{"id":"https://openalex.org/W4416034738","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.547","title":"ViFT: Towards Visual Instruction-Free Fine-tuning for Large Vision-Language Models","display_name":"ViFT: Towards Visual Instruction-Free Fine-tuning for Large Vision-Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034738","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.547"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.547","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.547","pdf_url":"https://aclanthology.org/2025.findings-emnlp.547.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: EMNLP 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-emnlp.547.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119269640","display_name":"Zikang Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zikang Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Kun Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031973958","display_name":"Xin Zhao","orcid":"https://orcid.org/0000-0001-6071-4433"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028318254","display_name":"Dawei Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dawei Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046576694","display_name":"Yaliang Li","orcid":"https://orcid.org/0000-0002-4204-6096"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaliang Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5025631695","display_name":"Ji-Rong Wen","orcid":"https://orcid.org/0000-0002-9777-9676"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji-Rong Wen","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":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10341","last_page":"10366"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.95169997215271,"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":0.95169997215271,"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":0.008299999870359898,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.005400000140070915,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.2946000099182129},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.28859999775886536},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.26969999074935913},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2685999870300293},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.2329999953508377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5076000094413757},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3926999866962433},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33649998903274536},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2329999953508377},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.225600004196167},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.22470000386238098}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.547","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.547","pdf_url":"https://aclanthology.org/2025.findings-emnlp.547.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.547","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.547","pdf_url":"https://aclanthology.org/2025.findings-emnlp.547.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G132187983","display_name":null,"funder_award_id":"62222215","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1899978318","display_name":null,"funder_award_id":"L233008","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/W4416034738.pdf","grobid_xml":"https://content.openalex.org/works/W4416034738.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Visual":[0],"instruction":[1],"tuning":[2],"has":[3],"become":[4],"the":[5,10,19,27,32,36,40,69,81,92,95,102],"predominant":[6],"technology":[7],"in":[8,34],"eliciting":[9],"multimodal":[11,107],"task-solving":[12,37,82],"capabilities":[13,38],"of":[14,94],"large":[15],"visionlanguage":[16],"models":[17],"(LVLMs).Despite":[18],"success,":[20],"as":[21,26],"visual":[22,59,84],"instructions":[23,71],"require":[24,68],"images":[25],"input,":[28],"it":[29,45],"would":[30],"leave":[31],"gap":[33],"inheriting":[35],"from":[39],"backbone":[41],"LLMs,":[42],"and":[43,72,83,90,97,127],"make":[44],"costly":[46],"to":[47,78,105],"collect":[48],"a":[49,58],"large-scale":[50],"high-quality":[51],"dataset.To":[52],"address":[53],"it,":[54],"we":[55,66,88],"propose":[56],"ViFT,":[57,65],"instruction-free":[60],"fine-tuning":[61],"framework":[62],"for":[63,100],"LVLMs.In":[64],"only":[67],"text-only":[70],"image":[73,98],"caption":[74],"data":[75,128],"during":[76],"training,":[77],"separately":[79],"learn":[80],"perception":[85],"abilities.During":[86],"inference,":[87],"extract":[89],"combine":[91],"representations":[93],"text":[96],"inputs,":[99],"fusing":[101],"two":[103],"abilities":[104],"fulfill":[106],"tasks.Experimental":[108],"results":[109],"demonstrate":[110],"that":[111],"ViFT":[112],"can":[113],"achieve":[114],"state-of-the-art":[115],"performance":[116],"on":[117],"several":[118],"downstream":[119],"benchmarks,":[120],"with":[121],"rather":[122],"less":[123],"training":[124],"data.Our":[125],"code":[126],"will":[129],"be":[130],"publicly":[131],"released.":[132]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}