{"id":"https://openalex.org/W7139096583","doi":"https://doi.org/10.48550/arxiv.2603.16271","title":"VIGOR: VIdeo Geometry-Oriented Reward for Temporal Generative Alignment","display_name":"VIGOR: VIdeo Geometry-Oriented Reward for Temporal Generative Alignment","publication_year":2026,"publication_date":"2026-03-17","ids":{"openalex":"https://openalex.org/W7139096583","doi":"https://doi.org/10.48550/arxiv.2603.16271"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.16271","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16271","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":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.2603.16271","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072083358","display_name":"Tengjiao Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Tengjiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007965169","display_name":"Jinglei Shi","orcid":"https://orcid.org/0000-0003-2926-0415"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Jinglei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129886354","display_name":"Heng Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Heng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130008916","display_name":"Xi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xi","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":0.7849000096321106,"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":0.7849000096321106,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.08190000057220459,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.015599999576807022,"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/robustness","display_name":"Robustness (evolution)","score":0.6140000224113464},{"id":"https://openalex.org/keywords/pointwise","display_name":"Pointwise","score":0.5357999801635742},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.45989999175071716},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.45829999446868896},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.43230000138282776},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.41350001096725464},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.3682999908924103},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.36149999499320984},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.3601999878883362}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7835000157356262},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6410999894142151},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6140000224113464},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5539000034332275},{"id":"https://openalex.org/C2777984123","wikidata":"https://www.wikidata.org/wiki/Q9248237","display_name":"Pointwise","level":2,"score":0.5357999801635742},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.45989999175071716},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.45829999446868896},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.43230000138282776},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.41350001096725464},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3682999908924103},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.367000013589859},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.36149999499320984},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.3601999878883362},{"id":"https://openalex.org/C23903533","wikidata":"https://www.wikidata.org/wiki/Q17122739","display_name":"Reprojection error","level":3,"score":0.35030001401901245},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.28519999980926514},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.26829999685287476},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C137105694","wikidata":"https://www.wikidata.org/wiki/Q3407510","display_name":"Local consistency","level":4,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.16271","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16271","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.16271","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16271","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video":[0,140],"diffusion":[1,118],"models":[2,40,119,191],"lack":[3],"explicit":[4],"geometric":[5,38,51],"supervision":[6],"during":[7],"training,":[8],"leading":[9],"to":[10,41,107,115,173],"inconsistency":[11,55],"artifacts":[12],"such":[13],"as":[14,152],"object":[15],"deformation,":[16],"spatial":[17],"drift,":[18],"and":[19,80,95,134],"depth":[20],"violations":[21],"in":[22,56,71],"generated":[23],"videos.":[24],"To":[25],"address":[26],"this":[27,112],"limitation,":[28],"we":[29,85],"propose":[30],"a":[31,72,76,87,126,138,153,184],"geometry-based":[32,167],"reward":[33,113,151,168],"model":[34,114,128],"that":[35,53,91,165],"leverages":[36],"pretrained":[37],"foundation":[39],"evaluate":[42],"multi-view":[43],"consistency":[44],"through":[45,120],"cross-frame":[46],"reprojection":[47],"error.":[48],"Unlike":[49],"previous":[50],"metrics":[52],"measure":[54],"pixel":[57,60],"space,":[58],"where":[59],"intensity":[61],"may":[62],"introduce":[63,86],"additional":[64],"noise,":[65],"our":[66,150,162,166,181],"approach":[67],"conducts":[68],"error":[69,82],"computation":[70],"pointwise":[73],"fashion,":[74],"yielding":[75],"more":[77],"physically":[78],"grounded":[79],"robust":[81],"metric.":[83],"Furthermore,":[84],"geometry-aware":[88],"sampling":[89],"strategy":[90],"filters":[92],"out":[93],"low-texture":[94],"non-semantic":[96],"regions,":[97],"focusing":[98],"evaluation":[99],"on":[100],"geometrically":[101],"meaningful":[102],"areas":[103],"with":[104,149],"reliable":[105],"correspondences":[106],"improve":[108],"robustness.":[109],"We":[110],"apply":[111],"align":[116],"video":[117,144,190],"two":[121],"complementary":[122],"pathways:":[123],"post-training":[124],"of":[125,137,161],"bidirectional":[127],"via":[129,146],"SFT":[130],"or":[131],"Reinforcement":[132],"Learning":[133],"inference-time":[135,179],"optimization":[136],"Causal":[139],"Model":[141],"(e.g.,":[142],"Streaming":[143],"generator)":[145],"test-time":[147],"scaling":[148],"path":[154],"verifier.":[155],"Experimental":[156],"results":[157],"validate":[158],"the":[159],"effectiveness":[160],"design,":[163],"demonstrating":[164],"provides":[169],"superior":[170],"robustness":[171],"compared":[172],"other":[174],"variants.":[175],"By":[176],"enabling":[177],"efficient":[178],"scaling,":[180],"method":[182],"offers":[183],"practical":[185],"solution":[186],"for":[187,197],"enhancing":[188],"open-source":[189],"without":[192],"requiring":[193],"extensive":[194],"computational":[195],"resources":[196],"retraining.":[198]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-20T00:00:00"}