{"id":"https://openalex.org/W7162686099","doi":"https://doi.org/10.48550/arxiv.2605.28230","title":"Proprio: Latent Self-Scoring and Inference-Time Refinement for Physically Plausible Video Generation","display_name":"Proprio: Latent Self-Scoring and Inference-Time Refinement for Physically Plausible Video Generation","publication_year":2026,"publication_date":"2026-05-27","ids":{"openalex":"https://openalex.org/W7162686099","doi":"https://doi.org/10.48550/arxiv.2605.28230"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.28230","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28230","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.2605.28230","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082185314","display_name":"Mariam Hassan","orcid":"https://orcid.org/0000-0002-7972-9827"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hassan, Mariam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063024690","display_name":"Kaouther Messaoud","orcid":"https://orcid.org/0000-0002-4602-8100"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Messaoud, Kaouther","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137287045","display_name":"Wuyang Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Wuyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137267262","display_name":"Alexandre Alahi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alahi, Alexandre","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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6247000098228455,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6247000098228455,"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/T12290","display_name":"Human Motion and Animation","score":0.09960000216960907,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.050999999046325684,"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/generator","display_name":"Generator (circuit theory)","score":0.6255999803543091},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5616000294685364},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.48539999127388},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.47189998626708984},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.45649999380111694},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4422999918460846},{"id":"https://openalex.org/keywords/physical-system","display_name":"Physical system","score":0.3903000056743622},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3871999979019165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7418000102043152},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6255999803543091},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5616000294685364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5411999821662903},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.48539999127388},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.47189998626708984},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.45649999380111694},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4422999918460846},{"id":"https://openalex.org/C116672817","wikidata":"https://www.wikidata.org/wiki/Q1454986","display_name":"Physical system","level":2,"score":0.3903000056743622},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3871999979019165},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.3481000065803528},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33880001306533813},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32330000400543213},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27390000224113464},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.26030001044273376}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.28230","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28230","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.2605.28230","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28230","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modern":[0],"video":[1,24,168],"generative":[2],"models":[3],"produce":[4],"visually":[5],"impressive":[6],"results,":[7],"yet":[8],"frequently":[9],"violate":[10],"basic":[11],"physical":[12,31,113,137,156,179],"principles.":[13],"We":[14,77],"propose":[15],"Proprio,":[16],"a":[17,22,58,91],"training-free":[18],"framework":[19],"that":[20,62,148,166],"enables":[21],"frozen":[23,167],"generator":[25],"to":[26,132,141],"assess":[27],"and":[28,73,83,95,107,118,135,176],"improve":[29],"the":[30,40,49,67,178],"plausibility":[32,157,180],"of":[33,43,161,181],"its":[34],"own":[35,45,183],"outputs.":[36,184],"Inspired":[37],"by":[38,66],"proprioception,":[39],"biological":[41],"sense":[42],"one's":[44],"movement,":[46],"Proprio":[47,110,127],"treats":[48],"model's":[50],"flow":[51],"residual":[52],"under":[53],"controlled":[54],"latent":[55],"perturbations":[56],"as":[57],"self-scoring":[59],"signal.":[60],"Samples":[61],"are":[63],"better":[64],"explained":[65],"generator's":[68],"learned":[69],"dynamics":[70],"induce":[71],"smaller":[72],"more":[74],"stable":[75],"residuals.":[76],"aggregate":[78],"this":[79],"signal":[80],"across":[81],"timesteps":[82],"perturbations,":[84],"focus":[85],"it":[86,97],"on":[87],"motion-relevant":[88],"regions":[89],"with":[90],"dynamic":[92],"spatiotemporal":[93],"mask,":[94],"use":[96],"for":[98,155,174],"best-of-N":[99],"search,":[100],"gradient-based":[101],"self-refinement,":[102],"or":[103,152],"both.":[104],"Across":[105],"text-to-video":[106],"image-to-video":[108],"benchmarks,":[109],"consistently":[111],"improves":[112,128],"plausibility,":[114],"outperforming":[115],"VLM-based":[116],"scoring,":[117],"external":[119],"world-model":[120],"baselines":[121],"in":[122,158],"several":[123],"settings.":[124],"With":[125],"TurboWan2.2,":[126],"Physics-IQ":[129],"from":[130,139],"32.2":[131],"37.5":[133],"(+16.5%)":[134],"VideoPhy2-hard":[136],"commonsense":[138],"45.6":[140],"55.0":[142],"(+20.6%).":[143],"Human":[144],"evaluation":[145],"further":[146],"shows":[147],"raters":[149],"prefer":[150],"Proprio-selected":[151],"refined":[153],"videos":[154],"roughly":[159],"two-thirds":[160],"comparisons.":[162],"These":[163],"results":[164],"suggest":[165],"generators":[169],"contain":[170],"actionable":[171],"internal":[172],"signals":[173],"evaluating":[175],"improving":[177],"their":[182]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-29T00:00:00"}