{"id":"https://openalex.org/W7168635888","doi":"https://doi.org/10.1145/3799902.3811088","title":"UCM: Unified Modeling of Camera Control and Memory with Time-aware Positional Encoding Warping for World Models","display_name":"UCM: Unified Modeling of Camera Control and Memory with Time-aware Positional Encoding Warping for World Models","publication_year":2026,"publication_date":"2026-07-16","ids":{"openalex":"https://openalex.org/W7168635888","doi":"https://doi.org/10.1145/3799902.3811088"},"language":null,"primary_location":{"id":"doi:10.1145/3799902.3811088","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811088","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3799902.3811088","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058414523","display_name":"Tian-Xing Xu","orcid":"https://orcid.org/0000-0002-9433-1980"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian-Xing Xu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9433-1980","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103243439","display_name":"Zixuan Wang","orcid":"https://orcid.org/0000-0001-7291-6198"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zi-Xuan Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7291-6198","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101451274","display_name":"Guangyuan Wang","orcid":"https://orcid.org/0009-0007-2388-0716"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangyuan Wang","raw_affiliation_strings":["Tongyi Lab, Alibaba, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-2388-0716","affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141038688","display_name":"Li Hu","orcid":"https://orcid.org/0000-0002-9666-6872"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Hu","raw_affiliation_strings":["Tongyi Lab, Alibaba, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-9666-6872","affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140972626","display_name":"Zhongyi Zhang","orcid":"https://orcid.org/0009-0006-5648-1255"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongyi Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0006-5648-1255","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141020926","display_name":"Peng Zhang","orcid":"https://orcid.org/0009-0009-3704-051X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Zhang","raw_affiliation_strings":["Tongyi Lab, Alibaba, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-3704-051X","affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141008589","display_name":"Bang Zhang","orcid":"https://orcid.org/0009-0007-9529-0184"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bang Zhang","raw_affiliation_strings":["Tongyi Lab, Alibaba, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-9529-0184","affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049883689","display_name":"Song\u2013Hai Zhang","orcid":"https://orcid.org/0000-0003-0460-1586"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song-Hai Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0460-1586","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.5853999853134155},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.51910001039505},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4973999857902527},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.4724999964237213},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.47130000591278076},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4065000116825104},{"id":"https://openalex.org/keywords/view-synthesis","display_name":"View synthesis","score":0.3878999948501587},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.36629998683929443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8291000127792358},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6083999872207642},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.60589998960495},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.5853999853134155},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.51910001039505},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4973999857902527},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.4724999964237213},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.47130000591278076},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4065000116825104},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.3878999948501587},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.28790000081062317},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C2780139006","wikidata":"https://www.wikidata.org/wiki/Q1493902","display_name":"Key frame","level":3,"score":0.2648000121116638},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.26179999113082886},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.25600001215934753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3799902.3811088","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811088","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3799902.3811088","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811088","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2159269332","https://openalex.org/W2566265240","https://openalex.org/W2594519801","https://openalex.org/W2738551266","https://openalex.org/W2962785568","https://openalex.org/W3097660860","https://openalex.org/W4288099666","https://openalex.org/W4388979610","https://openalex.org/W4390541944","https://openalex.org/W4390872297","https://openalex.org/W4400403028","https://openalex.org/W4400573519","https://openalex.org/W4402775760","https://openalex.org/W4407722206","https://openalex.org/W4412171637","https://openalex.org/W4412587524","https://openalex.org/W4413144558","https://openalex.org/W4413145933","https://openalex.org/W4413146321","https://openalex.org/W4413147084","https://openalex.org/W4413147574","https://openalex.org/W4415798523","https://openalex.org/W7103752023","https://openalex.org/W7103755807","https://openalex.org/W7109971032","https://openalex.org/W7160095717","https://openalex.org/W7160137993"],"related_works":[],"abstract_inverted_index":{"World":[0],"models":[1],"based":[2,40],"on":[3,41,61,134,141,153],"video":[4,164],"generation":[5],"demonstrate":[6,146],"remarkable":[7],"potential":[8],"for":[9,85,113],"simulating":[10],"interactive":[11],"environments":[12],"yet":[13],"suffer":[14],"from":[15,35],"persistent":[16],"difficulties":[17],"in":[18,48,162],"two":[19],"key":[20],"areas:":[21],"maintaining":[22],"long-term":[23,89,154],"content":[24],"consistency":[25],"when":[26],"scenes":[27],"are":[28],"revisited":[29],"and":[30,51,73,91,143],"enabling":[31,132],"precise":[32,92,159],"camera":[33,93,160],"control":[34,94],"user-specified":[36],"inputs.":[37],"Existing":[38],"methods":[39,58,152],"explicit":[42,67],"3D":[43],"reconstruction":[44],"often":[45],"compromise":[46],"flexibility":[47],"unbounded":[49],"scenarios":[50],"struggle":[52],"to":[53,128],"preserve":[54],"fine-grained":[55],"structures.":[56],"Alternative":[57],"rely":[59],"directly":[60],"previously":[62],"generated":[63],"frames":[64],"without":[65],"establishing":[66],"spatial":[68],"correspondence,":[69],"thereby":[70],"limiting":[71],"controllability":[72,161],"consistency.":[74],"To":[75,102],"address":[76],"these":[77],"limitations,":[78],"we":[79,106,117],"present":[80],"UCM,":[81],"a":[82,96,119],"novel":[83],"framework":[84],"unified":[86],"modeling":[87],"of":[88],"memory":[90],"via":[95],"time-aware":[97],"positional":[98],"encoding":[99],"warping":[100],"mechanism.":[101],"reduce":[103],"computational":[104],"overhead,":[105],"design":[107],"an":[108],"efficient":[109],"dual-stream":[110],"diffusion":[111],"transformer":[112],"high-fidelity":[114,163],"generation.":[115,165],"Moreover,":[116],"introduce":[118],"scalable":[120],"data":[121],"curation":[122],"strategy":[123],"that":[124,147],"utilizes":[125],"point-cloud-based":[126],"rendering":[127],"simulate":[129],"scene":[130,155],"revisiting,":[131],"training":[133],"over":[135],"500K":[136],"monocular":[137],"videos.":[138],"Extensive":[139],"experiments":[140],"real-world":[142],"synthetic":[144],"benchmarks":[145],"UCM":[148],"significantly":[149],"outperforms":[150],"state-of-the-art":[151],"consistency,":[156],"while":[157],"achieving":[158],"Our":[166],"code":[167],"is":[168],"released":[169],"at":[170],"https://humanaigc.github.io/ucm-webpage/.":[171]},"counts_by_year":[],"updated_date":"2026-07-17T05:58:32.477365","created_date":"2026-07-17T00:00:00"}
