{"id":"https://openalex.org/W7163024921","doi":"https://doi.org/10.48550/arxiv.2605.30855","title":"Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation","display_name":"Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation","publication_year":2026,"publication_date":"2026-05-29","ids":{"openalex":"https://openalex.org/W7163024921","doi":"https://doi.org/10.48550/arxiv.2605.30855"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.30855","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.30855","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.2605.30855","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137555923","display_name":"Hanlin Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Hanlin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030033238","display_name":"Jiaxin Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Jiaxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137522106","display_name":"Xibin Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Xibin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137559735","display_name":"Yifu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yifu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137550943","display_name":"Steve Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Steve","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137556333","display_name":"Hongdong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Hongdong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137584457","display_name":"Pan Ji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji, Pan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137569943","display_name":"Gim Hee Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Gim Hee","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":0.6851000189781189,"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":0.6851000189781189,"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":0.09030000120401382,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.07029999792575836,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/autoregressive-model","display_name":"Autoregressive model","score":0.6136999726295471},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.49790000915527344},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.48510000109672546},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4675000011920929},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.4352000057697296},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.40790000557899475},{"id":"https://openalex.org/keywords/on-the-fly","display_name":"On the fly","score":0.3707999885082245},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.3596000075340271}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7781999707221985},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6136999726295471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.520799994468689},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.49790000915527344},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.48510000109672546},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4675000011920929},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.4352000057697296},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43470001220703125},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.40790000557899475},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.3707999885082245},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.3596000075340271},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35580000281333923},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.35030001401901245},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32850000262260437},{"id":"https://openalex.org/C2993691153","wikidata":"https://www.wikidata.org/wiki/Q492","display_name":"Memory formation","level":3,"score":0.3181999921798706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3176000118255615},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.29989999532699585},{"id":"https://openalex.org/C88576662","wikidata":"https://www.wikidata.org/wiki/Q18646","display_name":"Episodic memory","level":3,"score":0.2712000012397766},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25839999318122864},{"id":"https://openalex.org/C118702147","wikidata":"https://www.wikidata.org/wiki/Q189396","display_name":"Dynamic random-access memory","level":3,"score":0.2578999996185303},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.30855","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.30855","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.2605.30855","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.30855","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":{"Frame-wise":[0],"action-controlled":[1],"image-to-video":[2],"generation":[3,121],"is":[4],"a":[5,92,162],"promising":[6],"paradigm":[7],"for":[8,62],"interactive":[9],"world":[10],"simulation,":[11],"where":[12,52,74],"each":[13],"control":[14],"signal":[15],"should":[16],"elicit":[17],"an":[18],"immediate":[19],"visual":[20,24],"response.":[21],"However,":[22],"maintaining":[23],"fidelity":[25],"and":[26,60,65,102,126,170,173,190,200],"3D":[27,100],"consistency":[28],"over":[29],"long":[30],"autoregressive":[31,168],"rollouts":[32],"remains":[33],"challenging.":[34],"Existing":[35],"3D-aware":[36],"methods":[37],"often":[38],"suffer":[39],"from":[40,49,119,143],"catastrophic":[41],"drift":[42],"due":[43],"to":[44,58,79,98,104,123,185],"two":[45],"impediments:":[46],"information":[47],"loss":[48],"\\textit{Latent--RGB":[50],"Cycling},":[51],"generated":[53],"latents":[54,117],"are":[55],"repeatedly":[56],"decoded":[57],"RGB":[59],"re-encoded":[61],"future":[63],"conditioning,":[64],"the":[66,71,120,183],"training--inference":[67],"gap":[68],"induced":[69],"by":[70,167],"\\textit{error-free":[72],"hypothesis},":[73],"clean":[75],"training":[76],"memory":[77,101,178,188],"fails":[78],"match":[80],"prediction-corrupted":[81],"inference":[82],"memory.":[83],"To":[84],"address":[85],"these":[86],"challenges,":[87],"we":[88,109,148],"present":[89],"\\textbf{Robust":[90],"Dreamer},":[91],"memory-augmented":[93],"framework":[94],"built":[95],"around":[96],"how":[97,103],"design":[99],"use":[105],"it":[106],"robustly.":[107],"First,":[108],"introduce":[110],"\\textbf{Latent":[111],"Gaussian":[112,124,131],"Memory},":[113],"which":[114,156],"anchors":[115],"diffusion":[116],"inherited":[118],"process":[122],"primitives":[125],"recalls":[127],"them":[128,166,175],"via":[129],"latent-space":[130],"splatting.":[132],"This":[133,181],"provides":[134],"dense,":[135],"geometry-aware,":[136],"view-aligned":[137],"conditioning":[138],"while":[139],"avoiding":[140],"accumulated":[141],"degradation":[142],"repeated":[144],"VAE":[145],"conversion.":[146],"Second,":[147],"propose":[149],"\\textbf{Deviation":[150],"Learning":[151],"with":[152],"Dynamic":[153],"Deviation":[154],"Archive},":[155],"synthesizes":[157],"rollout-induced":[158],"latent":[159],"deviations":[160],"through":[161],"one-step":[163],"approximation,":[164],"stores":[165],"stage":[169],"denoising":[171],"timestamp,":[172],"injects":[174],"into":[176],"historical":[177],"during":[179],"training.":[180],"exposes":[182],"generator":[184],"realistic":[186],"corrupted":[187],"states":[189],"teaches":[191],"internal":[192],"correction":[193],"before":[194],"inference.":[195],"Experiments":[196],"on":[197],"ScanNet,":[198],"DL3DV,":[199],"OmniWorldGame":[201],"demonstrate":[202],"state-of-the-art":[203],"long-horizon":[204],"performance.":[205]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-02T00:00:00"}