{"id":"https://openalex.org/W4416322399","doi":"https://doi.org/10.48550/arxiv.2511.11113","title":"VIDEOP2R: Video Understanding from Perception to Reasoning","display_name":"VIDEOP2R: Video Understanding from Perception to Reasoning","publication_year":2025,"publication_date":"2025-11-14","ids":{"openalex":"https://openalex.org/W4416322399","doi":"https://doi.org/10.48550/arxiv.2511.11113"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2511.11113","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2511.11113","pdf_url":"https://arxiv.org/pdf/2511.11113","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":"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/2511.11113","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019429747","display_name":"Yifan Jiang","orcid":"https://orcid.org/0000-0002-4084-9194"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jiang, Yifan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100661706","display_name":"Yueying Wang","orcid":"https://orcid.org/0000-0003-1219-5987"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yueying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101608539","display_name":"Rui Zhao","orcid":"https://orcid.org/0000-0003-2915-9333"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Rui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062468877","display_name":"Toufiq Parag","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Parag, Toufiq","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100382189","display_name":"Zhimin Chen","orcid":"https://orcid.org/0000-0002-1017-7171"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Zhimin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120553097","display_name":"Zhenyu Liao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liao, Zhenyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5039592314","display_name":"Jayakrishnan Unnikrishnan","orcid":"https://orcid.org/0000-0002-8464-4641"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Unnikrishnan, Jayakrishnan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5019429747"],"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":0.8741000294685364,"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":0.8741000294685364,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.02019999921321869,"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"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.011300000362098217,"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/perception","display_name":"Perception","score":0.7160999774932861},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6121000051498413},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5814999938011169},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.31369999051094055},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.289000004529953}],"concepts":[{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.7160999774932861},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7006999850273132},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6121000051498413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5823000073432922},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5814999938011169},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3693000078201294},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28780001401901245},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.25529998540878296}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2511.11113","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2511.11113","pdf_url":"https://arxiv.org/pdf/2511.11113","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.11113","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.11113","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:2511.11113","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2511.11113","pdf_url":"https://arxiv.org/pdf/2511.11113","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"fine-tuning":[1,9],"(RFT),":[2],"a":[3,42,66,72,88],"two-stage":[4],"framework":[5,47],"consisting":[6],"of":[7,23,117,130],"supervised":[8],"(SFT)":[10],"and":[11,55,80,103,121,134,136],"reinforcement":[12],"learning":[13],"(RL)":[14],"has":[15],"shown":[16],"promising":[17],"results":[18],"on":[19,114],"improving":[20],"reasoning":[21,51,56,120],"ability":[22],"large":[24,32],"language":[25,34],"models":[26,35],"(LLMs).":[27],"Yet":[28],"extending":[29],"RFT":[30,46],"to":[31,69],"video":[33,45,50,119],"(LVLMs)":[36],"remains":[37],"challenging.":[38],"We":[39],"propose":[40],"VideoP2R,":[41],"novel":[43,89],"process-aware":[44,74,90,132],"that":[48,97,108,138],"enhances":[49],"by":[52],"modeling":[53,133],"perception":[54,79,102,140],"as":[57],"distinct":[58],"processes.":[59],"In":[60,82],"the":[61,83,128],"SFT":[62],"stage,":[63,85],"we":[64,86],"develop":[65],"three-step":[67],"pipeline":[68],"generate":[70],"VideoP2R-CoT-162K,":[71],"high-quality,":[73],"chain-of-thought":[75],"(CoT)":[76],"dataset":[77],"for":[78,101,144],"reasoning.":[81,104,146],"RL":[84],"introduce":[87],"group":[91],"relative":[92],"policy":[93],"optimization":[94],"(PA-GRPO)":[95],"algorithm":[96],"supplies":[98],"separate":[99],"rewards":[100],"Extensive":[105],"experiments":[106],"show":[107],"VideoP2R":[109],"achieves":[110],"state-of-the-art":[111],"(SotA)":[112],"performance":[113],"six":[115],"out":[116],"seven":[118],"understanding":[122],"benchmarks.":[123],"Ablation":[124],"studies":[125],"further":[126],"confirm":[127],"effectiveness":[129],"our":[131],"PA-GRPO":[135],"demonstrate":[137],"model's":[139],"output":[141],"is":[142,150],"information-sufficient":[143],"downstream":[145],"Our":[147],"project":[148],"page":[149],"available":[151],"at":[152],"https://videop2r.github.io/videop2r/.":[153]},"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-11-18T00:00:00"}