{"id":"https://openalex.org/W7130433105","doi":"https://doi.org/10.48550/arxiv.2602.15084","title":"TokaMind: A Multi-Modal Transformer Foundation Model for Tokamak Plasma Dynamics","display_name":"TokaMind: A Multi-Modal Transformer Foundation Model for Tokamak Plasma Dynamics","publication_year":2026,"publication_date":"2026-02-16","ids":{"openalex":"https://openalex.org/W7130433105","doi":"https://doi.org/10.48550/arxiv.2602.15084"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.15084","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.15084","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2602.15084","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106864191","display_name":"Tobia Boschi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Boschi, Tobia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125699797","display_name":"Andrea Loreti","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Loreti, Andrea","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076385727","display_name":"N. C. Amorisco","orcid":"https://orcid.org/0000-0002-3205-5335"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amorisco, Nicola C.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126285800","display_name":"Rodrigo H. Ordonez-Hurtado","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ordonez-Hurtado, Rodrigo H.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125687958","display_name":"C\u00e9cile Rousseau","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rousseau, C\u00e9cile","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041831295","display_name":"George K. Holt","orcid":"https://orcid.org/0000-0001-6814-9117"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Holt, George K.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125723603","display_name":"Eszter Sz\u00e9kely","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sz\u00e9kely, Eszter","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004032338","display_name":"Alexander Whittle","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Whittle, Alexander","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102885809","display_name":"Samuel Jackson","orcid":"https://orcid.org/0000-0001-5301-5095"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jackson, Samuel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087824287","display_name":"Adriano Agnello","orcid":"https://orcid.org/0000-0001-9775-0331"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Agnello, Adriano","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126278147","display_name":"Stanislas Pamela","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pamela, Stanislas","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126295025","display_name":"Alessandra Pascale","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pascale, Alessandra","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032151699","display_name":"R. Akers","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Akers, Robert","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108514955","display_name":"Jaime H. Moreno","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moreno, Juan Bernabe","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013084939","display_name":"Vassil Alexandrov","orcid":"https://orcid.org/0000-0002-4889-1207"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexandrov, Vassil","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5014090110","display_name":"Mykhaylo Zayats","orcid":"https://orcid.org/0009-0000-6090-6937"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zayats, Mykhaylo","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":16,"corresponding_author_ids":["https://openalex.org/A5106864191"],"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/T10346","display_name":"Magnetic confinement fusion research","score":0.9004999995231628,"subfield":{"id":"https://openalex.org/subfields/3106","display_name":"Nuclear and High Energy Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10346","display_name":"Magnetic confinement fusion research","score":0.9004999995231628,"subfield":{"id":"https://openalex.org/subfields/3106","display_name":"Nuclear and High Energy Physics"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.007799999788403511,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.0034000000450760126,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/tokamak","display_name":"Tokamak","score":0.7462000250816345},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6481000185012817},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.545799970626831},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5026000142097473},{"id":"https://openalex.org/keywords/plasma","display_name":"Plasma","score":0.3684999942779541},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.3529999852180481}],"concepts":[{"id":"https://openalex.org/C116515362","wikidata":"https://www.wikidata.org/wiki/Q188589","display_name":"Tokamak","level":3,"score":0.7462000250816345},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6481000185012817},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5666000247001648},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.545799970626831},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5026000142097473},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3865000009536743},{"id":"https://openalex.org/C82706917","wikidata":"https://www.wikidata.org/wiki/Q10251","display_name":"Plasma","level":2,"score":0.3684999942779541},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3662000000476837},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.33719998598098755},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.250900000333786},{"id":"https://openalex.org/C24671956","wikidata":"https://www.wikidata.org/wiki/Q641442","display_name":"Fusion power","level":3,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.15084","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.15084","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2602.15084","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.15084","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":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5844278335571289}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,85],"present":[1],"TokaMind,":[2],"an":[3],"open-source":[4],"foundation":[5,154],"model":[6,57,163],"framework":[7],"for":[8,77,117,145,155],"fusion":[9,157],"plasma":[10,147],"modeling,":[11],"based":[12],"on":[13,20,88,110],"a":[14,65,74,133,151],"Multi-Modal":[15],"Transformer":[16],"(MMT)":[17],"and":[18,38,47,54,72,97,115,149,162],"trained":[19],"heterogeneous":[21],"tokamak":[22,146],"diagnostics":[23],"from":[24,130],"the":[25,89,107,127,140],"publicly":[26,168],"available":[27],"MAST":[28,92],"dataset.":[29],"TokaMind":[30,87,105],"supports":[31],"multiple":[32],"data":[33],"modalities":[34],"(time-series,":[35],"2D":[36],"profiles,":[37],"videos)":[39],"with":[40],"different":[41],"sampling":[42],"rates,":[43],"robust":[44],"missing-signal":[45],"handling,":[46],"efficient":[48],"task":[49],"adaptation":[50],"via":[51],"selectively":[52],"loading":[53],"freezing":[55],"four":[56],"components.":[58],"To":[59],"represent":[60],"multi-modal":[61,143],"signals,":[62],"we":[63],"use":[64],"training-free":[66],"Discrete":[67],"Cosine":[68],"Transform":[69],"embedding":[70,98],"(DCT3D)":[71],"provide":[73,150],"clean":[75],"interface":[76],"alternative":[78],"embeddings":[79],"(e.g.,":[80],"Variational":[81],"Autoencoders":[82],"-":[83],"VAEs).":[84],"evaluate":[86],"recently":[90],"introduced":[91],"benchmark":[93,108],"TokaMark,":[94],"comparing":[95],"training":[96,126],"strategies.":[99],"Our":[100],"results":[101],"show":[102],"that":[103],"fine-tuned":[104],"outperforms":[106],"baseline":[109],"all":[111],"but":[112],"one":[113],"task,":[114],"that,":[116],"several":[118],"tasks,":[119],"lightweight":[120],"fine-tuning":[121],"yields":[122],"better":[123],"performance":[124],"than":[125],"same":[128],"architecture":[129],"scratch":[131],"under":[132],"matched":[134],"epoch":[135],"budget.":[136],"These":[137],"findings":[138],"highlight":[139],"benefits":[141],"of":[142],"pretraining":[144],"dynamics":[148],"practical,":[152],"extensible":[153],"future":[156],"modeling":[158],"tasks.":[159],"Training":[160],"code":[161],"weights":[164],"will":[165],"be":[166],"made":[167],"available.":[169]},"counts_by_year":[],"updated_date":"2026-02-19T06:31:58.851227","created_date":"2026-02-19T00:00:00"}