{"id":"https://openalex.org/W7197036780","doi":"https://doi.org/10.52202/085713-2501","title":"Temporal In\u2011Context Fine\u2011Tuning with Temporal Reasoning for Versatile Control of Video Diffusion Models","display_name":"Temporal In\u2011Context Fine\u2011Tuning with Temporal Reasoning for Versatile Control of Video Diffusion Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7197036780","doi":"https://doi.org/10.52202/085713-2501"},"language":"en","primary_location":{"id":"doi:10.52202/085713-2501","doi":"https://doi.org/10.52202/085713-2501","is_oa":false,"landing_page_url":"https://doi.org/10.52202/085713-2501","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 38","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.00996","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101769965","display_name":"Kinam Kim","orcid":"https://orcid.org/0000-0002-7517-588X","observed_orcids":["https://orcid.org/0000-0002-7517-588X"]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kinam Kim","raw_affiliation_strings":["Korea Advanced Institute of Science & Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science & Technology","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108852702","display_name":"Junha Hyung","orcid":"https://orcid.org/0009-0002-8244-3659","observed_orcids":["https://orcid.org/0009-0002-8244-3659"]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Junha Hyung","raw_affiliation_strings":["Korea Advanced Institute of Science & Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science & Technology","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5145875510","display_name":"Jaegul Choo","orcid":"https://orcid.org/0000-0003-1071-4835","observed_orcids":["https://orcid.org/0000-0003-1071-4835"]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaegul Choo","raw_affiliation_strings":["KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":2.068,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8999235,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"82923","last_page":"82950"},"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":1.0,"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":1.0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.0,"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/video-diffusion-models","display_name":"video diffusion models","score":0.8230000138282776},{"id":"https://openalex.org/keywords/temporal-reasoning","display_name":"temporal reasoning","score":0.8379999995231628},{"id":"https://openalex.org/keywords/controllable-video-generation","display_name":"controllable video generation","score":0.8209999799728394},{"id":"https://openalex.org/keywords/text-to-video-generation","display_name":"text-to-video generation","score":0.734000027179718},{"id":"https://openalex.org/keywords/image-to-video-generation","display_name":"image-to-video generation","score":0.8849999904632568},{"id":"https://openalex.org/keywords/noise-injection","display_name":"noise injection","score":0.367000013589859},{"id":"https://openalex.org/keywords/few-shot-adaptation","display_name":"few-shot adaptation","score":0.5419999957084656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6650000214576721},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5680999755859375},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45719999074935913},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.37139999866485596},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.35929998755455017},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32519999146461487},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C119666444","wikidata":"https://www.wikidata.org/wiki/Q5977280","display_name":"Temporal resolution","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26019999384880066}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/085713-2501","doi":"https://doi.org/10.52202/085713-2501","is_oa":false,"landing_page_url":"https://doi.org/10.52202/085713-2501","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 38","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.00996","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.00996","pdf_url":"https://arxiv.org/pdf/2506.00996","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.00996","doi":"https://doi.org/10.48550/arxiv.2506.00996","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.00996","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.00996","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.00996","pdf_url":"https://arxiv.org/pdf/2506.00996","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3736587842","display_name":null,"funder_award_id":"RS-2019-II190075","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4468082379","display_name":null,"funder_award_id":"RS-2019-II190075","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320324161","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7197036780.pdf","grobid_xml":"https://content.openalex.org/works/W7197036780.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W4287029626","https://openalex.org/W4313483544","https://openalex.org/W4385327921","https://openalex.org/W4385848774","https://openalex.org/W4388514904","https://openalex.org/W4389115686","https://openalex.org/W4392341509","https://openalex.org/W4392970189","https://openalex.org/W4394868337","https://openalex.org/W4400600814","https://openalex.org/W4402387301","https://openalex.org/W4403665738","https://openalex.org/W4404330874","https://openalex.org/W4404354211","https://openalex.org/W4404355664","https://openalex.org/W4405468560","https://openalex.org/W4406052102","https://openalex.org/W4406800380","https://openalex.org/W4409092337","https://openalex.org/W4415796513","https://openalex.org/W7131114081","https://openalex.org/W7137945250"],"related_works":["https://openalex.org/W4226057201","https://openalex.org/W6927689776","https://openalex.org/W7164166630","https://openalex.org/W7117331566","https://openalex.org/W7117980082","https://openalex.org/W4414404492","https://openalex.org/W4405468560","https://openalex.org/W4387929853","https://openalex.org/W4417152750","https://openalex.org/W4416548644"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,164,175],"text-to-video":[3],"diffusion":[4,70],"models":[5,71,150],"have":[6],"enabled":[7],"high-quality":[8],"video":[9,69],"synthesis,":[10],"but":[11],"controllable":[12],"generation":[13,27,75],"remains":[14],"challenging,":[15],"particularly":[16],"under":[17],"limited":[18],"data":[19],"and":[20,40,50,63,84,91,122,144,154,168,178],"compute.":[21],"Existing":[22],"fine-tuning":[23,109],"methods":[24],"for":[25,66],"conditional":[26,74],"often":[28],"rely":[29],"on":[30],"external":[31],"encoders":[32],"or":[33],"architectural":[34,120],"modifications,":[35],"which":[36],"demand":[37],"large":[38],"datasets":[39],"are":[41],"typically":[42],"restricted":[43],"to":[44,72,81],"spatially":[45],"aligned":[46],"conditioning,":[47],"limiting":[48],"flexibility":[49],"scalability.":[51],"In":[52],"this":[53],"work,":[54],"we":[55],"introduce":[56],"Temporal":[57],"In-Context":[58],"Fine-Tuning":[59],"(TIC-FT),":[60],"an":[61],"efficient":[62,174],"versatile":[64],"approach":[65],"adapting":[67],"pretrained":[68,113],"diverse":[73],"tasks.":[76],"Our":[77],"key":[78],"idea":[79],"is":[80],"concatenate":[82],"condition":[83,166],"target":[85],"frames":[86,95,103],"along":[87],"the":[88,108,112],"temporal":[89,115],"axis":[90],"insert":[92],"intermediate":[93],"buffer":[94,102],"with":[96,111,126],"progressively":[97],"increasing":[98],"noise":[99],"levels.":[100],"These":[101],"enable":[104],"smooth":[105],"transitions,":[106],"aligning":[107],"process":[110],"model's":[114],"dynamics.":[116],"TIC-FT":[117,160],"requires":[118],"no":[119],"changes":[121],"achieves":[123],"strong":[124],"performance":[125],"as":[127,129,152],"few":[128],"10-30":[130],"training":[131,177],"samples.":[132],"We":[133],"validate":[134],"our":[135],"method":[136],"across":[137],"a":[138],"range":[139],"of":[140],"tasks,":[141],"including":[142],"image-to-video":[143],"video-to-video":[145],"generation,":[146],"using":[147],"large-scale":[148],"base":[149],"such":[151],"CogVideoX-5B":[153],"Wan-14B.":[155],"Extensive":[156],"experiments":[157],"show":[158],"that":[159],"outperforms":[161],"existing":[162],"baselines":[163],"both":[165,176],"fidelity":[167],"visual":[169],"quality,":[170],"while":[171],"remaining":[172],"highly":[173],"inference.":[179],"For":[180],"additional":[181],"results,":[182],"visit":[183],"https://kinam0252.github.io/TIC-FT/":[184]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-08-07T00:00:00"}