{"id":"https://openalex.org/W7204272178","doi":"https://doi.org/10.1038/s41467-026-76378-7","title":"Scaling multimodal materials representation learning with synthetic narratives","display_name":"Scaling multimodal materials representation learning with synthetic narratives","publication_year":2026,"publication_date":"2026-08-26","ids":{"openalex":"https://openalex.org/W7204272178","doi":"https://doi.org/10.1038/s41467-026-76378-7","pmid":"https://pubmed.ncbi.nlm.nih.gov/42802153"},"language":"en","primary_location":{"id":"doi:10.1038/s41467-026-76378-7","doi":"https://doi.org/10.1038/s41467-026-76378-7","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41467-026-76378-7","pdf_url":"https://www.nature.com/articles/s41467-026-76378-7_reference.pdf","source":{"id":"https://openalex.org/S64187185","display_name":"Nature Communications","issn_l":"2041-1723","issn":["2041-1723"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-a","doyens","jufo-3","ki-jl-3","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Communications","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.nature.com/articles/s41467-026-76378-7_reference.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042277801","display_name":"Yang Jeong Park","orcid":"https://orcid.org/0000-0002-3773-7407","observed_orcids":["https://orcid.org/0000-0002-3773-7407"]},"institutions":[{"id":"https://openalex.org/I48566637","display_name":"Ulsan National Institute of Science and Technology","ror":"https://ror.org/017cjz748","country_code":"KR","type":"education","lineage":["https://openalex.org/I48566637"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Yang Jeong Park","raw_affiliation_strings":["Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA","Department of Materials Science and Engineering, Ulsan National Institute of Science and Technology, Ulju-gun, Ulsan, Republic of Korea","Department of Nuclear Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3773-7407","affiliations":[{"raw_affiliation_string":"Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Department of Materials Science and Engineering, Ulsan National Institute of Science and Technology, Ulju-gun, Ulsan, Republic of Korea","institution_ids":["https://openalex.org/I48566637"]},{"raw_affiliation_string":"Department of Nuclear Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148258094","display_name":"Mayank Kumaran","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":"Mayank Kumaran","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148339368","display_name":"Chia-Wei Hsu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chia-Wei Hsu","raw_affiliation_strings":["Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073567771","display_name":"Elsa Olivetti","orcid":"https://orcid.org/0000-0002-8043-2385","observed_orcids":["https://orcid.org/0000-0002-8043-2385","https://orcid.org/0009-0005-4190-8319"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Elsa Olivetti","raw_affiliation_strings":["Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA. elsao@mit.edu","MIT-IBM Watson AI Lab, Massachusetts Institute of Technology, Cambridge, MA, USA. elsao@mit.edu"],"raw_orcid":"https://orcid.org/0000-0002-8043-2385","affiliations":[{"raw_affiliation_string":"Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA. elsao@mit.edu","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"MIT-IBM Watson AI Lab, Massachusetts Institute of Technology, Cambridge, MA, USA. elsao@mit.edu","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100609041","display_name":"Ju Li","orcid":"https://orcid.org/0000-0002-7841-8058","observed_orcids":["https://orcid.org/0000-0002-7841-8058","https://orcid.org/0000-0002-1203-4684"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ju Li","raw_affiliation_strings":["Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA. liju@mit.edu","Department of Nuclear Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA. liju@mit.edu","MIT-IBM Watson AI Lab, Massachusetts Institute of Technology, Cambridge, MA, USA. liju@mit.edu"],"raw_orcid":"https://orcid.org/0000-0002-7841-8058","affiliations":[{"raw_affiliation_string":"Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA. liju@mit.edu","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Department of Nuclear Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA. liju@mit.edu","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"MIT-IBM Watson AI Lab, Massachusetts Institute of Technology, Cambridge, MA, USA. liju@mit.edu","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5073567771","https://openalex.org/A5100609041"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":{"value":6990,"currency":"USD","value_usd":6990},"apc_paid":{"value":6990,"currency":"USD","value_usd":6990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.53536993,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9994999766349792,"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":0.00039999998989515007,"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"}},{"id":"https://openalex.org/T10939","display_name":"Crystal Structures and Properties","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2504","display_name":"Electronic, Optical and Magnetic Materials"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/multimodal-representation-learning","display_name":"multimodal representation learning","score":0.7789999842643738},{"id":"https://openalex.org/keywords/crystal-structure","display_name":"crystal structure","score":0.6620000004768372},{"id":"https://openalex.org/keywords/language-models","display_name":"language models","score":0.5550000071525574},{"id":"https://openalex.org/keywords/inverse-materials-design","display_name":"inverse materials design","score":0.8309999704360962},{"id":"https://openalex.org/keywords/semantic-alignment","display_name":"semantic alignment","score":0.5299999713897705},{"id":"https://openalex.org/keywords/embedding-space-analysis","display_name":"embedding space