{"id":"https://openalex.org/W4416144397","doi":"https://doi.org/10.1145/3721201.3721413","title":"Optimizing Veterinary Language Modeling with Mamba Architecture for Long-Sequence Efficiency","display_name":"Optimizing Veterinary Language Modeling with Mamba Architecture for Long-Sequence Efficiency","publication_year":2025,"publication_date":"2025-06-24","ids":{"openalex":"https://openalex.org/W4416144397","doi":"https://doi.org/10.1145/3721201.3721413"},"language":null,"primary_location":{"id":"doi:10.1145/3721201.3721413","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721201.3721413","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3721201.3721413","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE International Conference on Connected Health: Applications, Systems and Engineering Technologies","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3721201.3721413","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120084225","display_name":"Lakshmi Priya Ramisetty","orcid":"https://orcid.org/0009-0002-3593-9598"},"institutions":[{"id":"https://openalex.org/I19772626","display_name":"Yeshiva University","ror":"https://ror.org/045x93337","country_code":"US","type":"education","lineage":["https://openalex.org/I19772626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lakshmi Priya Ramisetty","raw_affiliation_strings":["Yeshiva University, New York, NY, USA"],"raw_orcid":"https://orcid.org/0009-0002-3593-9598","affiliations":[{"raw_affiliation_string":"Yeshiva University, New York, NY, USA","institution_ids":["https://openalex.org/I19772626"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079460371","display_name":"Youshan Zhang","orcid":"https://orcid.org/0000-0002-0074-0979"},"institutions":[{"id":"https://openalex.org/I19772626","display_name":"Yeshiva University","ror":"https://ror.org/045x93337","country_code":"US","type":"education","lineage":["https://openalex.org/I19772626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Youshan Zhang","raw_affiliation_strings":["Yeshiva University, New York, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-0074-0979","affiliations":[{"raw_affiliation_string":"Yeshiva University, New York, NY, USA","institution_ids":["https://openalex.org/I19772626"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I19772626"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31519523,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"289","last_page":"293"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.43630000948905945,"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/T10028","display_name":"Topic Modeling","score":0.43630000948905945,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.07880000025033951,"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/T12031","display_name":"Speech and dialogue systems","score":0.04439999908208847,"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/scalability","display_name":"Scalability","score":0.5461999773979187},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5095000267028809},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.45249998569488525},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.43220001459121704},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.38940000534057617},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.38190001249313354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.618399977684021},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5461999773979187},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5095000267028809},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.45249998569488525},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.43220001459121704},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4032999873161316},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.38940000534057617},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.38190001249313354},{"id":"https://openalex.org/C178009071","wikidata":"https://www.wikidata.org/wiki/Q93344","display_name":"Trigonometric functions","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3231000006198883},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.29010000824928284},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2800000011920929},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2768999934196472},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.26350000500679016},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3721201.3721413","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721201.3721413","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3721201.3721413","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE International Conference on Connected Health: Applications, Systems and Engineering Technologies","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3721201.3721413","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721201.3721413","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3721201.3721413","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE International Conference on Connected Health: Applications, Systems and Engineering Technologies","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416144397.pdf","grobid_xml":"https://content.openalex.org/works/W4416144397.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W2911489562","https://openalex.org/W3015453090","https://openalex.org/W3034999214","https://openalex.org/W3046375318"],"related_works":[],"abstract_inverted_index":{"This":[0,70],"paper":[1],"introduces":[2],"VetMamba,":[3],"a":[4,34],"veterinary":[5,37,79],"language":[6],"model":[7],"leveraging":[8],"the":[9,73],"Mamba":[10],"architecture":[11],"for":[12,29,85],"efficient":[13],"long-sequence":[14],"processing.":[15],"Unlike":[16],"traditional":[17],"transformer-based":[18],"models,":[19],"which":[20],"struggle":[21],"with":[22],"quadratic":[23],"complexity,":[24],"VetMamba":[25],"integrates":[26],"state-space":[27,76],"mechanisms":[28],"linear":[30],"scaling.":[31],"Trained":[32],"on":[33,96],"420GB":[35],"curated":[36],"dataset,":[38],"it":[39],"incorporates":[40],"optimizations":[41],"like":[42],"mixed":[43],"precision":[44],"training,":[45],"cosine":[46],"annealing":[47],"learning":[48],"rate":[49],"scheduling,":[50],"and":[51,87],"DeepSpeed":[52],"acceleration.":[53],"Our":[54],"results":[55],"demonstrate":[56],"VetMamba's":[57],"superiority":[58],"in":[59,78],"domain-specific":[60],"question-answering,":[61],"achieving":[62],"improved":[63],"ROUGE":[64],"scores":[65],"over":[66],"baseline":[67],"transformer":[68],"models.":[69],"work":[71],"highlights":[72],"potential":[74],"of":[75],"models":[77],"informatics,":[80],"offering":[81],"scalable":[82],"AI-driven":[83],"solutions":[84],"professionals":[86],"pet":[88],"owners.":[89],"The":[90],"complete":[91],"source":[92],"code":[93],"is":[94],"available":[95],"our":[97],"GitHub":[98],"repository1.":[99]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-12T00:00:00"}