{"id":"https://openalex.org/W4412889707","doi":"https://doi.org/10.18653/v1/2025.acl-long.1482","title":"Benchmarking and Improving Large Vision-Language Models for Fundamental Visual Graph Understanding and Reasoning","display_name":"Benchmarking and Improving Large Vision-Language Models for Fundamental Visual Graph Understanding and Reasoning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889707","doi":"https://doi.org/10.18653/v1/2025.acl-long.1482"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.1482","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1482","pdf_url":"https://aclanthology.org/2025.acl-long.1482.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 63rd 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/2025.acl-long.1482.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yingjie Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingjie Zhu","raw_affiliation_strings":["Institute of Computing and Intelligence , Harbin Institute of Technology , Shenzhen , China","Peng Cheng Laboratory , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing and Intelligence , Harbin Institute of Technology , Shenzhen , China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Peng Cheng Laboratory , Shenzhen , China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101905617","display_name":"Xuefeng Bai","orcid":"https://orcid.org/0000-0001-7044-0683"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuefeng Bai","raw_affiliation_strings":["Institute of Computing and Intelligence , Harbin Institute of Technology , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing and Intelligence , Harbin Institute of Technology , Shenzhen , China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006323375","display_name":"Kehai Chen","orcid":"https://orcid.org/0000-0002-4346-7618"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kehai Chen","raw_affiliation_strings":["Institute of Computing and Intelligence , Harbin Institute of Technology , Shenzhen , China","Peng Cheng Laboratory , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing and Intelligence , Harbin Institute of Technology , Shenzhen , China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Peng Cheng Laboratory , Shenzhen , China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082981111","display_name":"Yang Xiang","orcid":"https://orcid.org/0000-0002-7865-2565"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Xiang","raw_affiliation_strings":["Peng Cheng Laboratory , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory , Shenzhen , China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050817770","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0003-1922-7283"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yu","raw_affiliation_strings":["School of Intelligence Science and Engineering , Harbin Institute of Technology , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Intelligence Science and Engineering , Harbin Institute of Technology , Shenzhen , China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052195927","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0001-5812-9518"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Zhang","raw_affiliation_strings":["Institute of Computing and Intelligence , Harbin Institute of Technology , Shenzhen , China","Peng Cheng Laboratory , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing and Intelligence , Harbin Institute of Technology , Shenzhen , China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Peng Cheng Laboratory , Shenzhen , China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5435,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93251084,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"30678","last_page":"30701"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9861000180244446,"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":0.9861000180244446,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9617000222206116,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.9226999878883362,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/benchmarking","display_name":"Benchmarking","score":0.7990434169769287},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7289612293243408},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5168074369430542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4502227008342743},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.4238974452018738},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3426933288574219},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2470371425151825},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09855258464813232}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7990434169769287},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7289612293243408},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5168074369430542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4502227008342743},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.4238974452018738},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3426933288574219},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2470371425151825},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09855258464813232},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.1482","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1482","pdf_url":"https://aclanthology.org/2025.acl-long.1482.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.1482","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1482","pdf_url":"https://aclanthology.org/2025.acl-long.1482.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1289754401","display_name":null,"funder_award_id":"U24A20328","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3537643952","display_name":null,"funder_award_id":"62350710797","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6570941292","display_name":null,"funder_award_id":"62125201","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7320519987","display_name":null,"funder_award_id":"62276077","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/W4412889707.pdf","grobid_xml":"https://content.openalex.org/works/W4412889707.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2000169967","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Large":[0],"Vision-Language":[1],"Models":[2],"(LVLMs)":[3],"have":[4],"demonstrated":[5],"remarkable":[6],"performance":[7,107],"across":[8],"diverse":[9],"tasks.Despite":[10],"great":[11],"success,":[12],"recent":[13],"studies":[14],"show":[15],"that":[16,58],"LVLMs":[17,56,59,88],"encounter":[18],"substantial":[19],"limitations":[20],"when":[21],"engaging":[22],"with":[23,89],"visual":[24,123],"graphs.To":[25],"study":[26],"the":[27,43,99],"reason":[28],"behind":[29],"these":[30],"limitations,":[31],"we":[32,80],"propose":[33,81],"VGCURE,":[34],"a":[35,82],"comprehensive":[36],"benchmark":[37],"covering":[38],"22":[39],"tasks":[40],"for":[41],"examining":[42],"fundamental":[44,109],"graph":[45,64,112],"understanding":[46,65],"and":[47,66,110],"reasoning":[48,67],"capacities":[49],"of":[50,101],"LVLMs.Extensive":[51],"evaluations":[52],"conducted":[53],"on":[54,77,108],"14":[55],"reveal":[57],"are":[60],"weak":[61],"in":[62,104],"basic":[63],"tasks,":[68,114],"particularly":[69],"those":[70],"concerning":[71],"relational":[72],"or":[73],"structurally":[74],"complex":[75,122],"information.Based":[76],"this":[78],"observation,":[79],"structure-aware":[83],"fine-tuning":[84],"framework":[85],"to":[86],"enhance":[87],"structure":[90],"learning":[91,96,113],"abilities":[92],"through":[93],"three":[94],"self-supervised":[95],"tasks.Experiments":[97],"validate":[98],"effectiveness":[100],"our":[102],"method":[103],"improving":[105],"LVLMs'":[106],"downstream":[111],"as":[115,117],"well":[116],"enhancing":[118],"their":[119],"robustness":[120],"against":[121],"graphs.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
