{"id":"https://openalex.org/W4416060898","doi":"https://doi.org/10.1109/iccv51701.2025.01352","title":"LiON-LoRA: Rethinking LoRA Fusion to Unify Controllable Spatial and Temporal Generation for Video Diffusion","display_name":"LiON-LoRA: Rethinking LoRA Fusion to Unify Controllable Spatial and Temporal Generation for Video Diffusion","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416060898","doi":"https://doi.org/10.1109/iccv51701.2025.01352"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01352","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.05678","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056363496","display_name":"Yisu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yisu Zhang","raw_affiliation_strings":["Zhejiang University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028833097","display_name":"Chenjie Cao","orcid":"https://orcid.org/0000-0003-3916-2843"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Chenjie Cao","raw_affiliation_strings":["DAMO Academy, Alibaba Group,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group,China","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033661654","display_name":"Chaohui Yu","orcid":"https://orcid.org/0000-0002-7852-4491"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Chaohui Yu","raw_affiliation_strings":["DAMO Academy, Alibaba Group,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group,China","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062252650","display_name":"Jianke Zhu","orcid":"https://orcid.org/0000-0003-1831-0106"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianke Zhu","raw_affiliation_strings":["Zhejiang University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":"14569","last_page":"14579"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.4251999855041504,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.4251999855041504,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.1436000019311905,"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":0.12759999930858612,"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/trajectory","display_name":"Trajectory","score":0.4503999948501587},{"id":"https://openalex.org/keywords/motion-compensation","display_name":"Motion compensation","score":0.4074000120162964},{"id":"https://openalex.org/keywords/motion-control","display_name":"Motion control","score":0.40130001306533813},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.38019999861717224},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.3750999867916107},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.36820000410079956},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.35409998893737793},{"id":"https://openalex.org/keywords/orthogonality","display_name":"Orthogonality","score":0.3479999899864197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7026000022888184},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6243000030517578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6157000064849854},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4503999948501587},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.4074000120162964},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.40130001306533813},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.38019999861717224},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.35409998893737793},{"id":"https://openalex.org/C17137986","wikidata":"https://www.wikidata.org/wiki/Q215067","display_name":"Orthogonality","level":2,"score":0.3479999899864197},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.3303000032901764},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.31349998712539673},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3050000071525574},{"id":"https://openalex.org/C205203396","wikidata":"https://www.wikidata.org/wiki/Q612143","display_name":"Bilinear interpolation","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.26579999923706055},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2635999917984009}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01352","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.05678","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.05678","pdf_url":"https://arxiv.org/pdf/2507.05678","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.05678","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.05678","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":"pmh:oai:arXiv.org:2507.05678","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.05678","pdf_url":"https://arxiv.org/pdf/2507.05678","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2368578961","display_name":null,"funder_award_id":"62376244","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5382396471","display_name":null,"funder_award_id":"2023YFF0905104","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"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],"Models":[2],"(VDMs)":[3],"have":[4],"demonstrated":[5],"remarkable":[6],"capabilities":[7],"in":[8,87,163],"synthesizing":[9],"realistic":[10],"videos":[11],"by":[12,147],"learning":[13],"from":[14],"large-scale":[15],"data.":[16,177],"Although":[17],"vanilla":[18],"Low-Rank":[19],"Adaptation":[20],"(LoRA)":[21],"can":[22],"learn":[23],"specific":[24],"spatial":[25,152],"or":[26],"temporal":[27,145,154],"movement":[28],"to":[29,48,102,121,136,144],"driven":[30],"VDMs":[31],"with":[32,131,174],"constrained":[33],"data,":[34],"achieving":[35,171],"precise":[36],"control":[37,165],"over":[38],"both":[39,127],"camera":[40,107],"trajectories":[41],"and":[42,52,76,129,153,167],"object":[43],"motion":[44,108,124,168],"remains":[45],"challenging":[46],"due":[47],"the":[49,82,117],"unstable":[50],"fusion":[51,68,104],"non-linear":[53],"scalability.":[54],"To":[55],"address":[56],"these":[57],"issues,":[58],"we":[59,80,141],"propose":[60],"LiON-LoRA,":[61],"a":[62,111,132],"novel":[63],"framework":[64],"that":[65,158],"rethinks":[66],"LoRA":[67,85],"through":[69],"three":[70],"core":[71],"principles:":[72],"Linear":[73],"scalability,":[74],"Orthogonality,":[75],"Norm":[77],"consistency.":[78],"First,":[79],"analyze":[81],"orthogonality":[83],"of":[84],"features":[86],"shallow":[88],"VDM":[89],"layers,":[90],"enabling":[91],"decoupled":[92,138],"low-level":[93],"controllability.":[94,155],"Second,":[95],"norm":[96],"consistency":[97],"is":[98,114],"enforced":[99],"across":[100],"layers":[101],"stabilize":[103],"during":[105],"complex":[106],"combinations.":[109],"Third,":[110],"controllable":[112],"token":[113],"integrated":[115],"into":[116],"diffusion":[118],"transformer":[119],"(DiT)":[120],"linearly":[122],"adjust":[123],"amplitudes":[125],"for":[126],"cameras":[128],"objects":[130],"modified":[133],"self-attention":[134],"mechanism":[135],"ensure":[137],"control.":[139],"Additionally,":[140],"extend":[142],"LiON-LoRA":[143,159],"generation":[146],"leveraging":[148],"static-camera":[149],"videos,":[150],"unifying":[151],"Experiments":[156],"demonstrate":[157],"outperforms":[160],"state-of-the-art":[161],"methods":[162],"trajectory":[164],"accuracy":[166],"strength":[169],"adjustment,":[170],"superior":[172],"generalization":[173],"minimal":[175],"training":[176],"Project":[178],"Page:":[179],"https://fuchengsu.github.io/lionlora.github.io/":[180]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}