{"id":"https://openalex.org/W6966771004","doi":"https://doi.org/10.48550/arxiv.2506.17967","title":"Adapting Vision-Language Models for Evaluating World Models","display_name":"Adapting Vision-Language Models for Evaluating World Models","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W6966771004","doi":"https://doi.org/10.48550/arxiv.2506.17967"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2506.17967","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.17967","pdf_url":"https://arxiv.org/pdf/2506.17967","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.17967","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015593025","display_name":"Mariya Hendriksen","orcid":"https://orcid.org/0000-0003-0314-2955","observed_orcids":["https://orcid.org/0000-0003-0314-2955"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hendriksen, Mariya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003400295","display_name":"Tabish Rashid","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rashid, Tabish","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Bignell, David","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bignell, David","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102589439","display_name":"Raluca Georgescu","orcid":"https://orcid.org/0000-0001-7917-3729","observed_orcids":["https://orcid.org/0000-0001-7917-3729"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Georgescu, Raluca","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068060069","display_name":"Abdelhak Lemkhenter","orcid":"https://orcid.org/0000-0001-6543-4772","observed_orcids":["https://orcid.org/0000-0001-6543-4772"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lemkhenter, Abdelhak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027441885","display_name":"Katja Hofmann","orcid":"https://orcid.org/0000-0003-3697-407X","observed_orcids":["https://orcid.org/0000-0003-3697-407X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hofmann, Katja","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048451922","display_name":"Sam Devlin","orcid":"https://orcid.org/0000-0002-7769-3090","observed_orcids":["https://orcid.org/0000-0002-7769-3090"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Devlin, Sam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5020523405","display_name":"Sarah Parisot","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Parisot, Sarah","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":true,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9735999703407288,"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":0.9735999703407288,"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":0.015200000256299973,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.002899999963119626,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/world-models","display_name":"world models","score":0.9190000295639038},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.8389999866485596},{"id":"https://openalex.org/keywords/automated-assessment","display_name":"automated assessment","score":0.4909999966621399},{"id":"https://openalex.org/keywords/simulation-environment","display_name":"simulation environment","score":0.6930000185966492},{"id":"https://openalex.org/keywords/human-action-recognition","display_name":"human action recognition","score":0.9110000133514404},{"id":"https://openalex.org/keywords/character-recognition","display_name":"character recognition","score":0.9860000014305115},{"id":"https://openalex.org/keywords/parameter-efficient-fine-tuning","display_name":"parameter-efficient fine-tuning","score":0.8090000152587891},{"id":"https://openalex.org/keywords/universe","display_name":"universe","score":0.6460000276565552},{"id":"https://openalex.org/keywords/temporal-grounding","display_name":"temporal grounding","score":0.546999990940094},{"id":"https://openalex.org/keywords/semantic-consistency","display_name":"semantic consistency","score":0.4790000021457672}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7940999865531921},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5803999900817871},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5307000279426575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5080999732017517},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5047000050544739},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4837999939918518},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4797999858856201},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.43799999356269836},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.42410001158714294},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40450000762939453},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.3693000078201294},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.3544999957084656},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3452000021934509},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29510000348091125},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.2912999987602234},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2614000141620636},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.260699987411499},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.25949999690055847},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2506.17967","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.17967","pdf_url":"https://arxiv.org/pdf/2506.17967","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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.2506.17967","doi":"https://doi.org/10.48550/arxiv.2506.17967","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.17967","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"pmh:oai:arXiv.org:2506.17967","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.17967","pdf_url":"https://arxiv.org/pdf/2506.17967","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"sustainable_development_goals_aurora":[{"score":0.584682822227478,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"World":[0],"models":[1,4],"-":[2,15,44,94,100],"generative":[3,61],"that":[5],"simulate":[6],"environment":[7],"dynamics":[8],"conditioned":[9],"on":[10],"past":[11],"observations":[12],"and":[13,22,41,81,97,106,134,149,161,191],"actions":[14],"are":[16],"gaining":[17],"prominence":[18],"in":[19,73,120],"planning,":[20],"simulation,":[21],"embodied":[23],"AI.":[24],"However,":[25],"evaluating":[26],"their":[27,65,71],"rollouts":[28,130],"remains":[29,79],"a":[30,123,188],"fundamental":[31],"challenge,":[32],"requiring":[33],"fine-grained,":[34,74],"temporally":[35,75],"grounded":[36],"assessment":[37],"of":[38,60],"action":[39,95],"alignment":[40,181],"semantic":[42],"consistency":[43],"capabilities":[45],"not":[46],"captured":[47],"by":[48],"existing":[49],"metrics.":[50],"Vision-Language":[51],"Models":[52],"(VLMs)":[53],"have":[54],"shown":[55],"promise":[56],"as":[57,187],"automatic":[58],"evaluators":[59],"content":[62],"due":[63],"to":[64],"strong":[66,180],"multimodal":[67],"reasoning":[68],"abilities.":[69],"Yet,":[70],"use":[72],"sensitive":[76],"evaluation":[77,88],"tasks":[78,93],"limited":[80],"requires":[82],"targeted":[83],"adaptation.":[84],"We":[85],"introduce":[86],"an":[87],"protocol":[89],"targeting":[90],"two":[91],"recognition":[92,96,99],"character":[98],"each":[101],"assessed":[102],"across":[103,153,175],"binary,":[104],"multiple-choice,":[105],"open-ended":[107],"formats.":[108],"To":[109],"support":[110],"this,":[111],"we":[112,145],"present":[113],"UNIVERSE":[114,186],"(UNIfied":[115],"Vision-language":[116],"Evaluator":[117],"for":[118,126,194],"Rollouts":[119],"Simulated":[121],"Environments),":[122],"VLM-based":[124],"evaluator":[125,167,193],"video":[127,195],"world":[128,196],"model":[129],"adapted":[131],"under":[132],"data":[133,162],"compute":[135],"constraints.":[136],"In":[137],"our":[138],"extensive":[139],"experiments":[140],"totaling":[141],"over":[142],"5,154":[143],"GPU-days,":[144],"explore":[146],"full,":[147],"partial,":[148],"parameter-efficient":[150],"adaptation":[151],"methods":[152],"various":[154],"task":[155],"formats,":[156],"context":[157],"lengths,":[158],"sampling":[159],"methods,":[160],"compositions.":[163],"The":[164],"resulting":[165],"unified":[166],"achieves":[168],"parity":[169],"with":[170,182],"task-specific":[171],"checkpoints.":[172],"Human":[173],"studies":[174],"seven":[176],"diverse":[177],"environments":[178],"confirm":[179],"human":[183],"judgments,":[184],"establishing":[185],"lightweight,":[189],"adaptable,":[190],"semantics-aware":[192],"models.":[197]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-10T00:00:00"}