{"id":"https://openalex.org/W7125772065","doi":"https://doi.org/10.1145/3779153.3779172","title":"GNP-FILTER: Gradient-Norm Proxy-Based Data Selection for Visual Instruction Tuning in Vison Language Model","display_name":"GNP-FILTER: Gradient-Norm Proxy-Based Data Selection for Visual Instruction Tuning in Vison Language Model","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W7125772065","doi":"https://doi.org/10.1145/3779153.3779172"},"language":null,"primary_location":{"id":"doi:10.1145/3779153.3779172","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3779153.3779172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 9th International Conference on Big Data and Internet of Things","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/A5124031113","display_name":"Changjiu Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I145581781","display_name":"Chongqing Technology and Business University","ror":"https://ror.org/05hqf1284","country_code":"CN","type":"education","lineage":["https://openalex.org/I145581781"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Changjiu Jiang","raw_affiliation_strings":["The Artificial Intelligence College, Chongqing Key Laboratory of IntelliSense and Blockchain Technology, Chongqing Technology and Business University, Chongqing, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"The Artificial Intelligence College, Chongqing Key Laboratory of IntelliSense and Blockchain Technology, Chongqing Technology and Business University, Chongqing, Chongqing, China","institution_ids":["https://openalex.org/I145581781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123959548","display_name":"Bo Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I145581781","display_name":"Chongqing Technology and Business University","ror":"https://ror.org/05hqf1284","country_code":"CN","type":"education","lineage":["https://openalex.org/I145581781"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["The Artificial Intelligence College, Chongqing Key Laboratory of IntelliSense and Blockchain Technology, Chongqing Technology and Business University, Chongqing, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"The Artificial Intelligence College, Chongqing Key Laboratory of IntelliSense and Blockchain Technology, Chongqing Technology and Business University, Chongqing, Chongqing, China","institution_ids":["https://openalex.org/I145581781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124036299","display_name":"Jie Li","orcid":null},"institutions":[{"id":"https://openalex.org/I145581781","display_name":"Chongqing Technology and Business University","ror":"https://ror.org/05hqf1284","country_code":"CN","type":"education","lineage":["https://openalex.org/I145581781"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Li","raw_affiliation_strings":["The Artificial Intelligence College, Chongqing Key Laboratory of IntelliSense and Blockchain Technology, Chongqing Technology and Business University, Chongqing, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"The Artificial Intelligence College, Chongqing Key Laboratory of IntelliSense and Blockchain Technology, Chongqing Technology and Business University, Chongqing, Chongqing, China","institution_ids":["https://openalex.org/I145581781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124040717","display_name":"Jinrui Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I145581781","display_name":"Chongqing Technology and Business University","ror":"https://ror.org/05hqf1284","country_code":"CN","type":"education","lineage":["https://openalex.org/I145581781"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinrui Qian","raw_affiliation_strings":["The Artificial Intelligence College, Chongqing Key Laboratory of IntelliSense and Blockchain Technology, Chongqing Technology and Business University, Chongqing, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"The Artificial Intelligence College, Chongqing Key Laboratory of IntelliSense and Blockchain Technology, Chongqing Technology and Business University, Chongqing, Chongqing, China","institution_ids":["https://openalex.org/I145581781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123945418","display_name":"Run Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I145581781","display_name":"Chongqing Technology and Business University","ror":"https://ror.org/05hqf1284","country_code":"CN","type":"education","lineage":["https://openalex.org/I145581781"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Run Zeng","raw_affiliation_strings":["The Artificial Intelligence College, Chongqing Key Laboratory of IntelliSense and Blockchain Technology, Chongqing Technology and Business University, Chongqing, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"The Artificial Intelligence College, Chongqing Key Laboratory of IntelliSense and Blockchain Technology, Chongqing Technology and Business University, Chongqing, Chongqing, China","institution_ids":["https://openalex.org/I145581781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123910975","display_name":"Xin Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I145581781","display_name":"Chongqing Technology and Business University","ror":"https://ror.org/05hqf1284","country_code":"CN","type":"education","lineage":["https://openalex.org/I145581781"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Huang","raw_affiliation_strings":["The Artificial Intelligence College, Chongqing Key Laboratory of IntelliSense and Blockchain Technology, Chongqing Technology and Business