{"id":"https://openalex.org/W4406072293","doi":"https://doi.org/10.48550/arxiv.2407.14875","title":"Seal: Advancing Speech Language Models to be Few-Shot Learners","display_name":"Seal: Advancing Speech Language Models to be Few-Shot Learners","publication_year":2024,"publication_date":"2024-07-20","ids":{"openalex":"https://openalex.org/W4406072293","doi":"https://doi.org/10.48550/arxiv.2407.14875"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2407.14875","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.14875","pdf_url":"https://arxiv.org/pdf/2407.14875","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2407.14875","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080354629","display_name":"Shuyu Lei","orcid":"https://orcid.org/0000-0002-3160-6668"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lei, Shuyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100771916","display_name":"Lu Liu","orcid":"https://orcid.org/0000-0001-8137-671X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Lingen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076804411","display_name":"Jiaolong Yang","orcid":"https://orcid.org/0000-0002-7314-6567"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Jiaolong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115771757","display_name":"Yasen Jiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiao, Yasen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041959802","display_name":"Yuxiang Yang","orcid":"https://orcid.org/0000-0002-3031-2756"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yuxiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020143813","display_name":"Yushu Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yushu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5033083184","display_name":"Xiang Guo","orcid":"https://orcid.org/0000-0001-6795-5395"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Xiang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5080354629"],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9541000127792358,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9541000127792358,"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/shot","display_name":"Shot (pellet)","score":0.6906591653823853},{"id":"https://openalex.org/keywords/seal","display_name":"Seal (emblem)","score":0.607327938079834},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.5497007966041565},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.541593074798584},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.4487522840499878},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3404809236526489},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.2218644618988037},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1670527160167694},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.06390240788459778},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.0475306510925293},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.04464989900588989}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6906591653823853},{"id":"https://openalex.org/C2777755289","wikidata":"https://www.wikidata.org/wiki/Q162919","display_name":"Seal (emblem)","level":2,"score":0.607327938079834},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5497007966041565},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.541593074798584},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.4487522840499878},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3404809236526489},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.2218644618988037},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1670527160167694},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06390240788459778},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0475306510925293},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.04464989900588989},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2407.14875","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.14875","pdf_url":"https://arxiv.org/pdf/2407.14875","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2407.14875","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2407.14875","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2407.14875","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.14875","pdf_url":"https://arxiv.org/pdf/2407.14875","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406072293.pdf","grobid_xml":"https://content.openalex.org/works/W4406072293.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2497720472","https://openalex.org/W4292659306","https://openalex.org/W3044321615","https://openalex.org/W2806221744","https://openalex.org/W2326937258","https://openalex.org/W394267150","https://openalex.org/W2773965352","https://openalex.org/W4294892107","https://openalex.org/W2357748469","https://openalex.org/W2392917037"],"abstract_inverted_index":{"Existing":[0],"auto-regressive":[1],"language":[2,50,78,109],"models":[3],"have":[4],"demonstrated":[5],"a":[6,11,16,33,54,67,71,76,89],"remarkable":[7],"capability":[8,31],"to":[9,28,32,65,102],"perform":[10],"new":[12],"task":[13],"with":[14,75],"just":[15],"few":[17],"examples":[18],"in":[19,58],"prompt,":[20],"without":[21],"requiring":[22],"any":[23],"additional":[24],"training.":[25],"In":[26],"order":[27],"extend":[29],"this":[30,40],"multi-modal":[34],"setting":[35],"(i.e.":[36],"speech":[37,49,73,94],"and":[38],"language),":[39],"paper":[41],"introduces":[42],"the":[43],"Seal":[44,83],"model,":[45],"an":[46],"abbreviation":[47],"for":[48],"model.":[51],"It":[52],"incorporates":[53],"novel":[55],"alignment":[56],"method,":[57],"which":[59],"Kullback-Leibler":[60],"divergence":[61],"loss":[62],"is":[63],"performed":[64],"train":[66],"projector":[68],"that":[69],"bridges":[70],"frozen":[72,77],"encoder":[74],"model":[79,84],"decoder.":[80],"The":[81],"resulting":[82],"exhibits":[85],"robust":[86],"performance":[87],"as":[88],"few-shot":[90],"learner":[91],"on":[92,106],"two":[93],"understanding":[95],"tasks.":[96],"Additionally,":[97],"consistency":[98],"experiments":[99],"are":[100],"conducted":[101],"validate":[103],"its":[104],"robustness":[105],"different":[107],"pre-trained":[108],"models.":[110]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}