{"id":"https://openalex.org/W4414790544","doi":"https://doi.org/10.48550/arxiv.2509.21100","title":"VideoChat-R1.5: Visual Test-Time Scaling to Reinforce Multimodal Reasoning by Iterative Perception","display_name":"VideoChat-R1.5: Visual Test-Time Scaling to Reinforce Multimodal Reasoning by Iterative Perception","publication_year":2025,"publication_date":"2025-09-25","ids":{"openalex":"https://openalex.org/W4414790544","doi":"https://doi.org/10.48550/arxiv.2509.21100"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2509.21100","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.21100","pdf_url":"https://arxiv.org/pdf/2509.21100","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.21100","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002572395","display_name":"Ziang Yan","orcid":"https://orcid.org/0000-0003-1941-3537"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yan, Ziang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100611718","display_name":"Xinhao Li","orcid":"https://orcid.org/0000-0003-4566-5121"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xinhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100555075","display_name":"Yinan He","orcid":"https://orcid.org/0000-0002-6200-9938"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Yinan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107916129","display_name":"Zhengrong Yue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue, Zhengrong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101695670","display_name":"Xiangyu Zeng","orcid":"https://orcid.org/0009-0008-6890-4619"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Xiangyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100335705","display_name":"Yali Wang","orcid":"https://orcid.org/0000-0002-2999-7428"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yali","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101732858","display_name":"Yu Qiao","orcid":"https://orcid.org/0000-0003-0962-826X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao, Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100781160","display_name":"Limin Wang","orcid":"https://orcid.org/0000-0002-0472-3383"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Limin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100398357","display_name":"Zhichao Wang","orcid":"https://orcid.org/0000-0001-6662-835X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yi","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5002572395"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.9739999771118164,"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":0.9739999771118164,"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/perception","display_name":"Perception","score":0.6991000175476074},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5875999927520752},{"id":"https://openalex.org/keywords/iterative-refinement","display_name":"Iterative refinement","score":0.535099983215332},{"id":"https://openalex.org/keywords/iterative-and-incremental-development","display_name":"Iterative and incremental development","score":0.5300999879837036},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.4763999879360199},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.4413999915122986},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4269999861717224},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4072999954223633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7024000287055969},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6991000175476074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6144999861717224},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5875999927520752},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.535099983215332},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.5300999879837036},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49480000138282776},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4763999879360199},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.4413999915122986},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4269999861717224},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4072999954223633},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3889999985694885},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.38679999113082886},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.35109999775886536},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.3391000032424927},{"id":"https://openalex.org/C22033958","wikidata":"https://www.wikidata.org/wiki/Q7167036","display_name":"Perceptual learning","level":3,"score":0.2842999994754791},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2761000096797943},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25850000977516174}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2509.21100","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.21100","pdf_url":"https://arxiv.org/pdf/2509.21100","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2509.21100","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.21100","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.21100","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.21100","pdf_url":"https://arxiv.org/pdf/2509.21100","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":{"Inducing":[0],"reasoning":[1,21,45],"in":[2],"multimodal":[3],"large":[4],"language":[5],"models":[6],"(MLLMs)":[7],"is":[8],"critical":[9],"for":[10,97],"achieving":[11],"human-level":[12],"perception":[13,30,48],"and":[14,119,124,149,162],"understanding.":[15],"Existing":[16],"methods":[17],"mainly":[18],"leverage":[19],"LLM":[20],"to":[22,42,83,105,143],"analyze":[23],"parsed":[24],"visuals,":[25],"often":[26],"limited":[27],"by":[28,56,65,109],"static":[29],"stages.":[31],"This":[32],"paper":[33],"introduces":[34],"Visual":[35],"Test-Time":[36],"Scaling":[37],"(VTTS),":[38],"a":[39,94,103],"novel":[40],"approach":[41],"enhance":[43,106],"MLLMs'":[44],"via":[46],"iterative":[47,98],"during":[49],"inference.":[50],"VTTS":[51,70],"mimics":[52],"humans'":[53],"hierarchical":[54],"attention":[55],"progressively":[57],"refining":[58],"focus":[59],"on":[60],"high-confidence":[61],"spatio-temporal":[62,81,163],"regions,":[63],"guided":[64],"updated":[66],"textual":[67],"predictions.":[68],"Specifically,":[69],"employs":[71],"an":[72,136],"Iterative":[73],"Perception":[74],"(ITP)":[75],"mechanism,":[76],"incorporating":[77],"reinforcement":[78],"learning":[79],"with":[80,135],"supervision":[82],"optimize":[84],"reasoning.":[85],"To":[86],"support":[87],"this":[88],"paradigm,":[89],"we":[90],"also":[91],"present":[92],"VTTS-80K,":[93],"dataset":[95],"tailored":[96],"perception.":[99,164],"These":[100],"designs":[101],"allows":[102],"MLLM":[104],"its":[107,111],"performance":[108],"increasing":[110],"perceptual":[112],"compute.":[113],"Extensive":[114],"experiments":[115],"validate":[116],"VTTS's":[117],"effectiveness":[118],"generalization":[120],"across":[121,151],"diverse":[122],"tasks":[123],"benchmarks.":[125],"Our":[126],"newly":[127],"introduced":[128],"Videochat-R1.5":[129],"model":[130],"has":[131],"achieved":[132],"remarkable":[133],"improvements,":[134],"average":[137],"increase":[138],"of":[139],"over":[140],"5\\%,":[141],"compared":[142],"robust":[144],"baselines":[145],"such":[146],"as":[147],"Qwen2.5VL-3B":[148],"-7B,":[150],"more":[152],"than":[153],"15":[154],"benchmarks":[155],"that":[156],"encompass":[157],"video":[158,160],"conversation,":[159],"reasoning,":[161]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}
