{"id":"https://openalex.org/W7204179305","doi":"https://doi.org/10.48550/arxiv.2608.22642","title":"Mol-JEPA: A multimodal Joint Embedding Predictive Architecture for Molecules","display_name":"Mol-JEPA: A multimodal Joint Embedding Predictive Architecture for Molecules","publication_year":2026,"publication_date":"2026-08-23","ids":{"openalex":"https://openalex.org/W7204179305","doi":"https://doi.org/10.48550/arxiv.2608.22642"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2608.22642","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22642","pdf_url":"https://arxiv.org/pdf/2608.22642","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","license_id":"https://openalex.org/licenses/cc-by","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/2608.22642","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5094178932","display_name":"Florian Rottach","orcid":"https://orcid.org/0009-0001-4718-9168","observed_orcids":["https://orcid.org/0009-0001-4718-9168"]},"institutions":[{"id":"https://openalex.org/I1330995197","display_name":"Boehringer Ingelheim (Germany)","ror":"https://ror.org/00q32j219","country_code":"DE","type":"company","lineage":["https://openalex.org/I1330995197"]},{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rottach, Florian","raw_affiliation_strings":["Boehringer Ingelheim","University of T\u00fcbingen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boehringer Ingelheim","institution_ids":["https://openalex.org/I1330995197"]},{"raw_affiliation_string":"University of T\u00fcbingen","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067734121","display_name":"Sebastian Schieferdecker","orcid":"https://orcid.org/0000-0002-4016-7409","observed_orcids":["https://orcid.org/0000-0002-4016-7409"]},"institutions":[{"id":"https://openalex.org/I1330995197","display_name":"Boehringer Ingelheim (Germany)","ror":"https://ror.org/00q32j219","country_code":"DE","type":"company","lineage":["https://openalex.org/I1330995197"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Schieferdecker, Sebastian","raw_affiliation_strings":["Boehringer Ingelheim"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boehringer Ingelheim","institution_ids":["https://openalex.org/I1330995197"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153427926","display_name":"William Rudman","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rudman, William","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047293370","display_name":"Randall Balestriero","orcid":"https://orcid.org/0000-0002-5692-4187","observed_orcids":["https://orcid.org/0000-0002-5692-4187"]},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Balestriero, Randall","raw_affiliation_strings":["Brown University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014921416","display_name":"Carsten Eickhoff","orcid":"https://orcid.org/0000-0001-9895-4061","observed_orcids":["https://orcid.org/0000-0001-9895-4061"]},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Eickhoff, Carsten","raw_affiliation_strings":["University of T\u00fcbingen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of T\u00fcbingen","institution_ids":["https://openalex.org/I8087733"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.9961000084877014,"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"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9961000084877014,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.0007999999797903001,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/molecular-representation-learning","display_name":"molecular representation learning","score":0.5740000009536743},{"id":"https://openalex.org/keywords/binding-affinity-prediction","display_name":"binding affinity prediction","score":0.621999979019165},{"id":"https://openalex.org/keywords/admet-properties","display_name":"ADMET properties","score":0.9049999713897705},{"id":"https://openalex.org/keywords/quantum-chemical-simulation","display_name":"quantum chemistry simulation","score":0.7820000052452087},{"id":"https://openalex.org/keywords/cell-phenotype","display_name":"cell phenotype","score":0.7990000247955322}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6754000186920166},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6679999828338623},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6514000296592712},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5778999924659729},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5440000295639038},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5325000286102295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44839999079704285},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4361000061035156},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.4327999949455261},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4269999861717224},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4194999933242798},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.41760000586509705},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.40149998664855957},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.302700012922287},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.2955000102519989},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C179303850","wikidata":"https://www.wikidata.org/wiki/Q4300362","display_name":"Molecular recognition","level":3,"score":0.2775999903678894},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.27489998936653137},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.22642","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22642","pdf_url":"https://arxiv.org/pdf/2608.22642","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.22642","doi":"https://doi.org/10.48550/arxiv.2608.22642","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.22642","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.22642","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22642","pdf_url":"https://arxiv.org/pdf/2608.22642","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204179305.pdf","grobid_xml":"https://content.openalex.org/works/W7204179305.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"recent":[1],"advances":[2],"in":[3],"molecular":[4,35,43,54],"foundation":[5],"models,":[6],"several":[7],"limitations":[8],"remain,":[9],"such":[10],"as":[11],"chemically":[12],"invalid":[13],"augmentations,":[14],"modality":[15,48],"collapse,":[16],"and":[17,65],"incomplete":[18],"representation":[19],"of":[20,87],"biochemical":[21,89],"environments.":[22],"To":[23],"address":[24],"these":[25],"challenges,":[26],"we":[27,73],"present":[28],"\\textbf{Mol-JEPA},":[29],"a":[30],"scalable":[31],"framework":[32],"for":[33],"learning":[34],"world":[36],"models.":[37],"Rather":[38],"than":[39],"relying":[40],"on":[41],"suboptimal":[42],"perturbations,":[44],"our":[45],"model":[46],"uses":[47],"masking":[49],"to":[50],"exploit":[51],"information":[52],"from":[53],"structures,":[55],"cellular":[56],"phenotypes,":[57],"binding":[58],"affinities,":[59],"ADMET":[60],"profiles,":[61],"quantum":[62],"chemistry":[63],"simulations":[64],"other":[66],"drug":[67],"discovery":[68],"data.":[69],"Across":[70],"various":[71],"benchmarks,":[72],"show":[74],"that":[75],"the":[76,85],"representations":[77],"learned":[78],"by":[79],"Mol-JEPA":[80],"deliver":[81],"strong":[82],"performance,":[83],"demonstrating":[84],"value":[86],"incorporating":[88],"context":[90],"through":[91],"latent":[92],"space":[93],"prediction.":[94]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2026-08-26T00:00:00"}