{"id":"https://openalex.org/W7133493150","doi":"https://doi.org/10.48550/arxiv.2603.03269","title":"LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory","display_name":"LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory","publication_year":2026,"publication_date":"2026-03-03","ids":{"openalex":"https://openalex.org/W7133493150","doi":"https://doi.org/10.48550/arxiv.2603.03269"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.03269","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.03269","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.03269","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128075891","display_name":"Junyi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhang, Junyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060577899","display_name":"Charles Herrmann","orcid":"https://orcid.org/0000-0002-9576-9394"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Herrmann, Charles","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005363574","display_name":"Junhwa Hur","orcid":"https://orcid.org/0000-0002-9164-3049"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hur, Junhwa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128041734","display_name":"Chen Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128087729","display_name":"Ming-Hsuan Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Ming-Hsuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109934168","display_name":"Forrester Cole","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cole, Forrester","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128101929","display_name":"Trevor Darrell","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Darrell, Trevor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128120412","display_name":"Deqing Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Deqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5128075891"],"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.54339998960495,"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"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.54339998960495,"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"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.29580000042915344,"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":0.043699998408555984,"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/context","display_name":"Context (archaeology)","score":0.5548999905586243},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.43140000104904175},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4174000024795532},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.414900004863739},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.40560001134872437},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4027999937534332},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.349700003862381},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.3490999937057495},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.337799996137619}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7440999746322632},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5548999905586243},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5051000118255615},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.43140000104904175},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42829999327659607},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4174000024795532},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.414900004863739},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.40560001134872437},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4027999937534332},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3799000084400177},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3490999937057495},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C70958404","wikidata":"https://www.wikidata.org/wiki/Q7512728","display_name":"Signal reconstruction","level":4,"score":0.28630000352859497},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27889999747276306},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C2779602883","wikidata":"https://www.wikidata.org/wiki/Q15544750","display_name":"Memory architecture","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.03269","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.03269","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.03269","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.03269","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":"article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.6743113994598389}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Feedforward":[0],"geometric":[1],"foundation":[2],"models":[3],"achieve":[4],"strong":[5,54],"short-window":[6],"reconstruction,":[7],"yet":[8],"scaling":[9],"them":[10],"to":[11,41,88,106,120,131,151],"minutes-long":[12],"videos":[13],"is":[14],"bottlenecked":[15],"by":[16,164],"quadratic":[17],"attention":[18],"complexity":[19],"or":[20],"limited":[21],"effective":[22],"memory":[23,76,87,116],"in":[24,51],"recurrent":[25],"designs.":[26],"We":[27],"present":[28],"LoGeR":[29,47,119,154],"(Long-context":[30],"Geometric":[31],"Reconstruction),":[32],"a":[33,73,82,99,142],"novel":[34],"architecture":[35,117],"that":[36],"scales":[37],"dense":[38],"3D":[39],"reconstruction":[40,171],"extremely":[42],"long":[43],"sequences":[44,124,148],"without":[45],"post-optimization.":[46],"processes":[48],"video":[49],"streams":[50],"chunks,":[52],"leveraging":[53],"bidirectional":[55],"priors":[56],"for":[57,110],"high-fidelity":[58],"intra-chunk":[59],"reasoning.":[60],"To":[61],"manage":[62],"the":[63,90],"critical":[64],"challenge":[65],"of":[66,125,133,149],"coherence":[67],"across":[68,138],"chunk":[69],"boundaries,":[70],"we":[71],"propose":[72],"learning-based":[74],"hybrid":[75],"module.":[77],"This":[78],"dual-component":[79],"system":[80],"combines":[81],"parametric":[83],"Test-Time":[84],"Training":[85],"(TTT)":[86],"anchor":[89],"global":[91],"coordinate":[92],"frame":[93],"and":[94,128,141],"prevent":[95],"scale":[96],"drift,":[97],"alongside":[98],"non-parametric":[100],"Sliding":[101],"Window":[102],"Attention":[103],"(SWA)":[104],"mechanism":[105],"preserve":[107],"uncompressed":[108],"context":[109],"high-precision":[111],"adjacent":[112],"alignment.":[113],"Remarkably,":[114],"this":[115],"enables":[118],"be":[121],"trained":[122],"on":[123,162],"128":[126],"frames,":[127,153],"generalize":[129],"up":[130,150],"thousands":[132],"frames":[134],"during":[135],"inference.":[136],"Evaluated":[137],"standard":[139],"benchmarks":[140],"newly":[143],"repurposed":[144],"VBR":[145],"dataset":[146],"with":[147],"19k":[152],"substantially":[155],"outperforms":[156],"prior":[157],"state-of-the-art":[158],"feedforward":[159],"methods--reducing":[160],"ATE":[161],"KITTI":[163],"over":[165,172],"74%--and":[166],"achieves":[167],"robust,":[168],"globally":[169],"consistent":[170],"unprecedented":[173],"horizons.":[174]},"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2026-03-05T00:00:00"}