{"id":"https://openalex.org/W7127977097","doi":"https://doi.org/10.48550/arxiv.2602.04883","title":"Protein Autoregressive Modeling via Multiscale Structure Generation","display_name":"Protein Autoregressive Modeling via Multiscale Structure Generation","publication_year":2026,"publication_date":"2026-02-04","ids":{"openalex":"https://openalex.org/W7127977097","doi":"https://doi.org/10.48550/arxiv.2602.04883"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2602.04883","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.04883","pdf_url":"https://arxiv.org/pdf/2602.04883","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2602.04883","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037311972","display_name":"Yanru Qu","orcid":"https://orcid.org/0000-0002-7664-0421","observed_orcids":["https://orcid.org/0000-0002-7664-0421"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qu, Yanru","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125241801","display_name":"Cheng-Yen Hsieh","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hsieh, Cheng-Yen","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100939869","display_name":"Zaixiang Zheng","orcid":"https://orcid.org/0009-0002-2717-3836","observed_orcids":["https://orcid.org/0009-0002-2717-3836"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheng, Zaixiang","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100731237","display_name":"Ge Liu","orcid":"https://orcid.org/0000-0001-9383-5186","observed_orcids":["https://orcid.org/0000-0001-9383-5186"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu, Ge","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120284571","display_name":"Quanquan Gu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gu, Quanquan","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9916999936103821,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9916999936103821,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.0017999999690800905,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.0015999999595806003,"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/protein-structure-generation","display_name":"protein structure generation","score":0.7789999842643738},{"id":"https://openalex.org/keywords/autoregressive-models","display_name":"autoregressive models","score":0.8709999918937683},{"id":"https://openalex.org/keywords/autoregressive-transformer","display_name":"autoregressive transformers","score":0.8489999771118164},{"id":"https://openalex.org/keywords/exposure-bias","display_name":"exposure bias","score":0.9819999933242798},{"id":"https://openalex.org/keywords/scheduled-sampling","display_name":"scheduled sampling","score":0.9990000128746033},{"id":"https://openalex.org/keywords/zero-shot-generalization","display_name":"zero-shot generalization","score":0.8550000190734863},{"id":"https://openalex.org/keywords/protein-design","display_name":"protein design","score":0.6179999709129333}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.8458999991416931},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5914999842643738},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.444599986076355},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.3896999955177307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38109999895095825},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3596999943256378},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35089999437332153},{"id":"https://openalex.org/C194657046","wikidata":"https://www.wikidata.org/wiki/Q7394685","display_name":"STAR model","level":4,"score":0.31380000710487366},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2969000041484833},{"id":"https://openalex.org/C141123601","wikidata":"https://www.wikidata.org/wiki/Q6935072","display_name":"Multiscale modeling","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.28209999203681946}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.04883","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.04883","pdf_url":"https://arxiv.org/pdf/2602.04883","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2602.04883","doi":"https://doi.org/10.48550/arxiv.2602.04883","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.04883","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:2602.04883","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.04883","pdf_url":"https://arxiv.org/pdf/2602.04883","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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/W7127977097.pdf","grobid_xml":"https://content.openalex.org/works/W7127977097.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415082968","https://openalex.org/W7165922185","https://openalex.org/W7220651762","https://openalex.org/W4280491725","https://openalex.org/W4396846556","https://openalex.org/W4281702815","https://openalex.org/W4417100710","https://openalex.org/W7104997350","https://openalex.org/W7222986605","https://openalex.org/W4391530977"],"abstract_inverted_index":{"We":[0,116],"present":[1],"protein":[2,12,58,158,182],"autoregressive":[3,9,67,95],"modeling":[4],"(PAR),":[5],"the":[6,20,103,106,151],"first":[7],"multi-scale":[8,53,71],"framework":[10,180],"for":[11,181],"backbone":[13,84,88,131],"generation":[14,107,114,143,153],"via":[15],"coarse-to-fine":[16],"next-scale":[17],"prediction.":[18],"Using":[19],"hierarchical":[21],"nature":[22],"of":[23,48,163],"proteins,":[24],"PAR":[25,46,134,155,176],"generates":[26,87],"structures":[27,59],"that":[28,56,69,86],"mimic":[29],"sculpting":[30],"a":[31,34,82,178],"statue,":[32],"forming":[33],"coarse":[35],"topology":[36],"and":[37,73,105,110,126,144,160,167],"refining":[38],"structural":[39],"details":[40],"over":[41],"scales.":[42],"To":[43],"achieve":[44],"this,":[45],"consists":[47],"three":[49],"key":[50],"components:":[51],"(i)":[52],"downsampling":[54],"operations":[55],"represent":[57],"across":[60],"multiple":[61],"scales":[62],"during":[63],"training;":[64],"(ii)":[65],"an":[66],"transformer":[68],"encodes":[70],"information":[72],"produces":[74,161],"conditional":[75,142],"embeddings":[76],"to":[77],"guide":[78],"structure":[79,113,183],"generation;":[80],"(iii)":[81],"flow-based":[83],"decoder":[85],"atoms":[89],"conditioned":[90],"on":[91],"these":[92,173],"embeddings.":[93],"Moreover,":[94],"models":[96],"suffer":[97],"from":[98],"exposure":[99],"bias,":[100],"caused":[101],"by":[102,121],"training":[104],"procedure":[108],"mismatch,":[109],"substantially":[111],"degrades":[112],"quality.":[115],"effectively":[117,156],"alleviate":[118],"this":[119],"issue":[120],"adopting":[122],"noisy":[123],"context":[124],"learning":[125],"scheduled":[127],"sampling,":[128],"enabling":[129],"robust":[130],"generation.":[132,184],"Notably,":[133],"exhibits":[135,168],"strong":[136],"zero-shot":[137],"generalization,":[138],"supporting":[139],"flexible":[140],"human-prompted":[141],"motif":[145],"scaffolding":[146],"without":[147],"requiring":[148],"fine-tuning.":[149],"On":[150],"unconditional":[152],"benchmark,":[154],"learns":[157],"distributions":[159],"backbones":[162],"high":[164],"design":[165],"quality,":[166],"favorable":[169],"scaling":[170],"behavior.":[171],"Together,":[172],"properties":[174],"establish":[175],"as":[177],"promising":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-07T00:00:00"}