{"id":"https://openalex.org/W4415537697","doi":"https://doi.org/10.1145/3746027.3755769","title":"TongGu-VL: Advancing Visual-Language Understanding in Chinese Classical Studies through Parameter Sensitivity-Guided Instruction Tuning","display_name":"TongGu-VL: Advancing Visual-Language Understanding in Chinese Classical Studies through Parameter Sensitivity-Guided Instruction Tuning","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537697","doi":"https://doi.org/10.1145/3746027.3755769"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755769","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102702850","display_name":"Jiahuan Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiahuan Cao","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100355764","display_name":"Yang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075367869","display_name":"Peirong Zhang","orcid":"https://orcid.org/0000-0002-1857-5473"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peirong Zhang","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010150576","display_name":"Yongxin Shi","orcid":"https://orcid.org/0009-0003-2650-1663"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongxin Shi","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114858729","display_name":"Kai Ding","orcid":"https://orcid.org/0000-0002-9371-0751"},"institutions":[{"id":"https://openalex.org/I4210089783","display_name":"Shanghai Medical Information Center","ror":"https://ror.org/007wz9933","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210089783"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Ding","raw_affiliation_strings":["INTSIG Information, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"INTSIG Information, Shanghai, China","institution_ids":["https://openalex.org/I4210089783"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080674767","display_name":"Lianwen Jin","orcid":"https://orcid.org/0000-0002-5456-0957"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianwen Jin","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102702850"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32314858,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11111","last_page":"11120"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9466999769210815,"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":0.9466999769210815,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9121999740600586,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6158000230789185},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.6118999719619751},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5604000091552734},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5598999857902527},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.3790999948978424},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.36730000376701355},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.35899999737739563},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.35760000348091125},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.34220001101493835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7556999921798706},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6158000230789185},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.6118999719619751},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5604000091552734},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5598999857902527},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4837000072002411},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C49777639","wikidata":"https://www.wikidata.org/wiki/Q5264354","display_name":"Design language","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3095000088214874},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3091999888420105},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C3018428822","wikidata":"https://www.wikidata.org/wiki/Q7850","display_name":"Chinese language","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C2777710495","wikidata":"https://www.wikidata.org/wiki/Q5527195","display_name":"Gateway (web page)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2583000063896179},{"id":"https://openalex.org/C94922259","wikidata":"https://www.wikidata.org/wiki/Q33215","display_name":"Constructed language","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2513999938964844},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755769","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W4385571927","https://openalex.org/W4389267014","https://openalex.org/W4402155831","https://openalex.org/W4402307586","https://openalex.org/W4402727764"],"related_works":[],"abstract_inverted_index":{"Chinese":[0,10],"Classical":[1],"Studies":[2],"(CCS)":[3],"is":[4],"a":[5,66,82,100,124,155],"pivotal":[6],"gateway":[7],"to":[8,26,40,56,87,135],"ancient":[9,13],"culture.":[11],"Spanning":[12],"texts,":[14],"illustrations,":[15],"paintings,":[16],"and":[17,29,173],"calligraphy,":[18],"CCS":[19,72,90,119,159],"presents":[20],"significant":[21],"challenges":[22],"for":[23,71],"non-specialists":[24],"due":[25],"its":[27,118],"language":[28,142],"visual":[30,53,138],"complexity.":[31],"While":[32],"Large":[33],"Language":[34],"Models":[35],"(LLMs)":[36],"have":[37],"been":[38],"explored":[39],"facilitate":[41],"CCS,":[42],"current":[43],"methods":[44],"primarily":[45],"focus":[46],"on":[47,154],"textual":[48],"analysis,":[49],"overlooking":[50],"the":[51],"rich":[52],"information":[54],"intrinsic":[55],"classical":[57],"materials.":[58],"To":[59],"bridge":[60],"this":[61],"gap,":[62],"we":[63,79,93,122],"propose":[64,94],"TongGu-VL,":[65],"pioneering":[67],"specialized":[68],"MLLM":[69],"designed":[70],"applications.":[73],"Our":[74,171],"contributions":[75],"are":[76],"threefold.":[77],"First,":[78],"construct":[80],"CCS358K,":[81],"comprehensive":[83],"multimodal":[84],"instruction":[85],"dataset":[86,174],"enhance":[88],"MLLMs'":[89,132],"capabilities.":[91],"Second,":[92],"Parameter":[95],"Sensitivity-Guided":[96],"Instruction":[97],"Tuning":[98],"(PSG-IT),":[99],"novel":[101],"method":[102],"that":[103,148,165],"mitigates":[104],"catastrophic":[105],"forgetting":[106],"without":[107],"data":[108],"replay.":[109],"It":[110],"effectively":[111],"preserves":[112],"TongGu-VL's":[113],"general":[114,163],"skills,":[115],"while":[116,161],"optimizing":[117],"performance.":[120],"Third,":[121],"design":[123],"Visual-Text":[125],"Early":[126],"Fusion":[127],"(VTEF)":[128],"module,":[129],"which":[130],"harnesses":[131],"modality":[133],"alignment":[134],"generate":[136],"instruction-aware":[137],"representations,":[139],"thus":[140],"improving":[141],"modeling.":[143],"Extensive":[144],"experimental":[145],"results":[146],"demonstrate":[147],"our":[149],"model":[150,172],"outperforms":[151],"existing":[152],"MLLMs":[153],"broad":[156],"range":[157],"of":[158],"tasks,":[160],"maintaining":[162],"capabilities":[164],"benefit":[166],"other":[167],"domains":[168],"beyond":[169],"CCS.":[170],"will":[175],"be":[176],"publicly":[177],"available.":[178]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-25T00:00:00"}