{"id":"https://openalex.org/W7214913076","doi":"https://doi.org/10.48550/arxiv.2609.38098","title":"NeuronEye: Query-Guided Visual Concept Activation for Vision-Language Reasoning","display_name":"NeuronEye: Query-Guided Visual Concept Activation for Vision-Language Reasoning","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214913076","doi":"https://doi.org/10.48550/arxiv.2609.38098"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.38098","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.38098","pdf_url":"https://arxiv.org/pdf/2609.38098","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.38098","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112999203","display_name":"Ruiyu Yan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan, Ruiyu","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153662702","display_name":"Bowen Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, Bowen","raw_affiliation_strings":["New Jersey Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040827184","display_name":"Shaowen Wan","orcid":"https://orcid.org/0009-0009-0551-3052","observed_orcids":["https://orcid.org/0009-0009-0551-3052"]},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wan, Shaowen","raw_affiliation_strings":["New Jersey Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153588232","display_name":"Lin Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhao, Lin","raw_affiliation_strings":["New Jersey Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology","institution_ids":["https://openalex.org/I118118575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0,"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/vision-language-models","display_name":"vision-language models","score":0.8140000104904175},{"id":"https://openalex.org/keywords/top-down-modulation","display_name":"top-down modulation","score":0.6480000019073486},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"visual reasoning","score":0.5120000243186951},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.7820000052452087}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.91839998960495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7031999826431274},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.6908000111579895},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.635200023651123},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6157000064849854},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6057000160217285},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5659000277519226},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5554999709129333},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5532000064849854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5529000163078308},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5070000290870667},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.48420000076293945},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.47029998898506165},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.46309998631477356},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.40950000286102295},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3986999988555908},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.3774000108242035},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.3603000044822693},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3343999981880188},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C2776010242","wikidata":"https://www.wikidata.org/wiki/Q4677575","display_name":"Active perception","level":3,"score":0.2872999906539917},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.28119999170303345},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26190000772476196},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2606000006198883},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25529998540878296},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.25189998745918274}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.38098","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.38098","pdf_url":"https://arxiv.org/pdf/2609.38098","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.38098","doi":"https://doi.org/10.48550/arxiv.2609.38098","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.38098","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.38098","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.38098","pdf_url":"https://arxiv.org/pdf/2609.38098","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214913076.pdf","grobid_xml":"https://content.openalex.org/works/W7214913076.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W4392678661","https://openalex.org/W4402698743","https://openalex.org/W4403370767","https://openalex.org/W4404570200","https://openalex.org/W4407794264","https://openalex.org/W4415085804","https://openalex.org/W4416053382"],"related_works":["https://openalex.org/W4415536407","https://openalex.org/W7165666335","https://openalex.org/W4402618835","https://openalex.org/W7162403736","https://openalex.org/W4417012255","https://openalex.org/W7153289478","https://openalex.org/W7127737099","https://openalex.org/W7117671263","https://openalex.org/W7168255808","https://openalex.org/W7221358595"],"abstract_inverted_index":{"Current":[0],"vision-language":[1],"models":[2],"(VLMs)":[3],"encode":[4],"visual":[5,35,75,193],"information":[6],"in":[7,51,135],"dense":[8],"hidden":[9],"states":[10,82],"where":[11,104],"object":[12],"identity,":[13],"spatial":[14],"layout,":[15],"and":[16,31,48,71,100,109,160],"local":[17],"attributes":[18],"are":[19,107],"implicitly":[20],"entangled":[21],"rather":[22],"than":[23],"explicitly":[24],"disentangled,":[25],"limiting":[26],"their":[27],"ability":[28],"to":[29,96,126],"isolate":[30],"modulate":[32],"the":[33,93,102,111],"specific":[34],"evidence":[36,113],"required":[37],"by":[38,44,89,152,164],"a":[39,57,62,136,141],"given":[40],"language":[41,94],"query.":[42],"Inspired":[43],"sparse":[45,86,175],"population":[46],"coding":[47],"top-down":[49],"modulation":[50],"biological":[52],"vision,":[53],"we":[54],"introduce":[55],"NeuronEye,":[56],"plug-in":[58],"framework":[59],"that":[60,174],"constructs":[61],"sparse,":[63],"concept-level":[64,90,192],"neuron":[65,176],"vocabulary":[66],"from":[67],"intermediate":[68],"VLM":[69,143],"representations":[70],"selectively":[72],"activates":[73],"query-relevant":[74],"concepts":[76,106],"during":[77],"inference.":[78],"NeuronEye":[79,147],"decomposes":[80],"vision-token":[81],"into":[83,115],"an":[84],"overcomplete":[85],"basis":[87],"organized":[88],"clusters,":[91],"uses":[92],"query":[95],"activate":[97],"relevant":[98,130],"clusters":[99],"localize":[101],"patches":[103],"selected":[105],"expressed,":[108],"injects":[110],"focused":[112],"back":[114],"vision":[116],"tokens.":[117],"A":[118],"complementary":[119],"suppression":[120],"mechanism":[121],"attenuates":[122],"dominant":[123],"perceptual":[124],"directions":[125],"preserve":[127],"weaker":[128],"but":[129,186],"cues.":[131],"All":[132],"operations":[133],"run":[134],"single":[137],"forward":[138],"pass":[139],"over":[140],"frozen":[142],"backbone.":[144],"On":[145],"Qwen2.5-VL-7B,":[146],"raises":[148],"CV-Bench":[149],"overall":[150],"accuracy":[151],"+3.1":[153],"with":[154,166],"gains":[155],"of":[156],"+9.5":[157],"on":[158,169],"Distance,":[159],"improves":[161],"BLINK":[162],"Multi-view":[163],"+8.3,":[165],"similar":[167],"trends":[168],"LLaVA-1.6-7B.":[170],"These":[171],"results":[172],"suggest":[173],"vocabularies":[177],"can":[178],"serve":[179],"not":[180],"only":[181],"as":[182,188],"post-hoc":[183],"interpretability":[184],"tools":[185],"also":[187],"active":[189],"interfaces":[190],"for":[191],"reasoning.":[194]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-01T00:00:00"}