{"id":"https://openalex.org/W4406311999","doi":"https://doi.org/10.1109/lsp.2025.3528362","title":"DPO: Discrete Prompt Optimization for Vision-Language Models","display_name":"DPO: Discrete Prompt Optimization for Vision-Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406311999","doi":"https://doi.org/10.1109/lsp.2025.3528362"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2025.3528362","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3528362","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5101319191","display_name":"Nanhao Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I2802624667","display_name":"Hefei Institutes of Physical Science","ror":"https://ror.org/046n57345","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Nanhao Liang","raw_affiliation_strings":["Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, China","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, China","institution_ids":["https://openalex.org/I2802624667","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072988055","display_name":"Yong Liu","orcid":"https://orcid.org/0000-0001-9031-9696"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I2802624667","display_name":"Hefei Institutes of Physical Science","ror":"https://ror.org/046n57345","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Liu","raw_affiliation_strings":["Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, China","institution_ids":["https://openalex.org/I2802624667","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101319191"],"corresponding_institution_ids":["https://openalex.org/I126520041","https://openalex.org/I19820366","https://openalex.org/I2802624667"],"apc_list":null,"apc_paid":null,"fwci":6.6374,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.96159923,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"671","last_page":"675"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9957000017166138,"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":0.9957000017166138,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9154000282287598,"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/computer-science","display_name":"Computer science","score":0.6184768676757812},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4299657344818115},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38282081484794617},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.33972281217575073},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18572255969047546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6184768676757812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4299657344818115},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38282081484794617},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33972281217575073},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18572255969047546}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3528362","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3528362","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W1977295328","https://openalex.org/W2017814585","https://openalex.org/W2047643928","https://openalex.org/W2108598243","https://openalex.org/W2138011018","https://openalex.org/W2155904486","https://openalex.org/W2533598788","https://openalex.org/W2964194231","https://openalex.org/W3198377975","https://openalex.org/W3213454282","https://openalex.org/W4312310776","https://openalex.org/W4385567149","https://openalex.org/W4386065763","https://openalex.org/W4386071547","https://openalex.org/W4400070365","https://openalex.org/W6600983433","https://openalex.org/W6638677478","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6803872405","https://openalex.org/W6810334672","https://openalex.org/W6859043230"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"the":[3,12,50,88,94,133],"emergence":[4],"of":[5,14,46,52,135],"large":[6],"visionlanguage":[7],"models":[8],"(VLMs)":[9],"has":[10],"catalyzed":[11],"development":[13],"prompt":[15,32,53],"learning,":[16],"where":[17],"networks":[18],"are":[19,77,83,140],"trained":[20],"to":[21,40,49,79,86],"enhance":[22],"VLM":[23],"performance":[24],"by":[25],"learning":[26,33,134],"continuous":[27,31],"prompts.":[28],"However,":[29],"traditional":[30],"often":[34],"struggles":[35],"with":[36],"challenges":[37],"like":[38,108],"overfitting":[39,124],"Base":[41],"classes":[42,114],"and":[43,110,129],"a":[44,65],"lack":[45],"interpretability":[47],"due":[48],"nature":[51],"parameterization.":[54],"To":[55],"overcome":[56],"these":[57],"limitations,":[58],"we":[59],"introduce":[60],"Discrete":[61],"Prompt":[62],"Optimization":[63],"(DPO),":[64],"method":[66],"that":[67,139],"optimizes":[68],"text":[69,137],"prompts":[70,138],"in":[71,115],"discrete":[72,119],"word-space.":[73],"During":[74],"training,":[75],"scores":[76],"assigned":[78],"token":[80,91],"embeddings,":[81],"which":[82],"then":[84],"used":[85],"select":[87],"most":[89,116],"effective":[90],"sequence":[92],"for":[93],"downstream":[95],"task.":[96],"DPO":[97],"was":[98],"tested":[99],"across":[100],"11":[101],"diverse":[102],"datasets,":[103],"consistently":[104],"outperforming":[105],"baseline":[106],"methods":[107],"CLIP":[109],"CoOp":[111],"on":[112],"Novel":[113],"cases.":[117],"This":[118],"approach":[120],"not":[121],"only":[122],"reduces":[123],"but":[125],"also":[126],"enhances":[127],"transparency":[128],"model":[130],"interpretability,":[131],"enabling":[132],"dataset-specific":[136],"easily":[141],"understandable.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-21T08:13:44.787528","created_date":"2025-10-10T00:00:00"}