{"id":"https://openalex.org/W7225779282","doi":"https://doi.org/10.5281/zenodo.24137243","title":"Fly-CfC: Connectome-Constrained Closed-Form Continuous-Time Neural Networks for Sub-Millisecond Autonomous Flight","display_name":"Fly-CfC: Connectome-Constrained Closed-Form Continuous-Time Neural Networks for Sub-Millisecond Autonomous Flight","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225779282","doi":"https://doi.org/10.5281/zenodo.24137243"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24137243","doi":"https://doi.org/10.5281/zenodo.24137243","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24137243","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"article-journal"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.24137243","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5161489368","display_name":"Surayut Chanthanarat","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chanthanarat, Surayut","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5161489368"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T10320","display_name":"Neural Networks and Applications","score":0.5054000020027161,"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"}},"topics":[{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.5054000020027161,"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"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.13259999454021454,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/T10581","display_name":"Neural dynamics and brain function","score":0.08380000293254852,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C45715564","wikidata":"https://www.wikidata.org/wiki/Q1292103","display_name":"Connectome","level":3,"score":0.7490000128746033},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6930000185966492},{"id":"https://openalex.org/C2779097318","wikidata":"https://www.wikidata.org/wiki/Q2993446","display_name":"Connectomics","level":4,"score":0.5580999851226807},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5570999979972839},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5044999718666077},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.4715999960899353},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.44620001316070557},{"id":"https://openalex.org/C118403218","wikidata":"https://www.wikidata.org/wiki/Q43283","display_name":"Biological neural network","level":2,"score":0.42669999599456787},{"id":"https://openalex.org/C142812007","wikidata":"https://www.wikidata.org/wiki/Q6675553","display_name":"Looming","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C556910895","wikidata":"https://www.wikidata.org/wiki/Q384188","display_name":"Magnetoencephalography","level":3,"score":0.33340001106262207},{"id":"https://openalex.org/C118070581","wikidata":"https://www.wikidata.org/wiki/Q2060528","display_name":"Neuroevolution","level":3,"score":0.3160000145435333},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.3001999855041504},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.2791000008583069},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C152478114","wikidata":"https://www.wikidata.org/wiki/Q660910","display_name":"Neurophysiology","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24137243","doi":"https://doi.org/10.5281/zenodo.24137243","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24137243","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"article-journal"},{"id":"doi:10.5281/zenodo.24137244","doi":"https://doi.org/10.5281/zenodo.24137244","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24137244","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"article-journal"}],"best_oa_location":{"id":"doi:10.5281/zenodo.24137243","doi":"https://doi.org/10.5281/zenodo.24137243","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24137243","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"article-journal"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Continuous-time":[0],"recurrent":[1],"neural":[2,65],"networks,":[3],"particularly":[4],"Liquid":[5],"Time-Constant":[6],"(LTC)":[7],"and":[8,17,98,132,179,213],"Closed-Form":[9],"Continuous-Time":[10],"(CfC)":[11],"models,":[12],"provide":[13],"expressive":[14],"temporal":[15],"dynamics":[16],"adaptive":[18],"time-scale":[19],"modeling.":[20],"However,":[21],"their":[22],"bio-constrained":[23],"manifestations":[24],"(e.g.,":[25],"Neural":[26],"Circuit":[27],"Policies)":[28],"have":[29],"predominantly":[30],"remained":[31],"confined":[32],"to":[33],"the":[34,60,70,80,206],"19\u201328":[35],"neuron":[36],"circuits":[37],"of":[38,73,110,117,147,162],"Caenorhabditis":[39],"elegans,":[40],"while":[41],"whole-brain":[42,71],"connectome":[43,72],"models":[44],"suffer":[45],"from":[46,69],"prohibitive":[47],"computational":[48],"overheads":[49],"that":[50],"preclude":[51],"real-time":[52],"closed-loop":[53,181],"robotic":[54,216],"control.":[55],"Here,":[56],"we":[57,84],"present":[58],"Fly-CfC,":[59],"first":[61],"functional,":[62],"connectome-constrained":[63],"continuous-time":[64,126],"network":[66],"directly":[67],"derived":[68],"Drosophila":[74],"melanogaster":[75],"(male-cns":[76],"v1.0).":[77],"By":[78],"isolating":[79],"sensorimotor":[81],"visual-to-motor":[82],"pathway,":[83],"extracted":[85],"an":[86,106,124],"ultra-sparse":[87],"subcircuit":[88],"comprising":[89],"1,683":[90],"Visual":[91],"Projection":[92],"Neurons":[93,101],"(VPNs),":[94],"1,961":[95],"Recurrent":[96],"Units,":[97],"1,300":[99],"Descending":[100],"(DNs).":[102],"The":[103],"architecture":[104],"enforces":[105],"extreme":[107],"biological":[108,114,211],"sparsity":[109],"99.5119%":[111],"(34,882":[112],"active":[113],"synapses":[115],"out":[116],"7.15":[118],"million":[119],"potential":[120],"pairs)":[121],"embedded":[122],"within":[123],"analytical":[125],"ODE":[127],"formulation.":[128],"We":[129],"mathematically":[130],"establish":[131],"empirically":[133],"verify":[134],"a":[135,158,189],"strict":[136],"Zero":[137],"Gradient":[138],"Leakage":[139],"Theorem":[140],"(\u2202L/\u2202W_masked":[141],"\u2261":[142],"0.0000000),":[143],"ensuring":[144],"absolute":[145],"preservation":[146],"synaptic":[148],"topologies":[149],"during":[150],"gradient":[151],"updates.":[152],"Across":[153],"high-fidelity":[154],"simulations,":[155],"Fly-CfC":[156,187],"achieves":[157],"sub-millisecond":[159],"inference":[160],"latency":[161],"0.45":[163],"ms/step":[164],"(>1,900":[165],"FPS)":[166],"on":[167],"consumer-grade":[168],"hardware\u20142.6\u00d7":[169],"faster":[170],"than":[171],"dense":[172],"CfC":[173],"baselines.":[174],"In":[175],"dynamic":[176],"2D":[177],"environments":[178],"6-DOF":[180],"3D":[182],"PyBullet":[183],"quadcopter":[184],"slalom":[185],"regimes,":[186],"demonstrated":[188],"100%":[190],"survival":[191],"rate":[192],"(zero":[193],"collisions)":[194],"across":[195],"all":[196],"evaluation":[197],"episodes":[198],"with":[199],"omnidirectional":[200],"looming":[201],"detection.":[202],"Our":[203],"results":[204],"bridge":[205],"decades-long":[207],"divide":[208],"between":[209],"large-scale":[210],"connectomics":[212],"ultra-low-power,":[214],"agile":[215],"navigation.":[217]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}