Accurate property characterization is a major bottleneck in materials design. While first-principles methods and task-specific machine-learning models have driven important progress, they remain fundamentally limited in scalability and generalizability across the vast space of structures and properties relevant to real-world materials design. We present MatterSim-MT, a multi-task foun\u0002dation model for in silico materials simulation and property characterization. The model is pretrained on over 35 million first-principles-labeled structures covering 89 elements, temperatures up to 5000 K and pressures up to 1000 GPa, and is fine-tuned on various properties including Bader charges, magnetic moments, Born effective charges, and dielectric matrices. Out of the box, MatterSim-MT not only serves as a foundation model for predicting material structure, dynamics and thermodynamics, its multi-task architecture also enables a wide range of complex simula\u0002tions that cannot be captured by potential energy surfaces alone. For example, we demonstrate pressure-dependent LO-TO phonon splitting in SiC with close agreement with experiment, electric hysteresis in ferroelectric BaTiO3, and the cationic-to-anionic redox transition during delithiation of a Li-rich cathode material. Finally, we show that MatterSim-MT scales well with more data and parameters, can be efficiently fine-tuned to higher levels of theory, and can be efficiently extended to new systems via active learning. Overall, we believe this approach provides a scalable route to accurate in silico materials characterization.<\/p>\n","protected":false},"excerpt":{"rendered":"
Accurate property characterization is a major bottleneck in materials design. While first-principles methods and task-specific machine-learning models have driven important progress, they remain fundamentally limited in scalability and generalizability across the vast space of structures and properties relevant to real-world materials design. We present MatterSim-MT, a multi-task foun\u0002dation model for in silico materials simulation and […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr-author-ordering":null,"msr_publishername":"","msr_publisher_other":"","msr_booktitle":"","msr_chapter":"","msr_edition":"","msr_editors":"","msr_how_published":"","msr_isbn":"","msr_issue":"","msr_journal":"","msr_number":"","msr_organization":"","msr_pages_string":"","msr_page_range_start":"","msr_page_range_end":"","msr_series":"","msr_volume":"","msr_copyright":"","msr_conference_name":"","msr_doi":"","msr_arxiv_id":"","msr_s2_paper_id":"","msr_mag_id":"","msr_pubmed_id":"","msr_other_authors":"","msr_other_contributors":"","msr_speaker":"","msr_award":"","msr_affiliation":"","msr_institution":"","msr_host":"","msr_version":"","msr_duration":"","msr_original_fields_of_study":"","msr_release_tracker_id":"","msr_s2_match_type":"","msr_citation_count_updated":"","msr_published_date":"2026-05-01","msr_highlight_text":"","msr_notes":"","msr_longbiography":"","msr_publicationurl":"","msr_external_url":"","msr_secondary_video_url":"","msr_conference_url":"","msr_journal_url":"","msr_s2_pdf_url":"","msr_year":0,"msr_citation_count":0,"msr_influential_citations":0,"msr_reference_count":0,"msr_s2_match_confidence":0,"msr_microsoftintellectualproperty":false,"msr_s2_open_access":false,"msr_s2_author_ids":[],"msr_pub_ids":[],"msr_hide_image_in_river":null,"footnotes":""},"msr-research-highlight":[],"research-area":[13556],"msr-publication-type":[193726],"msr-publisher":[],"msr-focus-area":[],"msr-locale":[268875],"msr-post-option":[269148,269142],"msr-field-of-study":[246694],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-1171344","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us","msr-post-option-approved-for-river","msr-post-option-include-in-river","msr-field-of-study-artificial-intelligence"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2026-05-01","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":0,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":"","msr_related_uploader":[{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/arxiv.org\/pdf\/2605.07927v1","label_id":"243118","label":0},{"type":"file","viewUrl":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-content\/uploads\/2026\/05\/MatterSimMT.pdf","id":"1171345","title":"mattersimmt","label_id":"243112","label":0}],"msr_citation_count":0,"msr_citation_count_updated":"","msr_s2_paper_id":"","msr_influential_citations":0,"msr_reference_count":0,"msr_arxiv_id":"","msr_s2_author_ids":[],"msr_s2_open_access":false,"msr_s2_pdf_url":null,"msr_attachments":[{"id":1171345,"url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-content\/uploads\/2026\/05\/MatterSimMT.pdf"}],"msr-author-ordering":[{"type":"user_nicename","value":"Han Yang","user_id":44006,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Han Yang"},{"type":"text","value":"Xixian Liu","user_id":0,"rest_url":false},{"type":"text","value":"Chenxi Hu","user_id":0,"rest_url":false},{"type":"text","value":"Yichi Zhou","user_id":0,"rest_url":false},{"type":"text","value":"Yu Shi","user_id":0,"rest_url":false},{"type":"text","value":"Chang Liu","user_id":0,"rest_url":false},{"type":"text","value":"Junfu Tan","user_id":0,"rest_url":false},{"type":"text","value":"Jielan Li","user_id":0,"rest_url":false},{"type":"text","value":"Guanzhi Li","user_id":0,"rest_url":false},{"type":"text","value":"Qian Wang","user_id":0,"rest_url":false},{"type":"text","value":"Yu Zhu","user_id":0,"rest_url":false},{"type":"text","value":"Zekun Chen","user_id":0,"rest_url":false},{"type":"text","value":"Shuizhou Chen","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Fabian Thiemann","user_id":44168,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Fabian Thiemann"},{"type":"user_nicename","value":"Claudio Zeni","user_id":41817,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Claudio Zeni"},{"type":"text","value":"Matthew Horton","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Robert Pinsler","user_id":41725,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Robert Pinsler"},{"type":"user_nicename","value":"Andrew Fowler","user_id":41850,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Andrew Fowler"},{"type":"user_nicename","value":"Daniel Z\u00fcgner","user_id":42990,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Daniel Z\u00fcgner"},{"type":"text","value":"Tian Xie","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Lixin Sun","user_id":41823,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Lixin Sun"},{"type":"text","value":"Yicheng Chen","user_id":0,"rest_url":false},{"type":"text","value":"Lingyu Kong","user_id":0,"rest_url":false},{"type":"text","value":"Yeqi Bai","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Deniz Gunceler","user_id":42798,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Deniz Gunceler"},{"type":"user_nicename","value":"Frank No\u00e9","user_id":42216,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Frank No\u00e9"},{"type":"text","value":"Hongxia Hao","user_id":0,"rest_url":false},{"type":"text","value":"Ziheng Lu","user_id":0,"rest_url":false}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[],"publication":[],"video":[],"msr-tool":[],"msr_publication_type":"unpublished","related_content":[],"_links":{"self":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1171344","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":1,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1171344\/revisions"}],"predecessor-version":[{"id":1171347,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1171344\/revisions\/1171347"}],"wp:attachment":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/media?parent=1171344"}],"wp:term":[{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=1171344"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=1171344"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=1171344"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=1171344"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=1171344"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=1171344"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=1171344"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=1171344"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=1171344"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=1171344"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=1171344"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=1171344"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}