University, Chongqing, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"The Artificial Intelligence College, Chongqing Key Laboratory of IntelliSense and Blockchain Technology, Chongqing Technology and Business University, Chongqing, Chongqing, China","institution_ids":["https://openalex.org/I145581781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5124031113"],"corresponding_institution_ids":["https://openalex.org/I145581781"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.71384349,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"124","last_page":"129"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9502000212669373,"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":0.9502000212669373,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.011300000362098217,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.010999999940395355,"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/task","display_name":"Task (project management)","score":0.7106000185012817},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6396999955177307},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5892999768257141},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5385000109672546},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4553999900817871},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.44760000705718994},{"id":"https://openalex.org/keywords/model-selection","display_name":"Model selection","score":0.41819998621940613},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.37389999628067017}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7940999865531921},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7106000185012817},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6812000274658203},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6396999955177307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6205999851226807},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5892999768257141},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5385000109672546},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4553999900817871},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.44760000705718994},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.41819998621940613},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3790000081062317},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.37389999628067017},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3564999997615814},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3555000126361847},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.2870999872684479},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C40423286","wikidata":"https://www.wikidata.org/wiki/Q284172","display_name":"Selection bias","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3779153.3779172","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3779153.3779172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 9th International Conference on Big Data and Internet of Things","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W3153469116","https://openalex.org/W4389523832","https://openalex.org/W4402670838","https://openalex.org/W4404356490","https://openalex.org/W4415538849"],"related_works":[],"abstract_inverted_index":{"In":[0],"the":[1,36,52,99,103,109,122,158],"context":[2],"of":[3,40,102,157],"instruction":[4],"tuning":[5],"for":[6,19],"multi-task":[7],"Vision-Language":[8],"Models":[9],"(VLMs),":[10],"data":[11,77],"selection":[12,78,115,128],"has":[13],"emerged":[14],"as":[15],"a":[16,87,93],"critical":[17],"strategy":[18],"improving":[20],"training":[21,100,159,166],"efficiency.":[22],"However,":[23],"existing":[24],"approaches":[25],"encounter":[26],"two":[27],"key":[28],"challenges":[29],"when":[30],"applied":[31],"to":[32,56,97,131],"large-scale":[33],"datasets:":[34],"(1)":[35],"high":[37],"computational":[38,110],"cost":[39],"scoring":[41],"each":[42],"individual":[43],"sample,":[44],"which":[45],"hinders":[46],"scalability;":[47],"(2)":[48],"task":[49,58,114,135,169],"bias":[50],"in":[51,164],"selected":[53],"data,":[54,160],"leading":[55],"uneven":[57],"distribution":[59],"and":[60,75,91,125,134],"suboptimal":[61],"performance":[62],"on":[63,86,139],"underrepresented":[64],"tasks.":[65],"To":[66,112],"address":[67],"these":[68],"issues,":[69],"we":[70,117],"propose":[71],"GNP-FILTER,":[72],"an":[73],"efficient":[74],"task-aware":[76],"framework.":[79],"Specifically,":[80],"our":[81],"approach":[82],"computes":[83],"gradient":[84],"norms":[85],"small":[88],"representative":[89],"subset":[90],"trains":[92],"score":[94],"prediction":[95],"model":[96],"estimate":[98],"utility":[101],"remaining":[104],"samples,":[105],"thus":[106],"significantly":[107],"reducing":[108],"burden.":[111],"mitigate":[113],"bias,":[116],"perform":[118],"feature-based":[119],"clustering":[120],"over":[121],"entire":[123],"dataset":[124],"guide":[126],"sample":[127],"within":[129],"clusters":[130],"ensure":[132],"semantic":[133],"diversity.":[136],"Extensive":[137],"experiments":[138],"standard":[140],"vision-language":[141],"benchmarks":[142],"demonstrate":[143],"that":[144],"GNP-FILTER":[145],"can":[146],"match":[147],"or":[148],"even":[149],"outperform":[150],"full-data":[151],"fine-tuning":[152],"while":[153],"using":[154],"only":[155],"20%":[156],"demonstrating":[161],"its":[162],"effectiveness":[163],"balancing":[165],"efficiency":[167],"with":[168],"coverage.":[170]},"counts_by_year":[],"updated_date":"2026-01-28T23:18:48.515280","created_date":"2026-01-28T00:00:00"}