{"id":"https://openalex.org/W7160822422","doi":"https://doi.org/10.48550/arxiv.2605.07872","title":"Video Understanding Reward Modeling: A Robust Benchmark and Performant Reward Models","display_name":"Video Understanding Reward Modeling: A Robust Benchmark and Performant Reward Models","publication_year":2026,"publication_date":"2026-05-08","ids":{"openalex":"https://openalex.org/W7160822422","doi":"https://doi.org/10.48550/arxiv.2605.07872"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.07872","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07872","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":"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.07872","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135906945","display_name":"Yuancheng Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Yuancheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135907320","display_name":"Linli Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Linli","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135850911","display_name":"Lei Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135895774","display_name":"Haojie Zhang","orcid":"https://orcid.org/0000-0002-0165-7472"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Haojie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135909260","display_name":"Hao Zhou","orcid":"https://orcid.org/0000-0002-7425-7621"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135861979","display_name":"Fandong Meng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Fandong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135842599","display_name":"Xu Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Xu","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":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":0.4074000120162964,"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":0.4074000120162964,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.2329999953508377,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.04820000007748604,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/benchmark","display_name":"Benchmark (surveying)","score":0.7942000031471252},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7315000295639038},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.5253000259399414},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5085999965667725},{"id":"https://openalex.org/keywords/preference-learning","display_name":"Preference learning","score":0.4133000075817108},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.41280001401901245}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7942000031471252},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7402999997138977},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7315000295639038},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6169000267982483},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6115999817848206},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.5253000259399414},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5085999965667725},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.4133000075817108},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.41280001401901245},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.35019999742507935},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.2736000120639801},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.257999986410141}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.07872","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07872","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.07872","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07872","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":"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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7014356851577759}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"reward":[1,16,46,100,116,133],"models":[2],"have":[3],"advanced":[4],"substantially":[5],"in":[6,13],"text":[7],"and":[8,28,45,70,77,109,113,124,135,141],"image":[9],"domains,":[10],"yet":[11],"progress":[12],"video":[14,79,99],"understanding":[15],"modeling":[17],"remains":[18],"severely":[19],"limited":[20],"by":[21],"the":[22,104],"lack":[23],"of":[24],"robust":[25],"evaluation":[26,73],"benchmarks":[27],"high-quality":[29,96],"preference":[30,60],"data.":[31],"To":[32],"address":[33],"this,":[34],"we":[35,106],"propose":[36],"a":[37,56,90,111,114],"unified":[38],"framework":[39],"spanning":[40],"benchmark":[41,57],"design,":[42],"data":[43],"construction,":[44],"model":[47,136],"training.":[48,101],"We":[49,81],"introduce":[50],"Video":[51,84],"Understanding":[52,85],"Reward":[53],"Bench":[54],"(VURB),":[55],"featuring":[58],"2,100":[59],"pairs":[61],"with":[62],"long":[63],"chain-of-thought":[64],"reasoning":[65,137],"traces":[66],"(averaging":[67],"1,143":[68],"tokens)":[69],"majority":[71],"voting":[72],"across":[74],"general,":[75],"long,":[76],"reasoning-oriented":[78],"tasks.":[80],"further":[82],"construct":[83],"Preference":[86],"Dataset":[87],"(VUP-35K)":[88],"via":[89],"fully":[91],"automated":[92],"pipeline,":[93],"providing":[94],"large-scale":[95],"supervision":[97],"for":[98],"Building":[102],"on":[103,122],"data,":[105],"train":[107],"VideoDRM":[108,140],"VideoGRM,":[110],"discriminative":[112],"generative":[115],"model,":[117],"both":[118,132],"achieving":[119],"state-of-the-art":[120],"performance":[121,134],"VURB":[123],"VideoRewardBench.":[125],"Further":[126],"analysis":[127],"confirms":[128],"that":[129],"VUP-35K":[130],"enhances":[131],"capability,":[138],"while":[139],"VideoGRM":[142],"yield":[143],"significant":[144],"gains":[145],"under":[146],"best-of-$N$":[147],"test-time":[148],"scaling.":[149]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-12T00:00:00"}