{"id":"https://openalex.org/W7163998561","doi":"https://doi.org/10.48550/arxiv.2606.08204","title":"Neural Field Tokenizations with Hierarchy and Spatial Locality Priors","display_name":"Neural Field Tokenizations with Hierarchy and Spatial Locality Priors","publication_year":2026,"publication_date":"2026-06-06","ids":{"openalex":"https://openalex.org/W7163998561","doi":"https://doi.org/10.48550/arxiv.2606.08204"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.08204","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08204","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":"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.08204","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113077485","display_name":"Alonso Urbano","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Urbano, Alonso","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084474296","display_name":"David W. Romero","orcid":"https://orcid.org/0000-0001-5446-1070"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Romero, David W.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057301701","display_name":"Max Zimmer","orcid":"https://orcid.org/0009-0007-8683-1030"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zimmer, Max","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5043574831","display_name":"Sebastian Pokutta","orcid":"https://orcid.org/0000-0001-7365-3000"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pokutta, Sebastian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"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":0.3605000078678131,"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":0.3605000078678131,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.16269999742507935,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.13590000569820404,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.7775999903678894},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.6574000120162964},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.6252999901771545},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5637999773025513},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5516999959945679},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5497000217437744},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.5163999795913696},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4731999933719635},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.35109999775886536}],"concepts":[{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.7775999903678894},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.6574000120162964},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.6252999901771545},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6216999888420105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5759999752044678},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5637999773025513},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5516999959945679},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5497000217437744},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.5163999795913696},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4731999933719635},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3702000081539154},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.35109999775886536},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.34619998931884766},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3172999918460846},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.257999986410141},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.08204","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08204","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.08204","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08204","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":"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"},"sustainable_development_goals":[{"score":0.8845521807670593,"display_name":"Climate action","id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Neural":[0],"fields":[1,53],"parameterize":[2],"data":[3],"as":[4],"functions":[5],"from":[6,100],"coordinates":[7],"to":[8,30,80,97],"values,":[9],"providing":[10],"a":[11,78,114],"unified":[12],"framework":[13,79],"for":[14,64],"representation":[15],"learning":[16,50,65],"across":[17],"modalities.":[18],"Existing":[19],"approaches":[20],"are":[21,61],"dominated":[22],"by":[23],"per-sample":[24],"meta-learning,":[25],"which":[26,101],"scales":[27],"poorly":[28],"due":[29],"memory-intensive":[31],"inner-loop":[32],"optimization.":[33],"The":[34],"natural":[35],"alternative":[36],"--":[37,40],"feed-forward":[38],"encoding":[39],"typically":[41],"introduces":[42],"modality-specific":[43],"assumptions,":[44],"sacrificing":[45],"the":[46,102,129],"generality":[47],"that":[48,57,68],"makes":[49],"with":[51,113],"neural":[52,153],"attractive.":[54],"We":[55,75],"argue":[56],"locality":[58],"and":[59,123,137,150,159],"hierarchy":[60],"useful":[62],"priors":[63],"field":[66,95,103,154],"representations":[67,84,142],"can":[69],"be":[70],"injected":[71],"without":[72],"compromising":[73],"modality-agnosticism.":[74],"propose":[76],"LH-NeF,":[77],"learn":[81],"general-purpose":[82],"tokenized":[83],"of":[85,147],"continuous":[86],"signals.":[87],"A":[88],"locality-preserving":[89],"hierarchical":[90],"encoder":[91],"maps":[92],"raw":[93],"coordinate-value":[94],"observations":[96],"structured":[98],"tokens,":[99],"is":[104],"reconstructed":[105],"during":[106],"training.":[107],"By":[108],"replacing":[109],"meta-learning's":[110],"inner":[111],"loop":[112],"single":[115],"forward":[116],"pass,":[117],"LH-NeF":[118],"uses":[119],"42$\\times$":[120],"less":[121],"memory":[122],"supports":[124],"133$\\times$":[125],"larger":[126],"batches":[127],"than":[128],"strongest":[130],"modality-agnostic":[131],"baseline.":[132],"Across":[133],"images,":[134],"3D":[135],"shapes,":[136],"climate":[138],"fields,":[139],"our":[140],"learned":[141],"match":[143],"or":[144],"exceed":[145],"performance":[146],"modality-agnostic,":[148],"modality-specific,":[149],"specialized":[151],"generative":[152],"baselines":[155],"on":[156],"both":[157],"reconstruction":[158],"downstream":[160],"tasks.":[161]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-10T00:00:00"}