{"id":"https://openalex.org/W7166851294","doi":"https://doi.org/10.18653/v1/2026.acl-long.1622","title":"KG-ViP: Bridging Knowledge Grounding and Visual Perception in Multi-modal LLMs for Visual Question Answering","display_name":"KG-ViP: Bridging Knowledge Grounding and Visual Perception in Multi-modal LLMs for Visual Question Answering","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166851294","doi":"https://doi.org/10.18653/v1/2026.acl-long.1622"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1622","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1622","pdf_url":"https://aclanthology.org/2026.acl-long.1622.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.1622.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139764471","display_name":"Zhiyang Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyang Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139787038","display_name":"Ao Ke","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ao Ke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139726095","display_name":"Yukun Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yukun Cao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5037366245","display_name":"Xike Xie","orcid":"https://orcid.org/0000-0001-5290-5408"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xike Xie","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8730683,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"35144","last_page":"35157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9950000047683716,"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":0.9950000047683716,"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/T10028","display_name":"Topic Modeling","score":0.0010000000474974513,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.0006000000284984708,"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/bridging","display_name":"Bridging (networking)","score":0.6790000200271606},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5921000242233276},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5419999957084656},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.36090001463890076},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.2815999984741211}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6790000200271606},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5921000242233276},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5419999957084656},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.47200000286102295},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3921999931335449},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.36090001463890076},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.3492000102996826},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2976999878883362},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.2687999904155731},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.265500009059906},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26019999384880066}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1622","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1622","pdf_url":"https://aclanthology.org/2026.acl-long.1622.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1622","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1622","pdf_url":"https://aclanthology.org/2026.acl-long.1622.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3350212987","display_name":null,"funder_award_id":"62472400","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G378631614","display_name":null,"funder_award_id":"SYG202338","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5837042690","display_name":null,"funder_award_id":"2025YFC3408300","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7571408944","display_name":null,"funder_award_id":"62271465","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166851294.pdf","grobid_xml":"https://content.openalex.org/works/W7166851294.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multi-modal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"for":[5],"Visual":[6],"Question":[7],"Answering":[8],"(VQA)":[9],"often":[10],"suffer":[11],"from":[12],"dual":[13],"limitations:":[14],"knowledge":[15,42],"hallucination":[16],"and":[17,27,43,75,115],"insufficient":[18],"fine-grained":[19,45],"visual":[20,46],"perception.Crucially,":[21],"we":[22,62],"identify":[23],"that":[24,68,88,106,119],"commonsense":[25,76],"graphs":[26,29,74],"scene":[28,73],"provide":[30],"precisely":[31],"complementary":[32],"solutions":[33],"to":[34,96],"these":[35],"respective":[36],"deficiencies":[37],"by":[38,71],"providing":[39],"rich":[40],"external":[41],"capturing":[44],"details.However,":[47],"prior":[48],"works":[49],"typically":[50],"treat":[51],"them":[52],"in":[53],"isolation,":[54],"overlooking":[55],"their":[56],"synergistic":[57],"potential.To":[58],"bridge":[59,95],"this":[60],"gap,":[61],"propose":[63],"KG-ViP,":[64],"a":[65,84,93,102],"unified":[66,103],"framework":[67,82],"empowers":[69],"MLLMs":[70],"fusing":[72],"graphs.The":[77],"core":[78],"of":[79],"the":[80,90],"KG-ViP":[81,120],"is":[83],"novel":[85],"retrieval-and-fusion":[86],"pipeline":[87],"utilizes":[89],"query":[91],"as":[92],"semantic":[94],"progressively":[97],"integrate":[98],"both":[99],"graphs,":[100],"synthesizing":[101],"structured":[104],"context":[105],"facilitates":[107],"reliable":[108],"multi-modal":[109],"reasoning.Extensive":[110],"experiments":[111],"on":[112],"FVQA":[113],"2.0+":[114],"MVQA":[116],"benchmarks":[117],"demonstrate":[118],"significantly":[121],"outperforms":[122],"existing":[123],"VQA":[124],"methods.":[125]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}