{"id":"https://openalex.org/W7160859962","doi":"https://doi.org/10.48550/arxiv.2605.07794","title":"NoiseGate: Learning Per-Latent Timestep Schedules as Information Gating in World Action Models","display_name":"NoiseGate: Learning Per-Latent Timestep Schedules as Information Gating in World Action Models","publication_year":2026,"publication_date":"2026-05-08","ids":{"openalex":"https://openalex.org/W7160859962","doi":"https://doi.org/10.48550/arxiv.2605.07794"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.07794","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07794","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.07794","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135858997","display_name":"Wen Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Wen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135895948","display_name":"Haoran Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Haoran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135879126","display_name":"Yongjian Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Yongjian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063077903","display_name":"Yunxuan Ma","orcid":"https://orcid.org/0009-0005-1819-2594"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Yunxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135898306","display_name":"Haoran Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Haoran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135891094","display_name":"Jing Long","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Long, Jing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135875109","display_name":"Zhouying Mo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mo, Zhouying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125195887","display_name":"Zhong Guan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guan, Zhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125221891","display_name":"Yucheng Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Yucheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041877213","display_name":"Shuai Di","orcid":"https://orcid.org/0000-0001-7466-9709"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Di, Shuai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102937576","display_name":"Junwu Xiong","orcid":"https://orcid.org/0009-0008-2028-510X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiong, Junwu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"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":0.3379000127315521,"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":0.3379000127315521,"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":0.11540000140666962,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.09080000221729279,"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/schedule","display_name":"Schedule","score":0.6230999827384949},{"id":"https://openalex.org/keywords/gating","display_name":"Gating","score":0.4747999906539917},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4625000059604645},{"id":"https://openalex.org/keywords/information-flow","display_name":"Information flow","score":0.46230000257492065},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.44679999351501465},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.41920000314712524},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.38350000977516174},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.3691999912261963},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3614000082015991}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7469000220298767},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.6230999827384949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5149000287055969},{"id":"https://openalex.org/C194544171","wikidata":"https://www.wikidata.org/wiki/Q21105679","display_name":"Gating","level":2,"score":0.4747999906539917},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4625000059604645},{"id":"https://openalex.org/C2779136372","wikidata":"https://www.wikidata.org/wiki/Q10283002","display_name":"Information flow","level":2,"score":0.46230000257492065},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.44679999351501465},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4390000104904175},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.41920000314712524},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.38350000977516174},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.3691999912261963},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3614000082015991},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.35670000314712524},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.34689998626708984},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3199999928474426},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.3107999861240387},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C122770356","wikidata":"https://www.wikidata.org/wiki/Q1656753","display_name":"Identifiability","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25380000472068787},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.07794","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07794","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":"doi:10.48550/arxiv.2605.07794","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07794","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":"article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7930454015731812}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"World":[0],"Action":[1],"Models":[2],"(WAMs)":[3],"are":[4,35,50],"an":[5],"emerging":[6],"family":[7],"of":[8,96,108,151],"policies":[9],"that":[10,45,118,176,186],"tie":[11],"robot":[12],"action":[13,69,126,157],"generation":[14],"to":[15,85,155],"future-observation":[16],"modeling.":[17],"In":[18],"this":[19,60,94,111],"work,":[20],"we":[21],"focus":[22],"on":[23,196,206],"the":[24,105,115,131,146,149,156,188],"joint":[25,198],"video--action":[26,199],"modeling":[27],"paradigm,":[28],"where":[29,66],"actions":[30],"and":[31,48,68,183],"imagined":[32],"future":[33],"observations":[34],"co-generated":[36],"along":[37],"a":[38,63,81,99,135,141,171,197],"shared":[39,73,101,112],"denoising":[40],"or":[41],"flow":[42],"trajectory,":[43],"so":[44],"perception,":[46],"prediction,":[47],"control":[49],"coupled":[51],"within":[52],"one":[53],"generative":[54],"process.":[55],"Existing":[56],"WAMs":[57],"typically":[58],"realize":[59],"paradigm":[61],"with":[62],"Mixture-of-Transformers":[64],"(MoT),":[65],"video":[67],"tokens":[70],"interact":[71],"through":[72],"self-attention.":[74],"This":[75],"architecture":[76],"can":[77],"in":[78],"principle":[79],"assign":[80],"separate":[82],"timestep":[83,166],"$t_f$":[84],"each":[86],"predicted":[87,120],"latent":[88,121,142],"frame,":[89],"yet":[90],"current":[91],"systems":[92],"collapse":[93],"degree":[95],"freedom":[97],"onto":[98],"single":[100],"scalar":[102],"$t$.":[103],"Under":[104],"noise-as-masking":[106],"view":[107,130],"Diffusion":[109],"Forcing,":[110],"schedule":[113,133,189],"imposes":[114],"unjustified":[116],"prior":[117],"every":[119],"is":[122],"equally":[123],"reliable":[124],"for":[125],"generation.":[127],"We":[128,159],"instead":[129],"per-latent":[132,165,178],"as":[134],"\\emph{learnable":[136],"information-gating":[137],"policy}:":[138],"by":[139],"changing":[140],"frame's":[143],"noise":[144],"level,":[145],"policy":[147,190],"modulates":[148],"reliability":[150],"its":[152],"Key/Value":[153],"contribution":[154],"tokens.":[158],"propose":[160],"\\textbf{NoiseGate},":[161],"which":[162],"combines":[163],"independent":[164],"sampling":[167],"during":[168,181],"backbone":[169],"training,":[170],"lightweight":[172],"Gating":[173],"Policy":[174],"Network":[175],"emits":[177],"time":[179],"increments":[180],"denoising,":[182],"task-reward":[184],"optimization":[185],"trains":[187],"without":[191],"hand-crafted":[192],"shape":[193],"priors.":[194],"Built":[195],"MoT":[200],"backbone,":[201],"NoiseGate":[202],"delivers":[203],"consistent":[204],"gains":[205],"diverse":[207],"RoboTwin":[208],"random-scene":[209],"manipulation":[210],"tasks.":[211]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-12T00:00:00"}