{"id":"https://openalex.org/W7167822818","doi":"https://doi.org/10.48550/arxiv.2607.07647","title":"Are Machine Learning Interatomic Potentials Truly Practical? A Benchmark of 23 Mainstream Models","display_name":"Are Machine Learning Interatomic Potentials Truly Practical? A Benchmark of 23 Mainstream Models","publication_year":2026,"publication_date":"2026-07-08","ids":{"openalex":"https://openalex.org/W7167822818","doi":"https://doi.org/10.48550/arxiv.2607.07647"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.07647","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.07647","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2607.07647","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109445912","display_name":"H. Kang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kang, Hanwen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140372429","display_name":"Tenglong Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Tenglong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140355766","display_name":"Sheng Meng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Sheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5140356561","display_name":"Miao Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Miao","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":0.8833000063896179,"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":0.8833000063896179,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.013100000098347664,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.006300000008195639,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8529000282287598},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7990999817848206},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.682699978351593},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.6284000277519226},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4869000017642975},{"id":"https://openalex.org/keywords/reboot","display_name":"Reboot","score":0.45329999923706055},{"id":"https://openalex.org/keywords/pareto-principle","display_name":"Pareto principle","score":0.3896999955177307}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8529000282287598},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7990999817848206},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.682699978351593},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6628000140190125},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.6284000277519226},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5986999869346619},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4927999973297119},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4869000017642975},{"id":"https://openalex.org/C120524526","wikidata":"https://www.wikidata.org/wiki/Q1709148","display_name":"Reboot","level":2,"score":0.45329999923706055},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.3896999955177307},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30660000443458557},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.30250000953674316},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C2777617010","wikidata":"https://www.wikidata.org/wiki/Q18957","display_name":"Mainstream","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C2986314615","wikidata":"https://www.wikidata.org/wiki/Q36829","display_name":"Pareto optimal","level":3,"score":0.251800000667572},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.07647","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.07647","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2607.07647","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.07647","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,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Most":[0],"MLIP":[1,132],"benchmarks":[2,125],"reward":[3],"static":[4],"accuracy":[5,83],"while":[6],"ignoring":[7],"inference":[8],"efficiency":[9,136],"and":[10,65,115,129,137],"hardware":[11],"scalability":[12,138],"--":[13,94],"driving":[14],"model":[15],"bloat":[16],"with":[17],"unclear":[18],"real-world":[19],"value.":[20],"We":[21,56],"benchmark":[22],"23":[23],"mainstream":[24],"open-source":[25],"MLIPs":[26],"on":[27,111,117],"a":[28,47,52,71],"low-cost":[29],"NVIDIA":[30],"DGX":[31],"Spark":[32],"(128":[33],"GB":[34,40],"native":[35],"memory,":[36],"capped":[37],"at":[38],"80":[39],"to":[41],"mimic":[42],"ordinary":[43],"lab":[44],"hardware),":[45],"using":[46],"fixed":[48],"192-atom":[49],"system":[50],"under":[51],"unified":[53],"ASE-based":[54],"pipeline.":[55],"evaluate":[57],"three":[58],"dimensions:":[59],"predictive":[60],"accuracy,":[61],"MD":[62],"simulation":[63],"throughput,":[64],"atomic":[66],"scalability.":[67],"Our":[68],"results":[69],"expose":[70],"sharp":[72],"accuracy-efficiency":[73],"trade-off:":[74],"large":[75],"SOTA":[76],"models":[77],"deliver":[78],"only":[79,100],"3-5":[80],"meV/atom":[81],"more":[82],"than":[84,103],"lightweight":[85],"ones,":[86],"but":[87],"lose":[88],"orders":[89],"of":[90],"magnitude":[91],"in":[92,95],"throughput":[93],"the":[96,112,127],"worst":[97],"case,":[98],"becoming":[99],"marginally":[101],"faster":[102],"DFT":[104],"itself.":[105],"Lightweight":[106],"MLIPs,":[107],"by":[108],"contrast,":[109],"sit":[110],"Pareto":[113],"frontier":[114],"run":[116],"modest":[118],"hardware.":[119],"The":[120],"lesson":[121],"is":[122],"that":[123,130],"single-dimensional":[124],"mislead":[126],"field,":[128],"future":[131],"development":[133],"should":[134],"value":[135],"alongside":[139],"accuracy.":[140]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-10T00:00:00"}