{"id":"https://openalex.org/W4392903970","doi":"https://doi.org/10.1109/icassp48485.2024.10446407","title":"Empowering Vision-Language Models for Reasoning Ability through Large Language Models","display_name":"Empowering Vision-Language Models for Reasoning Ability through Large Language Models","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903970","doi":"https://doi.org/10.1109/icassp48485.2024.10446407"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5102515648","display_name":"Yueting Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yueting Yang","raw_affiliation_strings":["Beijing Jiaotong University,Beijing,China","Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,Beijing,China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100461959","display_name":"Xintong Zhang","orcid":"https://orcid.org/0000-0003-2302-9642"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xintong Zhang","raw_affiliation_strings":["Beijing Jiaotong University,Beijing,China","Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,Beijing,China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101698034","display_name":"Jinan Xu","orcid":"https://orcid.org/0000-0003-0170-626X"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinan Xu","raw_affiliation_strings":["Beijing Jiaotong University,Beijing,China","Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,Beijing,China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100990897","display_name":"Wenjuan Han","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjuan Han","raw_affiliation_strings":["Beijing Jiaotong University,Beijing,China","Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,Beijing,China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102515648"],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":1.5745,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.83266704,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"10056","last_page":"10060"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9977999925613403,"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":0.9785000085830688,"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/computer-science","display_name":"Computer science","score":0.7797685861587524},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.6157381534576416},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.566236138343811},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5655970573425293},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.526892900466919},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4719863533973694},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4457191824913025},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4032306373119354},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.134105384349823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7797685861587524},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.6157381534576416},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.566236138343811},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5655970573425293},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.526892900466919},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4719863533973694},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4457191824913025},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4032306373119354},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.134105384349823},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323066","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2560730294","https://openalex.org/W2963518342","https://openalex.org/W3210277894","https://openalex.org/W4225323055","https://openalex.org/W4283208789","https://openalex.org/W4285239949","https://openalex.org/W4286894277","https://openalex.org/W4292779060","https://openalex.org/W4303443398","https://openalex.org/W4318718936","https://openalex.org/W4323717348","https://openalex.org/W4353113046","https://openalex.org/W4364383163","https://openalex.org/W4385570217","https://openalex.org/W4385571011","https://openalex.org/W4386071547","https://openalex.org/W4386075985","https://openalex.org/W6778883912","https://openalex.org/W6803645040","https://openalex.org/W6810334672","https://openalex.org/W6811013733","https://openalex.org/W6811070434","https://openalex.org/W6839091850","https://openalex.org/W6846002521","https://openalex.org/W6849177959","https://openalex.org/W6850071225","https://openalex.org/W6850140740","https://openalex.org/W6852293568"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4224009465","https://openalex.org/W4306674287","https://openalex.org/W4286629047","https://openalex.org/W4389443772","https://openalex.org/W4205958290","https://openalex.org/W4384212932","https://openalex.org/W2548721895","https://openalex.org/W2373456246","https://openalex.org/W4390590544"],"abstract_inverted_index":{"Vision-language":[0],"models":[1,21],"(VLM)":[2],"have":[3,23],"shown":[4],"excellent":[5],"performance":[6],"in":[7,47],"vision-language":[8],"tasks.":[9],"However,":[10],"they":[11],"sometimes":[12],"lack":[13],"sufficient":[14],"reasoning":[15,27,39,127],"ability.":[16],"In":[17],"contrast,":[18],"large":[19],"language":[20],"(LLMs)":[22],"emerged":[24],"with":[25,177],"powerful":[26],"capabilities.":[28],"Therefore,":[29],"we":[30,140],"propose":[31],"a":[32,52,144,182,189],"framework":[33],"called":[34],"TReE,":[35],"which":[36,139],"transfers":[37],"the":[38,42,45,63,71,74,78,85,88,94,100,107,112,116,120,125,136,149,168],"ability":[40,128],"of":[41,185,192],"LLM":[43],"to":[44,65,92,122,135,142,148],"VLM":[46,64],"learning-free":[48],"settings.":[49],"TReE":[50,155,187],"is":[51],"three-stage":[53],"framework:":[54],"observation,":[55],"thinking,":[56],"and":[57,81,109,164,196],"re-thinking.":[58],"The":[59],"observation":[60],"stage":[61,76,102],"requires":[62],"obtain":[66],"overall":[67],"visual":[68,79,160],"information":[69,80,105],"about":[70],"image.":[72],"Then,":[73],"thinking":[75,95],"combines":[77],"task":[82],"description":[83],"as":[84,143],"prompt":[86],"for":[87],"LLM,":[89],"allowing":[90],"it":[91],"present":[93],"process":[96],"(namely,":[97],"rationale).":[98],"Lastly,":[99],"re-thinking":[101],"learns":[103],"useful":[104],"from":[106],"rationale":[108],"then":[110],"predicts":[111],"final":[113],"result":[114],"using":[115,181],"VLM.":[117],"We":[118],"are":[119],"first":[121],"explore":[123],"enhancing":[124],"VLM\u2019s":[126],"without":[129],"any":[130],"training,":[131],"finetuning,":[132],"or":[133],"access":[134],"LLM\u2019s":[137],"parameters,":[138,186],"refer":[141],"plug-in":[145],"mode,":[146],"leading":[147],"model-agnostic":[150],"feature.":[151],"Experiments":[152],"show":[153],"that":[154],"performed":[156],"well":[157],"on":[158,167,194,198],"general":[159],"questionanswering":[161],"(VQA)":[162],"tasks":[163],"outperformed":[165],"KOSMOS-1":[166],"challenging":[169],"Raven":[170],"IQ":[171],"test":[172],"dataset":[173],"by":[174],"6%.":[175],"Furthermore,":[176],"additional":[178],"lightweight":[179],"finetuning":[180],"smaller":[183],"amount":[184],"achieved":[188],"high":[190],"accuracy":[191],"81.7%":[193],"GQA":[195],"67.3%":[197],"VQAv2.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}