{"id":"https://openalex.org/W7138427119","doi":"https://doi.org/10.1609/aaai.v40i4.37250","title":"Latent Knowledge-Guided Video Diffusion for Scientific Phenomena Generation from a Single Initial Frame","display_name":"Latent Knowledge-Guided Video Diffusion for Scientific Phenomena Generation from a Single Initial Frame","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138427119","doi":"https://doi.org/10.1609/aaai.v40i4.37250"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i4.37250","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37250","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37250/41212","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37250/41212","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129709319","display_name":"Qinglong Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qinglong Cao","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai\nEastern Institute of Technology, Ningbo"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai\nEastern Institute of Technology, Ningbo","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129678568","display_name":"Xirui Li","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xirui Li","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129660437","display_name":"Ding Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ding Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai\nEastern Institute of Technology, Ningbo"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai\nEastern Institute of Technology, Ningbo","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129686942","display_name":"Chao Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Ma","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129680165","display_name":"Yuntian Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I127108677","display_name":"Eastern Institute of Technology","ror":"https://ror.org/00ct9cz38","country_code":"NZ","type":"education","lineage":["https://openalex.org/I127108677","https://openalex.org/I4387152882"]},{"id":"https://openalex.org/I4394709157","display_name":"Eastern Institute of Technology, Ningbo","ror":"https://ror.org/036mbz113","country_code":null,"type":"education","lineage":["https://openalex.org/I4394709157"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Yuntian Chen","raw_affiliation_strings":["Eastern Institute of Technology, Ningbo"],"affiliations":[{"raw_affiliation_string":"Eastern Institute of Technology, Ningbo","institution_ids":["https://openalex.org/I127108677","https://openalex.org/I4394709157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129671707","display_name":"Xiaokang Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaokang Yang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5129709319"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.78947368,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"4","first_page":"2625","last_page":"2633"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.5432000160217285,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.5432000160217285,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"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":0.3043999969959259,"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/T12303","display_name":"Tensor decomposition and applications","score":0.01679999940097332,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5728999972343445},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5094000101089478},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.48910000920295715},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.48829999566078186},{"id":"https://openalex.org/keywords/scientific-visualization","display_name":"Scientific visualization","score":0.4345000088214874},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.3935000002384186},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.3571999967098236},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.3425000011920929}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6363999843597412},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5728999972343445},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5094000101089478},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.48910000920295715},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.48829999566078186},{"id":"https://openalex.org/C59740354","wikidata":"https://www.wikidata.org/wiki/Q2737866","display_name":"Scientific visualization","level":3,"score":0.4345000088214874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4189999997615814},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3571999967098236},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C23213167","wikidata":"https://www.wikidata.org/wiki/Q2351730","display_name":"Scientific progress","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C138379479","wikidata":"https://www.wikidata.org/wiki/Q1116876","display_name":"Scientific modelling","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27559998631477356},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2741999924182892},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C55128770","wikidata":"https://www.wikidata.org/wiki/Q5275440","display_name":"Diffusion map","level":4,"score":0.2676999866962433},{"id":"https://openalex.org/C2781083858","wikidata":"https://www.wikidata.org/wiki/Q17327049","display_name":"Scientific literature","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C76969082","wikidata":"https://www.wikidata.org/wiki/Q486902","display_name":"Mathematical model","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C2992562121","wikidata":"https://www.wikidata.org/wiki/Q3817808","display_name":"Scientific reasoning","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i4.37250","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37250","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37250/41212","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i4.37250","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37250","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37250/41212","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138427119.pdf","grobid_xml":"https://content.openalex.org/works/W7138427119.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video":[0],"diffusion":[1,73,151],"models":[2,74],"have":[3],"achieved":[4],"impressive":[5],"results":[6],"in":[7,137],"natural":[8],"scene":[9],"generation,":[10],"yet":[11],"they":[12],"struggle":[13],"to":[14,16,75,131,162],"generalize":[15],"scientific":[17,32,61,77,121,126,163,190],"phenomena":[18,62,78,127],"such":[19],"as":[20],"fluid":[21,170],"simulations":[22,172],"and":[23,46,64,114,140,147,173,186],"meteorological":[24],"processes,":[25],"where":[26],"underlying":[27],"dynamics":[28,171],"are":[29,129],"governed":[30],"by":[31,124],"laws.":[33,164],"These":[34],"tasks":[35],"pose":[36],"unique":[37],"challenges,":[38],"including":[39],"severe":[40],"domain":[41],"gaps,":[42],"limited":[43],"training":[44],"data,":[45],"the":[47,59,106,111,117,133,149,155,178],"lack":[48],"of":[49,120,157,180],"descriptive":[50],"language":[51,115],"annotations.":[52],"To":[53],"handle":[54],"this":[55],"dilemma,":[56],"we":[57,153],"extracted":[58,88],"latent":[60,125],"knowledge":[63,86,95],"further":[65],"proposed":[66],"a":[67,80],"fresh":[68],"framework":[69],"that":[70,159],"teaches":[71],"video":[72,150],"generate":[76,132],"from":[79,98],"single":[81],"initial":[82],"frame.":[83],"Particularly,":[84],"static":[85],"is":[87,96],"via":[89],"pre-trained":[90,99],"masked":[91],"autoencoders,":[92],"while":[93],"dynamic":[94],"derived":[97],"optical":[100],"flow":[101],"prediction.":[102],"Subsequently,":[103],"based":[104],"on":[105,167],"aligned":[107],"spatial":[108,139],"relations":[109],"between":[110],"CLIP":[112],"vision":[113],"encoders,":[116],"visual":[118],"embeddings":[119,136],"phenomena,":[122],"guided":[123],"knowledge,":[128],"projected":[130],"pseudo-language":[134],"prompt":[135],"both":[138,168],"frequency":[141],"domains.":[142],"By":[143],"incorporating":[144],"these":[145],"prompts":[146],"fine-tuning":[148],"model,":[152],"enable":[154],"generation":[156],"videos":[158],"better":[160],"adhere":[161],"Extensive":[165],"experiments":[166],"computational":[169],"real-world":[174],"typhoon":[175],"observations":[176],"demonstrate":[177],"effectiveness":[179],"our":[181],"approach,":[182],"achieving":[183],"superior":[184],"fidelity":[185],"consistency":[187],"across":[188],"diverse":[189],"scenarios.":[191]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}
