{"id":"https://openalex.org/W4404781290","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.827","title":"Query-based Cross-Modal Projector Bolstering Mamba Multimodal LLM","display_name":"Query-based Cross-Modal Projector Bolstering Mamba Multimodal LLM","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404781290","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.827"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.findings-emnlp.827","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.findings-emnlp.827","pdf_url":"https://aclanthology.org/2024.findings-emnlp.827.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2024","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.findings-emnlp.827.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112980303","display_name":"SooHwan Eom","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"SooHwan Eom","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114847421","display_name":"Jay Shim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jay Shim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114847422","display_name":"Gwanhyeong Koo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gwanhyeong Koo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114847423","display_name":"Haebin Na","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haebin Na","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark A. Hasegawa-Johnson","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087294413","display_name":"Sungwoong Kim","orcid":"https://orcid.org/0000-0002-2676-9454"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sungwoong Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5073287748","display_name":"Chang D. Yoo","orcid":"https://orcid.org/0000-0002-0756-7179"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chang D. Yoo","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":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14158","last_page":"14167"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.6269999742507935,"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/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.6269999742507935,"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/modal","display_name":"Modal","score":0.6694842576980591},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.639874279499054},{"id":"https://openalex.org/keywords/projector","display_name":"Projector","score":0.5056712627410889},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22429361939430237},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.0682324469089508}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6694842576980591},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.639874279499054},{"id":"https://openalex.org/C2776865275","wikidata":"https://www.wikidata.org/wiki/Q311666","display_name":"Projector","level":2,"score":0.5056712627410889},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22429361939430237},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0682324469089508},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2024.findings-emnlp.827","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.findings-emnlp.827","pdf_url":"https://aclanthology.org/2024.findings-emnlp.827.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2606.04719","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.04719","pdf_url":"https://arxiv.org/pdf/2606.04719","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2606.04719","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04719","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-emnlp.827","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.findings-emnlp.827","pdf_url":"https://aclanthology.org/2024.findings-emnlp.827.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4099999964237213}],"awards":[{"id":"https://openalex.org/G4805667441","display_name":null,"funder_award_id":"UD230017TD","funder_id":"https://openalex.org/F4320334874","funder_display_name":"Defense Acquisition Program Administration"},{"id":"https://openalex.org/G6969530878","display_name":null,"funder_award_id":"RS-2019-II190079","funder_id":"https://openalex.org/F4320321373","funder_display_name":"Korea University"},{"id":"https://openalex.org/G8458676037","display_name":null,"funder_award_id":"RS-2019-II190079","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G960095468","display_name":null,"funder_award_id":"RS-2019-II190079","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320321373","display_name":"Korea University","ror":"https://ror.org/047dqcg40"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320334874","display_name":"Defense Acquisition Program Administration","ror":"https://ror.org/04bjg9m96"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404781290.pdf","grobid_xml":"https://content.openalex.org/works/W4404781290.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2366989203","https://openalex.org/W2013995543","https://openalex.org/W2547954852","https://openalex.org/W2800812882","https://openalex.org/W3198360760","https://openalex.org/W2388454722","https://openalex.org/W4388488814"],"abstract_inverted_index":{"The":[0],"Transformer's":[1],"quadratic":[2],"complexity":[3],"with":[4],"input":[5,51,78],"length":[6],"imposes":[7],"an":[8,77],"unsustainable":[9],"computational":[10,28],"load":[11],"on":[12,50],"large":[13],"language":[14],"models":[15],"(LLMs).In":[16],"contrast,":[17],"the":[18,53,60,65,91],"Selective":[19],"Scan":[20],"Structured":[21],"State-Space":[22],"Model,":[23],"or":[24],"Mamba,":[25],"addresses":[26],"this":[27],"challenge":[29],"effectively.This":[30],"paper":[31],"explores":[32],"a":[33],"query-based":[34],"cross-modal":[35,93],"projector":[36,57,94],"designed":[37],"to":[38],"bolster":[39],"Mamba's":[40],"efficiency":[41],"for":[42,62,80],"visionlanguage":[43],"modeling":[44],"by":[45],"compressing":[46],"visual":[47],"tokens":[48],"based":[49],"through":[52],"cross-attention":[54],"mechanism.This":[55],"innovative":[56],"also":[58],"removes":[59],"need":[61],"manually":[63],"designing":[64],"2D":[66],"scan":[67],"order":[68],"of":[69],"original":[70],"image":[71],"features":[72],"when":[73],"converting":[74],"them":[75],"into":[76],"sequence":[79],"Mamba":[81],"LLM.Experimental":[82],"results":[83],"across":[84],"various":[85],"vision-language":[86],"understanding":[87],"benchmarks":[88],"show":[89],"that":[90],"proposed":[92],"enhances":[95],"Mamba-based":[96],"multimodal":[97],"LLMs,":[98],"boosting":[99],"both":[100],"performance":[101],"and":[102],"throughput.":[103]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
