{"id":"https://openalex.org/W4415536407","doi":"https://doi.org/10.1145/3746027.3755003","title":"Deciphering Functions of Neurons in Vision-Language Models","display_name":"Deciphering Functions of Neurons in Vision-Language Models","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536407","doi":"https://doi.org/10.1145/3746027.3755003"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755003","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755003","pdf_url":null,"source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755003","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jiaqi Xu","orcid":"https://orcid.org/0009-0005-4081-736X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqi Xu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0005-4081-736X","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051469345","display_name":"Cuiling Lan","orcid":"https://orcid.org/0000-0001-9145-9957"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cuiling Lan","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9145-9957","affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100756584","display_name":"Yan Lu","orcid":"https://orcid.org/0000-0001-5383-6424"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Lu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5383-6424","affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.324232,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3173","last_page":"3181"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9916999936103821,"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":0.9916999936103821,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9847999811172485,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9675999879837036,"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/interpretability","display_name":"Interpretability","score":0.9262999892234802},{"id":"https://openalex.org/keywords/transparency","display_name":"Transparency (behavior)","score":0.6273999810218811},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.5845999717712402},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4970000088214874},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4722999930381775},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.376800000667572}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9262999892234802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6779000163078308},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.6273999810218811},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.5845999717712402},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4970000088214874},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4722999930381775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46070000529289246},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.376800000667572},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.3127000033855438},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.304500013589859},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2928999960422516},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.2856999933719635},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27410000562667847},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755003","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755003","pdf_url":null,"source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3755003","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755003","pdf_url":null,"source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W2963749936"],"related_works":[],"abstract_inverted_index":{"The":[0],"burgeoning":[1],"growth":[2],"of":[3,12,22,45,51,58,114,119,134,145,149,154,157],"open-source":[4],"vision-language":[5],"models":[6,24],"(VLMs)":[7],"has":[8],"catalyzed":[9],"a":[10,108],"plethora":[11],"applications":[13],"across":[14],"diverse":[15],"domains.":[16],"Ensuring":[17],"the":[18,43,49,56,63,112,117,132,135,152],"transparency":[19],"and":[20,30,67,70,102],"interpretability":[21],"these":[23],"is":[25,39],"critical":[26],"for":[27,83,122,137],"fostering":[28],"trustworthy":[29],"responsible":[31,82],"AI":[32],"systems.":[33],"In":[34],"this":[35],"study,":[36],"our":[37],"objective":[38],"to":[40,47,62,95,130],"delve":[41],"into":[42],"internals":[44],"VLMs":[46],"interpret":[48],"functions":[50],"individual":[52],"neurons.":[53,139,158],"We":[54,106],"observe":[55],"activations":[57],"neurons":[59,81,115],"with":[60,116],"respects":[61],"input":[64],"visual":[65,85,98,123,138],"tokens":[66],"text":[68,87,100],"tokens,":[69],"reveal":[71],"some":[72],"interesting":[73],"findings.":[74],"Particularly,":[75],"we":[76,93,125],"found":[77],"that":[78,110],"there":[79],"are":[80],"only":[84],"or":[86,89],"information,":[88],"both,":[90],"respectively,":[91],"which":[92],"refer":[94],"them":[96],"as":[97],"neurons,":[99,101,104,124],"multi-modal":[103],"respectively.":[105],"build":[107],"framework":[109],"automates":[111],"explanation":[113],"assistant":[118],"GPT-4o.":[120],"Meanwhile,":[121],"propose":[126],"an":[127],"activation":[128],"simulator":[129],"assess":[131],"reliability":[133],"explanations":[136],"System":[140],"statistical":[141],"analyses":[142],"on":[143],"top":[144],"one":[146],"representative":[147],"VLM":[148],"LLaVA,":[150],"uncover":[151],"behaviors/characteristics":[153],"different":[155],"categories":[156]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-25T00:00:00"}