{"id":"https://openalex.org/W7166010057","doi":"https://doi.org/10.48550/arxiv.2606.26410","title":"Neural Voxel Dynamics: Learning Implicit 3D Physics via Volumetric Feature Advection","display_name":"Neural Voxel Dynamics: Learning Implicit 3D Physics via Volumetric Feature Advection","publication_year":2026,"publication_date":"2026-06-24","ids":{"openalex":"https://openalex.org/W7166010057","doi":"https://doi.org/10.48550/arxiv.2606.26410"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.26410","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.26410","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.2606.26410","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121364512","display_name":"Zican Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zican","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5127861320","display_name":"Niloy Mitra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mitra, Niloy","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":0.7767000198364258,"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":0.7767000198364258,"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":0.1282999962568283,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.009200000204145908,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/physics-engine","display_name":"Physics engine","score":0.5679000020027161},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5534999966621399},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.42419999837875366},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3847000002861023},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.36809998750686646},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.3630000054836273},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.35749998688697815},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.35659998655319214},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.3476000130176544},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.33889999985694885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6126000285148621},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6105999946594238},{"id":"https://openalex.org/C190390380","wikidata":"https://www.wikidata.org/wiki/Q62505","display_name":"Physics engine","level":2,"score":0.5679000020027161},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5534999966621399},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46000000834465027},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.42419999837875366},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3847000002861023},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.3630000054836273},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.35659998655319214},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.3280999958515167},{"id":"https://openalex.org/C54170458","wikidata":"https://www.wikidata.org/wiki/Q663554","display_name":"Voxel","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32409998774528503},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.2985000014305115},{"id":"https://openalex.org/C2780799671","wikidata":"https://www.wikidata.org/wiki/Q17087362","display_name":"Transient (computer programming)","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C81587630","wikidata":"https://www.wikidata.org/wiki/Q5319044","display_name":"Dynamical simulation","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C5072599","wikidata":"https://www.wikidata.org/wiki/Q379788","display_name":"Advection","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27869999408721924},{"id":"https://openalex.org/C2777379011","wikidata":"https://www.wikidata.org/wiki/Q938545","display_name":"Implicit learning","level":3,"score":0.27869999408721924},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C116672817","wikidata":"https://www.wikidata.org/wiki/Q1454986","display_name":"Physical system","level":2,"score":0.25110000371932983},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.25099998712539673},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.26410","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.26410","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.2606.26410","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.26410","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,43,191],"present":[1],"a":[2,27,37,56,68,75,86,100,151,197],"self-supervised":[3],"framework":[4],"for":[5,120,136],"learning":[6],"implicit":[7,107],"3D":[8,28,58,108,208],"physical":[9,34,183,212],"dynamics":[10],"directly":[11],"from":[12,51,67],"video-derived":[13,159],"supervisory":[14],"signals.":[15],"While":[16],"current":[17],"generative":[18],"video":[19],"models":[20,113,204],"achieve":[21],"high":[22],"visual":[23],"fidelity,":[24],"they":[25],"lack":[26],"geometric":[29],"foundation,":[30],"often":[31],"resulting":[32],"in":[33,147],"inconsistencies":[35],"and":[36,182],"failure":[38],"to":[39,55,90,166],"maintain":[40],"object":[41],"permanence.":[42],"address":[44],"this":[45,194],"by":[46,79],"shifting":[47],"the":[48,137,207,211],"predictive":[49],"bottleneck":[50],"2D":[52],"image":[53],"space":[54],"`lifted'":[57],"Volumetric":[59,87],"Latent":[60],"Space.":[61],"Our":[62],"method":[63],"unprojects":[64],"semantic":[65],"features":[66],"Video":[69],"Joint-Embedding":[70],"Predictive":[71],"Architecture":[72],"(V-JEPA)":[73],"into":[74],"voxelized":[76],"grid,":[77],"grounded":[78],"monocular":[80,219],"depth":[81],"priors.":[82],"This":[83,134],"lifting":[84],"enables":[85],"Feature":[88],"Advection":[89],"learn":[91,106],"an":[92],"action-conditioned":[93],"transition":[94],"operator":[95],"that":[96,114,193,205],"treats":[97],"physics":[98,167],"as":[99],"spatio-temporal":[101],"state":[102],"advection":[103],"problem,":[104],"i.e.,":[105],"physics.":[109],"Unlike":[110],"state-of-the-art":[111],"hybrid":[112],"rely":[115],"on":[116,185],"explicit":[117],"classical":[118],"simulators":[119],"training":[121],"and/or":[122],"inference,":[123],"our":[124,175],"architecture":[125],"tracks":[126],"material":[127],"states":[128],"implicitly":[129],"within":[130,150],"high-dimensional":[131],"V-JEPA":[132],"features.":[133],"allows":[135],"emergent":[138],"simulation":[139],"of":[140,210,218],"heterogeneous":[141],"phenomena":[142],"(e.g.,":[143],"rigid":[144],"body":[145],"motion":[146],"fluid":[148],"flow)":[149],"single,":[152],"unified":[153],"pipeline.":[154],"Supervised":[155],"solely":[156,214],"via":[157],"end-to-end":[158],"signal":[160],"plus":[161],"action":[162],"conditions,":[163],"without":[164],"access":[165],"engine":[168],"internal":[169],"states,":[170],"labels,":[171],"or":[172],"surrogate":[173],"models,":[174],"model":[176],"demonstrates":[177],"good":[178],"long-term":[179],"structural":[180],"stability":[181],"plausibility":[184],"multiple":[186],"benchmarks":[187],"(CLEVERER,":[188],"PhysInOne,":[189],"PhysGaia).":[190],"believe":[192],"work":[195],"opens":[196],"scalable":[198],"pathway":[199],"toward":[200],"general-purpose":[201],"dynamic":[202],"world":[203,213],"internalize":[206],"invariants":[209],"through":[215],"passive":[216],"observation":[217],"videos.":[220]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-27T00:00:00"}