{"id":"https://openalex.org/W7204164859","doi":"https://doi.org/10.48550/arxiv.2608.22849","title":"RIBOSPAN: A Long-Context RNA Foundation Model for Versatile RNA Modeling","display_name":"RIBOSPAN: A Long-Context RNA Foundation Model for Versatile RNA Modeling","publication_year":2026,"publication_date":"2026-08-24","ids":{"openalex":"https://openalex.org/W7204164859","doi":"https://doi.org/10.48550/arxiv.2608.22849"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.22849","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22849","pdf_url":"https://arxiv.org/pdf/2608.22849","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.22849","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148080959","display_name":"Ziyuan Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Ziyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121656377","display_name":"Bohao Tang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Bohao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148173524","display_name":"Fei Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Fei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148150454","display_name":"Shuo Han","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210121447","display_name":"Center for Excellence in Molecular Cell Science","ror":"https://ror.org/02rrdvm96","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210121447"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han, Shuo","raw_affiliation_strings":["Center for Excellence in Molecular Cell Science , CAS","University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Excellence in Molecular Cell Science , CAS","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210121447"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5148109495","display_name":"Pengfei Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Pengfei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.8384000062942505,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.8384000062942505,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.10599999874830246,"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":0.012799999676644802,"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/mrna-design","display_name":"mRNA design","score":0.4300000071525574},{"id":"https://openalex.org/keywords/discrete-diffusion-models","display_name":"discrete diffusion models","score":0.6010000109672546}],"concepts":[{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.7329000234603882},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6565999984741211},{"id":"https://openalex.org/C67705224","wikidata":"https://www.wikidata.org/wiki/Q11053","display_name":"RNA","level":3,"score":0.6389999985694885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5586000084877014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43790000677108765},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41370001435279846},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4016000032424927},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.39980000257492065},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.37720000743865967},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.3702000081539154},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.3686999976634979},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3652999997138977},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.359499990940094},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3221000134944916},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.31360000371932983},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.2946999967098236}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.22849","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22849","pdf_url":"https://arxiv.org/pdf/2608.22849","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.22849","doi":"https://doi.org/10.48550/arxiv.2608.22849","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.22849","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.22849","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22849","pdf_url":"https://arxiv.org/pdf/2608.22849","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204164859.pdf","grobid_xml":"https://content.openalex.org/works/W7204164859.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7204009338","https://openalex.org/W4416414445","https://openalex.org/W4416088662","https://openalex.org/W4407446628","https://openalex.org/W7154387017","https://openalex.org/W7138937617","https://openalex.org/W7134914070","https://openalex.org/W4410165516","https://openalex.org/W7122672884","https://openalex.org/W7134067956"],"abstract_inverted_index":{"Full-length":[0],"RNAs,":[1,4],"particularly":[2,122],"messenger":[3],"often":[5],"exceed":[6],"the":[7,95,135,156],"context":[8,35],"lengths":[9,36],"used":[10],"to":[11,38,52],"pretrain":[12],"existing":[13],"RNA":[14,29,118,138,188],"foundation":[15,30,139,185],"models,":[16],"limiting":[17],"complete-transcript":[18],"modeling":[19,55],"at":[20,66],"single-nucleotide":[21,46],"resolution.":[22],"We":[23],"present":[24],"RIBOSPAN,":[25],"a":[26,71,121,161,182],"1.61-billion-parameter":[27],"bidirectional":[28,44],"model":[31],"natively":[32],"pretrained":[33],"with":[34,120],"up":[37],"10,240":[39,67],"nt.":[40],"RIBOSPAN":[41,115,132,180],"combines":[42],"dense":[43],"self-attention,":[45],"tokenization,":[47],"and":[48,79,150,170,193],"attention-isolated":[49],"sequence":[50],"packing":[51],"enable":[53],"high-resolution":[54],"of":[56,94],"complete":[57],"long":[58,126],"RNAs.":[59,127],"Native":[60],"10K":[61],"pretraining":[62],"preserves":[63],"strong":[64,76],"reconstruction":[65],"tokens":[68],"and,":[69],"in":[70,144],"controlled":[72],"long-context":[73,184],"benchmark,":[74],"maintains":[75],"contextual":[77,96],"responsiveness":[78],"context-specific":[80],"representation":[81,108,189],"separation":[82],"while":[83],"keeping":[84],"perturbation-induced":[85],"changes":[86],"highly":[87],"localized.":[88],"Inference-time":[89],"YaRN":[90],"scaling":[91],"recovers":[92],"much":[93],"organization":[97],"lost":[98],"by":[99],"direct":[100],"short-context":[101],"extrapolation,":[102],"but":[103],"induces":[104],"substantially":[105],"greater":[106],"distal":[107],"diffusion.":[109],"Frozen":[110],"RNA-type":[111],"evaluations":[112],"show":[113],"that":[114],"learns":[116],"state-of-the-art":[117,142],"representations,":[119],"clear":[123],"advantage":[124],"on":[125,155],"Across":[128],"downstream":[129],"biological":[130,147,191],"benchmarks,":[131],"emerges":[133],"as":[134],"strongest":[136],"encoder-only":[137],"model,":[140],"achieving":[141],"performance":[143],"both":[145],"full-transcript":[146,194],"property":[148],"prediction":[149],"zero-shot":[151],"mutation-fitness":[152],"modeling.":[153],"Building":[154],"same":[157],"backbone,":[158],"we":[159],"develop":[160],"multidimensionally":[162],"conditioned":[163],"discrete-diffusion":[164],"framework":[165],"for":[166,175,186],"full-length":[167],"mRNA":[168,195],"generation":[169],"redesign,":[171],"including":[172],"synonymous-codon":[173],"diffusion":[174],"protein-preserving":[176],"CDS":[177],"optimization.":[178],"Together,":[179],"establishes":[181],"powerful":[183],"transferable":[187],"learning,":[190],"prediction,":[192],"design.":[196]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-08-26T00:00:00"}