{"id":"https://openalex.org/W4415060502","doi":"https://doi.org/10.48550/arxiv.2503.16400","title":"ScalingNoise: Scaling Inference-Time Search for Generating Infinite Videos","display_name":"ScalingNoise: Scaling Inference-Time Search for Generating Infinite Videos","publication_year":2025,"publication_date":"2025-03-20","ids":{"openalex":"https://openalex.org/W4415060502","doi":"https://doi.org/10.48550/arxiv.2503.16400"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2503.16400","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.16400","pdf_url":"https://arxiv.org/pdf/2503.16400","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.16400","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101698326","display_name":"Haolin Yang","orcid":"https://orcid.org/0000-0002-5927-9005"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yang, Haolin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007640861","display_name":"Feilong Tang","orcid":"https://orcid.org/0000-0002-1384-198X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Feilong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090879497","display_name":"Ming Hu","orcid":"https://orcid.org/0000-0003-2336-1100"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Ming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100610166","display_name":"Qingyu Yin","orcid":"https://orcid.org/0009-0006-1129-4704"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Qingyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107953142","display_name":"Yulong Li","orcid":"https://orcid.org/0000-0003-0003-9653"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yulong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115076616","display_name":"Yexin Liu","orcid":"https://orcid.org/0000-0003-3164-6931"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yexin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016326528","display_name":"Zelin Peng","orcid":"https://orcid.org/0009-0002-4066-7929"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Zelin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085917066","display_name":"Peng Gao","orcid":"https://orcid.org/0000-0002-5176-628X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111345732","display_name":"Junjun He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Junjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005014252","display_name":"Zongyuan Ge","orcid":"https://orcid.org/0000-0002-5880-8673"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ge, Zongyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5033585021","display_name":"Imran Razzak","orcid":"https://orcid.org/0000-0002-3930-6600"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Razzak, Imran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5101698326"],"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/T11439","display_name":"Video Analysis and Summarization","score":0.9470000267028809,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9470000267028809,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9157999753952026,"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/noise-reduction","display_name":"Noise reduction","score":0.666700005531311},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.6547999978065491},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6288999915122986},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5899999737739563},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5806999802589417},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5386999845504761},{"id":"https://openalex.org/keywords/video-denoising","display_name":"Video denoising","score":0.5074999928474426},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4885999858379364},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.47870001196861267}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7383999824523926},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.666700005531311},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.6547999978065491},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6288999915122986},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5899999737739563},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5806999802589417},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5386999845504761},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5317999720573425},{"id":"https://openalex.org/C30814859","wikidata":"https://www.wikidata.org/wiki/Q4119603","display_name":"Video denoising","level":5,"score":0.5074999928474426},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4885999858379364},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.47870001196861267},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4528000056743622},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42239999771118164},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.41019999980926514},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.396699994802475},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39010000228881836},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.37560001015663147},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3693000078201294},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36899998784065247},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3662000000476837},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3637000024318695},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3619999885559082},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34200000762939453},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.2653999924659729},{"id":"https://openalex.org/C68710425","wikidata":"https://www.wikidata.org/wiki/Q5275442","display_name":"Diffusion process","level":3,"score":0.26499998569488525},{"id":"https://openalex.org/C39394851","wikidata":"https://www.wikidata.org/wiki/Q921594","display_name":"Inter frame","level":4,"score":0.26339998841285706},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2605000138282776},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.26019999384880066},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.25870001316070557}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2503.16400","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.16400","pdf_url":"https://arxiv.org/pdf/2503.16400","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2503.16400","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.16400","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.16400","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.16400","pdf_url":"https://arxiv.org/pdf/2503.16400","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"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],"diffusion":[1,117,163],"models":[2,41,118],"(VDMs)":[3],"facilitate":[4],"the":[5,51,70,84,87,91,97,103,147,162,240],"generation":[6,45],"of":[7,53,74,86,123],"high-quality":[8],"videos,":[9],"with":[10,37],"current":[11,92],"research":[12],"predominantly":[13],"concentrated":[14],"on":[15,64,146,235],"scaling":[16,32,71],"efforts":[17],"during":[18,61],"training":[19],"through":[20],"improvements":[21],"in":[22,90],"data":[23],"quality,":[24],"computational":[25],"resources,":[26],"and":[27,129,171,186,228],"model":[28,195],"complexity.":[29],"However,":[30],"inference-time":[31,72,153],"has":[33],"received":[34],"less":[35],"attention,":[36],"most":[38],"approaches":[39],"restricting":[40],"to":[42,76,166,179,202],"a":[43,131,138,151,184,193,209],"single":[44],"attempt.":[46],"Recent":[47],"studies":[48],"have":[49],"uncovered":[50],"existence":[52],"\"golden":[54],"noises\"":[55],"that":[56,68,116,156,213,239],"can":[57],"enhance":[58],"video":[59,231,246],"quality":[60,85],"generation.":[62,232,247],"Building":[63],"this,":[65],"we":[66,149,175,205],"find":[67],"guiding":[69],"search":[73,154],"VDMs":[75],"identify":[77],"better":[78],"noise":[79,211],"candidates":[80,207],"not":[81],"only":[82],"evaluates":[83],"frames":[88],"generated":[89,199],"step":[93],"but":[94],"also":[95],"preserves":[96],"high-level":[98],"object":[99],"features":[100],"by":[101,125,137,197],"referencing":[102],"anchor":[104],"frame":[105],"from":[106,208],"previous":[107],"multi-chunks,":[108],"thereby":[109],"delivering":[110],"long-term":[111,143,190],"value.":[112],"Our":[113],"analysis":[114],"reveals":[115],"inherently":[119],"possess":[120],"flexible":[121],"adjustments":[122],"computation":[124],"varying":[126],"denoising":[127,133,178],"steps,":[128],"even":[130],"one-step":[132,177],"approach,":[134],"when":[135],"guided":[136],"reward":[139,194],"signal,":[140],"yields":[141],"significant":[142],"benefits.":[144],"Based":[145],"observation,":[148],"proposeScalingNoise,":[150],"plug-and-play":[152],"strategy":[155],"identifies":[157],"golden":[158],"initial":[159,181],"noises":[160,182],"for":[161],"sampling":[164],"process":[165],"improve":[167],"global":[168],"content":[169],"consistency":[170],"visual":[172],"diversity.":[173],"Specifically,":[174],"perform":[176],"convert":[180],"into":[183],"clip":[185],"subsequently":[187],"evaluate":[188],"its":[189],"value,":[191],"leveraging":[192],"anchored":[196],"previously":[198],"content.":[200],"Moreover,":[201],"preserve":[203],"diversity,":[204],"sample":[206],"tilted":[210],"distribution":[212],"up-weights":[214],"promising":[215],"noises.":[216],"In":[217],"this":[218],"way,":[219],"ScalingNoise":[220,242],"significantly":[221],"reduces":[222],"noise-induced":[223],"errors,":[224],"ensuring":[225],"more":[226],"coherent":[227],"spatiotemporally":[229],"consistent":[230],"Extensive":[233],"experiments":[234],"benchmark":[236],"datasets":[237],"demonstrate":[238],"proposed":[241],"effectively":[243],"improves":[244],"long":[245]},"counts_by_year":[],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-11T00:00:00"}