{"id":"https://openalex.org/W7137921827","doi":"https://doi.org/10.1609/aaai.v40i1.37032","title":"MergeDNA: Context-Aware Genome Modeling with Dynamic Tokenization Through Token Merging","display_name":"MergeDNA: Context-Aware Genome Modeling with Dynamic Tokenization Through Token Merging","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137921827","doi":"https://doi.org/10.1609/aaai.v40i1.37032"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i1.37032","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i1.37032","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37032/40994","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37032/40994","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129741336","display_name":"Siyuan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Siyuan Li","raw_affiliation_strings":["Westlake University","Zhejiang University\nWestlake University\nBioMap Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Westlake University","institution_ids":["https://openalex.org/I3133055985"]},{"raw_affiliation_string":"Zhejiang University\nWestlake University\nBioMap Research","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129687103","display_name":"Kai Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["Westlake University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Westlake University","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129733687","display_name":"Anna Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Anna Wang","raw_affiliation_strings":["Westlake University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Westlake University","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101728120","display_name":"Zicheng Liu","orcid":"https://orcid.org/0000-0003-1106-2963"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zicheng Liu","raw_affiliation_strings":["Zhejiang University\nWestlake University\nBioMap Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University\nWestlake University\nBioMap Research","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129749699","display_name":"Chang Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang Yu","raw_affiliation_strings":["Westlake University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Westlake University","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129673039","display_name":"Jingbo Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingbo Zhou","raw_affiliation_strings":["Zhejiang University\nWestlake University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University\nWestlake University","institution_ids":["https://openalex.org/I3133055985","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121565577","display_name":"Qirong Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qirong Yang","raw_affiliation_strings":["BioMap Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BioMap Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129732690","display_name":"Yucheng Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yucheng Guo","raw_affiliation_strings":["BioMap Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BioMap Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129642167","display_name":"Xiaoming Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoming Zhang","raw_affiliation_strings":["BioMap Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BioMap Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129723385","display_name":"Stan Z. Li","orcid":null},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Stan Z. Li","raw_affiliation_strings":["Westlake University","Zhejiang University\nWestlake University\nBioMap Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Westlake University","institution_ids":["https://openalex.org/I3133055985"]},{"raw_affiliation_string":"Zhejiang University\nWestlake University\nBioMap Research","institution_ids":["https://openalex.org/I3133055985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5129741336"],"corresponding_institution_ids":["https://openalex.org/I3133055985"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2371134,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"1","first_page":"668","last_page":"676"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.3093000054359436,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.3093000054359436,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.1550000011920929,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.13809999823570251,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6973999738693237},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.6916999816894531},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44609999656677246},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4253000020980835},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.3806999921798706},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.35179999470710754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8384000062942505},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6973999738693237},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.6916999816894531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48089998960494995},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44609999656677246},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4253000020980835},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3806999921798706},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.35179999470710754},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2912999987602234},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2912999987602234},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2685000002384186},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2637999951839447},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.259799987077713}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i1.37032","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i1.37032","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37032/40994","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37032","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i1.37032","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i1.37032","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37032/40994","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6722809076309204,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1309843768","display_name":null,"funder_award_id":"624B2115","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2112497919","display_name":null,"funder_award_id":"WU2022A009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2543416449","display_name":null,"funder_award_id":"U21A20427","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320318567","display_name":"Westlake University","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137921827.pdf","grobid_xml":"https://content.openalex.org/works/W7137921827.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modeling":[0,152],"genomic":[1,52,69],"sequences":[2],"faces":[3],"two":[4,131],"unsolved":[5],"challenges:":[6],"the":[7,48,82,96,109,139],"information":[8],"density":[9],"varies":[10],"widely":[11],"across":[12],"different":[13],"regions,":[14],"while":[15,148],"there":[16],"is":[17],"no":[18],"clearly":[19],"defined":[20],"minimum":[21],"vocabulary":[22],"unit.":[23],"Relying":[24],"on":[25,171],"either":[26],"four":[27],"primitive":[28],"bases":[29,88],"or":[30,182],"independently":[31],"designed":[32],"DNA":[33,174,191],"tokenizers,":[34],"existing":[35],"approaches":[36],"with":[37,74,101,130,180],"naive":[38],"masked":[39],"language":[40],"modeling":[41],"pre-training":[42,76,132],"often":[43],"fail":[44],"to":[45,47,154,159],"adapt":[46],"varying":[49],"complexities":[50],"of":[51,95,112],"sequences.":[53],"Leveraging":[54],"Token":[55,135,151],"Merging":[56],"techniques,":[57],"this":[58],"paper":[59],"introduces":[60],"a":[61,67,105,121,125],"hierarchical":[62],"architecture":[63],"that":[64,166],"jointly":[65],"optimizes":[66],"dynamic":[68,140],"tokenizer":[70],"and":[71,124,143,176,189],"latent":[72],"Transformers":[73],"context-aware":[75],"tasks.":[77],"As":[78],"for":[79],"network":[80],"structures,":[81],"tokenization":[83,141,187],"module":[84,142],"automatically":[85],"chunks":[86],"adjacent":[87],"into":[89],"words":[90,115],"by":[91,116],"stacking":[92],"multiple":[93],"layers":[94],"differentiable":[97],"token":[98],"merging":[99],"blocks":[100],"local-window":[102],"constraints,":[103],"then":[104],"Latent":[106,122],"Encoder":[107],"captures":[108],"global":[110],"context":[111],"these":[113,156],"merged":[114],"full-attention":[117],"blocks.":[118],"Symmetrically":[119],"employing":[120],"Decoder":[123],"Local":[126],"Decoder,":[127],"MergeDNA":[128,167],"learns":[129,153],"tasks:":[133],"Merged":[134],"Reconstruction":[136],"simultaneously":[137],"trains":[138],"adaptively":[144],"filters":[145],"important":[146],"tokens,":[147],"Adaptive":[149],"Masked":[150],"predict":[155],"filtered":[157],"tokens":[158],"capture":[160],"informative":[161],"contents.":[162],"Extensive":[163],"experiments":[164],"show":[165],"achieves":[168],"superior":[169],"performance":[170],"three":[172],"popular":[173],"benchmarks":[175],"several":[177],"multi-omics":[178],"tasks":[179],"fine-tuning":[181],"zero-shot":[183],"evaluation,":[184],"outperforming":[185],"typical":[186],"methods":[188],"large-scale":[190],"foundation":[192],"models.":[193]},"counts_by_year":[],"updated_date":"2026-06-06T09:05:17.133730","created_date":"2026-03-18T00:00:00"}