],"Video-R4":[46],"(Reinforcing":[47],"Text-Rich":[48],"Video":[49],"Reasoning":[50],"with":[51,81],"Visual":[52],"Rumination),":[53],"a":[54,96,104],"reasoning":[56,75],"agent":[57],"performs":[59],"visual":[60,112],"rumination:":[61],"iteratively":[62],"selecting":[63],"zooming":[65],"into":[66],"informative":[67],"re-encoding":[69],"retrieved":[70],"pixels,":[71],"updating":[73],"its":[74],"state.":[76],"We":[77,94],"construct":[78],"two":[79],"datasets":[80],"executable":[82],"rumination":[83,98,141],"trajectories:":[84],"Video-R4-CoT-17k":[85],"for":[86,91,146],"supervised":[87],"practice":[88],"Video-R4-RL-30k":[90],"reinforcement":[92],"learning.":[93],"propose":[95],"multi-stage":[97],"learning":[99],"framework":[100],"progressively":[102],"finetunes":[103],"7B":[105],"LMM":[106],"learn":[108],"atomic":[109],"mixing":[111],"operations":[113],"via":[114],"SFT":[115],"GRPO-based":[117],"RL.":[118],"Video-R4-7B":[119],"achieves":[120],"state-of-the-art":[121],"results":[122],"M4-ViteVQA":[124],"further":[126],"generalizes":[127],"multi-page":[129],"document$Q":[130],"A$,":[131,133],"slides$Q":[132],"generic":[135],"QA,":[137],"demonstrating":[138],"iterative":[140],"is":[142],"an":[143],"effective":[144],"paradigm":[145],"pixel-grounded":[147],"multimodal":[148],"reasoning.":[149]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-09T00:00:00"}