{"id":"https://openalex.org/W7154984405","doi":"https://doi.org/10.48550/arxiv.2604.15821","title":"Breaking the Training Barrier of Billion-Parameter Universal Machine Learning Interatomic Potentials","display_name":"Breaking the Training Barrier of Billion-Parameter Universal Machine Learning Interatomic Potentials","publication_year":2026,"publication_date":"2026-04-17","ids":{"openalex":"https://openalex.org/W7154984405","doi":"https://doi.org/10.48550/arxiv.2604.15821"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.15821","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.15821","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.15821","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134086265","display_name":"Yuanchang Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Yuanchang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134053474","display_name":"Hongyu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Hongyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134060702","display_name":"Yiming Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Yiming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134014255","display_name":"Yan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134056494","display_name":"Mingzhen Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Mingzhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134045276","display_name":"Siyu Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Siyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134018361","display_name":"Xiangyu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xiangyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134051065","display_name":"Weijian Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Weijian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134028500","display_name":"Chen Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007580762","display_name":"Zhuoqiang Guo","orcid":"https://orcid.org/0000-0001-9418-3861"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Zhuoqiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134038981","display_name":"Long Wang","orcid":"https://orcid.org/0000-0003-3443-0626"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Long","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134075322","display_name":"Jingde Bu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bu, Jingde","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134061448","display_name":"Yutong Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Yutong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134079977","display_name":"Guangming Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Guangming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134010287","display_name":"Weile Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia, Weile","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.9921000003814697,"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":0.9921000003814697,"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/T11804","display_name":"Quantum many-body systems","score":0.003800000064074993,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10002","display_name":"Advanced Chemical Physics Studies","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.628000020980835},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5805000066757202},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5637999773025513},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5583999752998352},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5095999836921692},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.39329999685287476},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.38449999690055847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6610000133514404},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.628000020980835},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5805000066757202},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5637999773025513},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5583999752998352},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5095999836921692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5070000290870667},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4147999882698059},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.40230000019073486},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.39329999685287476},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.38449999690055847},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.35670000314712524},{"id":"https://openalex.org/C2778837361","wikidata":"https://www.wikidata.org/wiki/Q2450880","display_name":"Exascale computing","level":3,"score":0.3409999907016754},{"id":"https://openalex.org/C154238967","wikidata":"https://www.wikidata.org/wiki/Q12870","display_name":"Explosive material","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.31610000133514404},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28679999709129333},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C2776372370","wikidata":"https://www.wikidata.org/wiki/Q3399989","display_name":"Interatomic potential","level":3,"score":0.2554999887943268},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.15821","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.15821","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"doi:10.48550/arxiv.2604.15821","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.15821","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.6496198177337646,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Universal":[0],"Machine":[1],"Learning":[2],"Interatomic":[3],"Potentials":[4],"(uMLIPs),":[5],"pre-trained":[6],"on":[7],"massively":[8],"diverse":[9],"datasets":[10],"encompassing":[11],"inorganic":[12],"materials":[13],"and":[14,53,73,136],"organic":[15],"molecules":[16],"across":[17,87],"the":[18,45,113],"entire":[19],"periodic":[20],"table,":[21],"serve":[22],"as":[23],"foundational":[24],"models":[25,133],"for":[26,81,129,140],"quantum-accurate":[27],"physical":[28],"simulations.":[29],"However,":[30],"uMLIP":[31],"training":[32,40,58,79,114],"requires":[33],"second-order":[34],"derivatives,":[35],"which":[36],"lack":[37],"corresponding":[38],"parallel":[39,110],"frameworks;":[41],"moreover,":[42],"scaling":[43],"to":[44,120],"billion-parameter":[46,66,116],"regime":[47],"causes":[48],"explosive":[49],"growth":[50],"in":[51,104],"computation":[52],"communication":[54],"overhead,":[55],"making":[56],"its":[57],"a":[59,65,75,94,125],"tremendous":[60],"challenge.":[61],"We":[62],"introduce":[63],"MatRIS-MoE,":[64],"Mixture-of-Experts":[67],"model":[68],"built":[69],"upon":[70],"invariant":[71],"architecture,":[72],"{Janus},":[74],"pioneering":[76],"high-dimensional":[77],"distributed":[78],"framework":[80],"uMLIPs":[82,117],"with":[83],"hardware-aware":[84],"optimizations.":[85],"Deployed":[86],"two":[88],"Exascale":[89,135],"supercomputers,":[90],"our":[91],"code":[92],"attains":[93],"peak":[95],"performance":[96],"of":[97,101,115],"1.2/1.0":[98],"EFLOPS":[99],"(24\\%/{35.5\\%}":[100],"theoretical":[102],"peak)":[103],"single":[105],"precision":[106],"at":[107,134],"over":[108],"90\\%":[109],"efficiency,":[111],"compressing":[112],"from":[118],"weeks":[119],"hours.":[121],"This":[122],"work":[123],"establishes":[124],"new":[126],"high-water":[127],"mark":[128],"AI-for-Science":[130],"(AI4S)":[131],"foundation":[132],"provides":[137],"essential":[138],"infrastructure":[139],"rapid":[141],"scientific":[142],"discovery.":[143]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-21T00:00:00"}