{"id":"https://openalex.org/W7155048592","doi":"https://doi.org/10.48550/arxiv.2604.18284","title":"Spike-NVPT: Learning Robust Visual Prompts via Bio-Inspired Temporal Filtering and Discretization","display_name":"Spike-NVPT: Learning Robust Visual Prompts via Bio-Inspired Temporal Filtering and Discretization","publication_year":2026,"publication_date":"2026-04-20","ids":{"openalex":"https://openalex.org/W7155048592","doi":"https://doi.org/10.48550/arxiv.2604.18284"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.18284","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.18284","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.18284","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134163966","display_name":"Qiugang Zhan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhan, Qiugang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102585587","display_name":"Anning Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Anning","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134147080","display_name":"Ran Tao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao, Ran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134205727","display_name":"Ao Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Ao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134114455","display_name":"Xiangyu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xiangyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134100186","display_name":"Xiurui Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Xiurui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134137086","display_name":"Guisong Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Guisong","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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.4952000081539154,"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"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.4952000081539154,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0560000017285347,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.05460000038146973,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.670199990272522},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6517000198364258},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.6412000060081482},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.5533000230789185},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5310999751091003},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4578000009059906},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4343999922275543},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.42089998722076416},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.38589999079704285}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7218999862670898},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.670199990272522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6646999716758728},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6517000198364258},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.6412000060081482},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.5533000230789185},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5310999751091003},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4578000009059906},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4343999922275543},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.42089998722076416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40560001134872437},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.38589999079704285},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.3849000036716461},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3828999996185303},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.3677999973297119},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.367000013589859},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.32089999318122864},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.27140000462532043},{"id":"https://openalex.org/C41614226","wikidata":"https://www.wikidata.org/wiki/Q5449244","display_name":"Filtering problem","level":4,"score":0.2703000009059906},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.18284","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.18284","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.18284","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.18284","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":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.524370551109314}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Pre-trained":[0],"vision":[1,22],"models":[2],"have":[3,13],"found":[4],"widespread":[5],"application":[6],"across":[7],"diverse":[8],"domains.":[9],"Prompt":[10],"tuning-based":[11],"methods":[12],"emerged":[14],"as":[15,44,109],"a":[16,60,69,110,153],"parameter-efficient":[17],"paradigm":[18],"for":[19,183],"adapting":[20],"pre-trained":[21],"models.":[23,191],"While":[24],"effective":[25],"on":[26,74,120,165],"standard":[27],"benchmarks,":[28],"the":[29,45,79,114,121,128,169,176],"continuous":[30],"and":[31,89,124,161],"dense":[32],"nature":[33],"of":[34,156,171],"learned":[35],"prompts":[36,47,131],"can":[37],"lead":[38],"to":[39,49,83,116,179],"sensitivity":[40],"against":[41],"input":[42],"noise,":[43],"high-capacity":[46],"tend":[48],"overfit":[50],"task-irrelevant":[51],"details.":[52],"To":[53,168],"address":[54],"this":[55,174],"trade-off,":[56],"we":[57,67],"propose":[58],"Spike-NVPT,":[59],"noise-robust":[61],"visual":[62,190],"prompt":[63],"tuning":[64],"method.":[65],"Specifically,":[66],"design":[68],"Signal":[70],"Filtering":[71],"Layer":[72],"based":[73],"spiking":[75,181],"neurons,":[76],"which":[77],"uses":[78],"integrate-and-fire":[80],"(IF)":[81],"mechanism":[82],"accumulate":[84],"task-relevant":[85],"signals":[86,101],"over":[87,158],"time":[88],"filter":[90],"transient":[91],"noise":[92],"fluctuations.":[93],"A":[94],"subsequent":[95],"Spike":[96],"Discretization":[97],"Unit":[98],"converts":[99],"filtered":[100],"into":[102],"sparse":[103],"binary":[104,130],"prompts.":[105],"This":[106],"discretization":[107],"acts":[108],"strong":[111],"regularizer,":[112],"forcing":[113],"model":[115],"anchor":[117],"decision":[118],"boundaries":[119],"most":[122],"discriminative":[123],"robust":[125],"features.":[126],"Notably,":[127],"resulting":[129],"remain":[132],"static":[133],"during":[134,141],"deployment,":[135],"ensuring":[136],"zero":[137],"additional":[138],"computational":[139],"overhead":[140],"inference.":[142],"Experimental":[143],"results":[144],"demonstrate":[145],"that":[146],"Spike-NVPT":[147],"achieves":[148],"superior":[149],"robustness":[150],"performance,":[151],"with":[152],"maximum":[154],"improvement":[155],"11.2%":[157],"conventional":[159],"methods,":[160],"retains":[162],"competitive":[163],"accuracy":[164],"clean":[166],"datasets.":[167],"best":[170],"our":[172],"knowledge,":[173],"is":[175],"first":[177],"attempt":[178],"leverage":[180],"neurons":[182],"fine-tuning":[184],"traditional":[185],"artificial":[186],"neural":[187],"network":[188],"(ANN)-based":[189]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-22T00:00:00"}