analysis","score":0.41999998688697815}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6565999984741211},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.6237999796867371},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5867999792098999},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5304999947547913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47620001435279846},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40230000019073486},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.29910001158714294},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2937000095844269},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.2572000026702881}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1038/s41467-026-76378-7","doi":"https://doi.org/10.1038/s41467-026-76378-7","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41467-026-76378-7","pdf_url":"https://www.nature.com/articles/s41467-026-76378-7_reference.pdf","source":{"id":"https://openalex.org/S64187185","display_name":"Nature Communications","issn_l":"2041-1723","issn":["2041-1723"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-a","doyens","jufo-3","ki-jl-3","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Communications","raw_type":"journal-article"},{"id":"pmid:42802153","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42802153","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature communications","raw_type":"Journal Article"},{"id":"pmh:oai:doaj.org/article:192c9a172fd543cd8a79dda6cad44204","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/192c9a172fd543cd8a79dda6cad44204","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Nature Communications, Vol 17, Iss 1 (2026)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13616920","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13616920/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13616920/pdf/41467_2026_Article_76378.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"Nat Commun","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1038/s41467-026-76378-7","doi":"https://doi.org/10.1038/s41467-026-76378-7","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41467-026-76378-7","pdf_url":"https://www.nature.com/articles/s41467-026-76378-7_reference.pdf","source":{"id":"https://openalex.org/S64187185","display_name":"Nature Communications","issn_l":"2041-1723","issn":["2041-1723"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-a","doyens","jufo-3","ki-jl-3","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Communications","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6541015203","display_name":null,"funder_award_id":"HDTRA1","funder_id":"https://openalex.org/F4320332186","funder_display_name":"Defense Threat Reduction Agency"},{"id":"https://openalex.org/G6769886497","display_name":null,"funder_award_id":"RS-2026-25497753","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G772299097","display_name":null,"funder_award_id":"HDTRA12-02-0002","funder_id":"https://openalex.org/F4320332186","funder_display_name":"Defense Threat Reduction Agency"},{"id":"https://openalex.org/G8670235621","display_name":null,"funder_award_id":"HR00112490369","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G973822236","display_name":null,"funder_award_id":"HDTRA1-20-2-0002","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322091","display_name":"Korea Institute of Science and Technology","ror":"https://ror.org/05kzfa883"},{"id":"https://openalex.org/F4320322105","display_name":"Korea Institute of Science and Technology Information","ror":"https://ror.org/01k4yrm29"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332186","display_name":"Defense Threat Reduction Agency","ror":"https://ror.org/04tz64554"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337144","display_name":"National Supercomputing Center, Korea Institute of Science and Technology Information","ror":"https://ror.org/00cs28a13"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204272178.pdf","grobid_xml":"https://content.openalex.org/works/W7204272178.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Artificial":[0],"intelligence":[1],"is":[2,134],"increasingly":[3],"applied":[4],"to":[5],"inverse":[6],"materials":[7,34],"design,":[8],"including":[9],"crystals":[10],"and":[11,40,47,118],"molecules.":[12],"For":[13],"molecular":[14],"systems,":[15],"multimodal":[16,64],"models":[17,94],"that":[18,68,139],"integrate":[19],"chemical":[20],"structures":[21,71,142],"with":[22,72,93,107,143,156],"natural":[23,73,144],"language":[24,86,117,145],"have":[25],"enabled":[26],"flexible,":[27],"instruction-driven":[28,128],"reasoning.":[29],"However,":[30],"approaches":[31],"for":[32,126],"crystalline":[33,131],"remain":[35],"limited":[36],"by":[37,53,85],"the":[38,48],"scarcity":[39],"imbalanced":[41],"bias":[42],"of":[43,80],"available":[44],"crystal":[45,70,81,119,141],"datasets":[46],"weak":[49],"semantic":[50,104],"supervision":[51,102],"provided":[52],"peer-reviewed":[54],"literature.":[55],"We":[56],"introduce":[57],"a":[58,63,124,135],"contrastive":[59,65,136],"language-crystals":[60,137],"model":[61,138],"(CLaC),":[62],"learning":[66],"framework":[67],"aligns":[69,140],"language,":[74],"pre-trained":[75],"on":[76,96],"property-conditioned":[77,147],"synthetic":[78,101,148],"narratives":[79],"structure-text":[82],"pairs":[83],"generated":[84],"models.":[87],"Here":[88],"we":[89],"show":[90],"that,":[91],"compared":[92],"trained":[95],"literature-derived":[97,157],"text,":[98],"this":[99],"property-grounded":[100],"enables":[103],"alignment":[105],"unachievable":[106,155],"existing":[108],"academic":[109],"corpora.":[110],"Embedding-space":[111],"analyses":[112],"reveal":[113],"structured":[114],"associations":[115],"between":[116],"structures.":[120],"These":[121],"results":[122],"establish":[123],"foundation":[125],"zero-shot,":[127,151],"reasoning":[129,154],"in":[130],"materials.":[132],"CLaC":[133],"using":[146],"narratives,":[149],"enabling":[150],"instruction":[152],"driven":[153],"text":[158],"alone.":[159]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2026-08-27T00:00:00"}