{"id":"https://openalex.org/W7118014316","doi":"https://doi.org/10.1145/3765766.3765832","title":"HART-Pruner: A Human-Aligned Token Reduction Method for Interpretable and Efficient Vision-Language Inference","display_name":"HART-Pruner: A Human-Aligned Token Reduction Method for Interpretable and Efficient Vision-Language Inference","publication_year":2025,"publication_date":"2025-11-10","ids":{"openalex":"https://openalex.org/W7118014316","doi":"https://doi.org/10.1145/3765766.3765832"},"language":null,"primary_location":{"id":"doi:10.1145/3765766.3765832","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3765766.3765832","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Human-Agent Interaction","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3765766.3765832","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103740597","display_name":"Miho Takahashi","orcid":null},"institutions":[{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Miho Takahashi","raw_affiliation_strings":["Software Innovation Center, NTT, Inc., Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0009-3995-4542","affiliations":[{"raw_affiliation_string":"Software Innovation Center, NTT, Inc., Tokyo, Japan","institution_ids":["https://openalex.org/I2801547476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121816045","display_name":"Rintaro Harada","orcid":null},"institutions":[{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Rintaro Harada","raw_affiliation_strings":["Software Innovation Center, NTT, Inc., Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-5635-7936","affiliations":[{"raw_affiliation_string":"Software Innovation Center, NTT, Inc., Tokyo, Japan","institution_ids":["https://openalex.org/I2801547476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032808695","display_name":"Akiko Masaki-Kato","orcid":"https://orcid.org/0000-0003-0234-3552"},"institutions":[{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akiko Masaki-Kato","raw_affiliation_strings":["Software Innovation Center, NTT, Inc., Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-0234-3552","affiliations":[{"raw_affiliation_string":"Software Innovation Center, NTT, Inc., Tokyo, Japan","institution_ids":["https://openalex.org/I2801547476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019776988","display_name":"Takeharu Eda","orcid":null},"institutions":[{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeharu Eda","raw_affiliation_strings":["Software Innovation Center, NTT, Inc., Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0000-9814-5475","affiliations":[{"raw_affiliation_string":"Software Innovation Center, NTT, Inc., Tokyo, Japan","institution_ids":["https://openalex.org/I2801547476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103740597"],"corresponding_institution_ids":["https://openalex.org/I2801547476"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.64063717,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"458","last_page":"460"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8147000074386597,"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":0.8147000074386597,"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":0.031199999153614044,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.025200000032782555,"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":0.9039999842643738},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6037999987602234},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5885999798774719},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5264999866485596},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.474700003862381},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.40799999237060547}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9039999842643738},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7785999774932861},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6559000015258789},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6037999987602234},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5885999798774719},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5264999866485596},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.476500004529953},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.474700003862381},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.40799999237060547},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3192000091075897},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26600000262260437}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3765766.3765832","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3765766.3765832","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Human-Agent Interaction","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3765766.3765832","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3765766.3765832","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Human-Agent Interaction","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.40463632345199585}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2425121537","https://openalex.org/W2765716052","https://openalex.org/W4402716047"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2],"Multimodal":[3],"Large":[4],"Language":[5],"Models":[6],"(MLLMs)":[7],"enable":[8],"complex":[9],"vision-language":[10],"inference.":[11],"However,":[12],"visual":[13],"inputs":[14],"like":[15],"images":[16],"and":[17,27,42],"videos":[18],"consume":[19],"far":[20],"more":[21],"tokens":[22],"than":[23],"text,":[24],"increasing":[25],"computation":[26],"memory":[28],"costs.":[29],"Existing":[30],"token":[31],"pruning":[32],"methods":[33],"often":[34],"rely":[35],"on":[36],"attention":[37],"scores,":[38],"which":[39],"lack":[40],"interpretability":[41],"user":[43],"control,":[44],"sometimes":[45],"harming":[46],"performance.":[47]},"counts_by_year":[],"updated_date":"2026-01-03T23:08:47.215875","created_date":"2026-01-02T00:00:00"}
