{"id":"https://openalex.org/W7153257554","doi":"https://doi.org/10.48550/arxiv.2604.08539","title":"OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual Tasks","display_name":"OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual Tasks","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W7153257554","doi":"https://doi.org/10.48550/arxiv.2604.08539"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.08539","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.08539","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.2604.08539","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133373846","display_name":"Wenbo Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Wenbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133347880","display_name":"Xin Chen","orcid":"https://orcid.org/0000-0001-9940-3720"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133377013","display_name":"Yan Gao-Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao-Tian, Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133337080","display_name":"Yihe Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng, Yihe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133336086","display_name":"Nanyun Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Nanyun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133326758","display_name":"Kai-Wei Chang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chang, Kai-Wei","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":0.6615999937057495,"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":0.6615999937057495,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.17810000479221344,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.03779999911785126,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.5521000027656555},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5228999853134155},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4650000035762787},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.4293000102043152},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.4156000018119812},{"id":"https://openalex.org/keywords/forcing","display_name":"Forcing (mathematics)","score":0.39340001344680786},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.3905999958515167},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3871999979019165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.705299973487854},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5521000027656555},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5228999853134155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5047000050544739},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4691999852657318},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4650000035762787},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.4293000102043152},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.4156000018119812},{"id":"https://openalex.org/C197115733","wikidata":"https://www.wikidata.org/wiki/Q1003136","display_name":"Forcing (mathematics)","level":2,"score":0.39340001344680786},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3905999958515167},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3871999979019165},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.37540000677108765},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3154999911785126},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29840001463890076},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.2655999958515167},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.2572000026702881}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.08539","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.08539","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.2604.08539","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.08539","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":[{"score":0.40660470724105835,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Group":[0],"Relative":[1],"Policy":[2],"Optimization":[3],"(GRPO)":[4],"has":[5],"emerged":[6],"as":[7],"the":[8,39,50,87,124,168],"de":[9],"facto":[10],"Reinforcement":[11],"Learning":[12],"(RL)":[13],"objective":[14,74],"driving":[15],"recent":[16],"advancements":[17],"in":[18,42],"Multimodal":[19],"Large":[20],"Language":[21],"Models.":[22],"However,":[23],"extending":[24],"this":[25],"success":[26],"to":[27,94,97,111,137,159],"open-source":[28,204],"multimodal":[29,190],"generalist":[30],"models":[31],"remains":[32],"heavily":[33],"constrained":[34],"by":[35,129],"two":[36,133],"primary":[37],"challenges:":[38],"extreme":[40],"variance":[41],"reward":[43],"topologies":[44],"across":[45,194],"diverse":[46,196],"visual":[47,161],"tasks,":[48],"and":[49,114,120,141,177,205],"inherent":[51],"difficulty":[52],"of":[53,90],"balancing":[54],"fine-grained":[55],"perception":[56,140],"with":[57,80],"multi-step":[58],"reasoning":[59,150],"capabilities.":[60],"To":[61],"address":[62],"these":[63,181],"issues,":[64],"we":[65,131,183],"introduce":[66,132],"Gaussian":[67],"GRPO":[68],"(G$^2$RPO),":[69],"a":[70,98,186],"novel":[71],"RL":[72],"training":[73,126],"that":[75],"replaces":[76],"standard":[77,99],"linear":[78],"scaling":[79],"non-linear":[81],"distributional":[82],"matching.":[83],"By":[84],"mathematically":[85],"forcing":[86],"advantage":[88],"distribution":[89],"any":[91],"given":[92],"task":[93],"strictly":[95],"converge":[96],"normal":[100],"distribution,":[101],"$\\mathcal{N}(0,1)$,":[102],"G$^2$RPO":[103],"theoretically":[104],"ensures":[105],"inter-task":[106],"gradient":[107],"equity,":[108],"mitigates":[109],"vulnerabilities":[110],"heavy-tail":[112],"outliers,":[113],"offers":[115],"symmetric":[116],"update":[117],"for":[118,152],"positive":[119],"negative":[121],"rewards.":[122],"Leveraging":[123],"enhanced":[125],"stability":[127],"provided":[128],"G$^2$RPO,":[130],"task-level":[134],"shaping":[135,146,165],"mechanisms":[136],"seamlessly":[138],"balance":[139],"reasoning.":[142],"First,":[143],"response":[144],"length":[145],"dynamically":[147],"elicits":[148],"extended":[149],"chains":[151],"complex":[153],"queries":[154],"while":[155],"enforce":[156],"direct":[157],"outputs":[158],"bolster":[160],"grounding.":[162],"Second,":[163],"entropy":[164,175,178],"tightly":[166],"bounds":[167],"model's":[169],"exploration":[170],"zone,":[171],"effectively":[172],"preventing":[173],"both":[174],"collapse":[176],"explosion.":[179],"Integrating":[180],"methodologies,":[182],"present":[184],"OpenVLThinkerV2,":[185],"highly":[187],"robust,":[188],"general-purpose":[189],"model.":[191],"Extensive":[192],"evaluations":[193],"18":[195],"benchmarks":[197],"demonstrate":[198],"its":[199],"superior":[200],"performance":[201],"over":[202],"strong":[203],"leading":[206],"proprietary":[207],"frontier":[208],"models.":[209]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-11T00:00:00"}