{"id":"https://openalex.org/W4412888645","doi":"https://doi.org/10.18653/v1/2025.findings-acl.327","title":"Advancing General Multimodal Capability of Vision-language Models with Pyramid-descent Visual Position Encoding","display_name":"Advancing General Multimodal Capability of Vision-language Models with Pyramid-descent Visual Position Encoding","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888645","doi":"https://doi.org/10.18653/v1/2025.findings-acl.327"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.327","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.327","pdf_url":"https://aclanthology.org/2025.findings-acl.327.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: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.327.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020472862","display_name":"Z. J. Chen","orcid":"https://orcid.org/0009-0004-5840-2114"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhanpeng Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073657384","display_name":"Mingxiao Li","orcid":"https://orcid.org/0000-0002-7055-0281"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingxiao Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100324483","display_name":"Ziyang Chen","orcid":"https://orcid.org/0000-0002-2467-8372"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyang Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100721786","display_name":"Nan Du","orcid":"https://orcid.org/0000-0002-5226-2980"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nan Du","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100371551","display_name":"Xiaolong Li","orcid":"https://orcid.org/0000-0002-7467-2550"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaolong Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5034401157","display_name":"Yuexian Zou","orcid":"https://orcid.org/0000-0002-0144-1794"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuexian Zou","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":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6324","last_page":"6341"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9312999844551086,"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":0.9312999844551086,"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/T12031","display_name":"Speech and dialogue systems","score":0.917900025844574,"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/encoding","display_name":"Encoding (memory)","score":0.7648272514343262},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7409287095069885},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.7024279832839966},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.5659489631652832},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5348146557807922},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5342280864715576},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33782386779785156},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09197342395782471}],"concepts":[{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.7648272514343262},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7409287095069885},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.7024279832839966},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5659489631652832},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5348146557807922},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5342280864715576},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33782386779785156},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09197342395782471},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.327","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.327","pdf_url":"https://aclanthology.org/2025.findings-acl.327.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: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.327","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.327","pdf_url":"https://aclanthology.org/2025.findings-acl.327.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: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888645.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4249847449","https://openalex.org/W44395729","https://openalex.org/W2765338038","https://openalex.org/W1496225612","https://openalex.org/W1523500768","https://openalex.org/W1566843515","https://openalex.org/W4292850564","https://openalex.org/W2181660907","https://openalex.org/W4235381733","https://openalex.org/W4386191828"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
