{"id":"https://openalex.org/W7128314745","doi":"https://doi.org/10.36227/techrxiv.177042078.81811026/v1","title":"Foundation Models for Scientific Discovery: A Survey of Modalities, Architectures, and Pre-training Paradigms","display_name":"Foundation Models for Scientific Discovery: A Survey of Modalities, Architectures, and Pre-training Paradigms","publication_year":2026,"publication_date":"2026-02-06","ids":{"openalex":"https://openalex.org/W7128314745","doi":"https://doi.org/10.36227/techrxiv.177042078.81811026/v1"},"language":"en","primary_location":{"id":"doi:10.36227/techrxiv.177042078.81811026/v1","doi":"https://doi.org/10.36227/techrxiv.177042078.81811026/v1","is_oa":true,"landing_page_url":"https://doi.org/10.36227/techrxiv.177042078.81811026/v1","pdf_url":"https://www.techrxiv.org/doi/pdf/10.36227/techrxiv.177042078.81811026/v1","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.techrxiv.org/doi/pdf/10.36227/techrxiv.177042078.81811026/v1","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036734523","display_name":"Pinlong Zhao","orcid":"https://orcid.org/0000-0002-3161-5003","observed_orcids":["https://orcid.org/0000-0002-3161-5003"]},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Pinlong Zhao","raw_affiliation_strings":["School of Cyberspace, Hangzhou Dianzi University"],"raw_orcid":"https://orcid.org/0000-0002-3161-5003","affiliations":[{"raw_affiliation_string":"School of Cyberspace, Hangzhou Dianzi University","institution_ids":["https://openalex.org/I50760025"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5036734523"],"corresponding_institution_ids":["https://openalex.org/I50760025"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.8345000147819519,"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":0.8345000147819519,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.060600001364946365,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear 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/T13904","display_name":"Artificial Intelligence Applications","score":0.05570000037550926,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/foundation-models","display_name":"foundation models","score":0.902999997138977},{"id":"https://openalex.org/keywords/scientific-discovery","display_name":"scientific discovery","score":0.9539999961853027},{"id":"https://openalex.org/keywords/data-modalities","display_name":"data modalities","score":0.6660000085830688},{"id":"https://openalex.org/keywords/model-architecture","display_name":"model architecture","score":0.9750000238418579},{"id":"https://openalex.org/keywords/physics-informed-machine-learning","display_name":"physics-informed machine learning","score":0.7950000166893005},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.6499999761581421},{"id":"https://openalex.org/keywords/data-scarcity","display_name":"data scarcity","score":0.7960000038146973}],"concepts":[{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.5841000080108643},{"id":"https://openalex.org/C55587333","wikidata":"https://www.wikidata.org/wiki/Q1133029","display_name":"Engineering ethics","level":1,"score":0.49720001220703125},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.39399999380111694},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.33550000190734863},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3188999891281128},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2361000031232834},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.22290000319480896},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.22190000116825104},{"id":"https://openalex.org/C195732255","wikidata":"https://www.wikidata.org/wiki/Q981008","display_name":"Sociology of scientific knowledge","level":2,"score":0.21799999475479126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.36227/techrxiv.177042078.81811026/v1","doi":"https://doi.org/10.36227/techrxiv.177042078.81811026/v1","is_oa":true,"landing_page_url":"https://doi.org/10.36227/techrxiv.177042078.81811026/v1","pdf_url":"https://www.techrxiv.org/doi/pdf/10.36227/techrxiv.177042078.81811026/v1","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.36227/techrxiv.177042078.81811026/v1","doi":"https://doi.org/10.36227/techrxiv.177042078.81811026/v1","is_oa":true,"landing_page_url":"https://doi.org/10.36227/techrxiv.177042078.81811026/v1","pdf_url":"https://www.techrxiv.org/doi/pdf/10.36227/techrxiv.177042078.81811026/v1","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.4583337604999542,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7128314745.pdf","grobid_xml":"https://content.openalex.org/works/W7128314745.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7169808136","https://openalex.org/W4392598384","https://openalex.org/W4415877562","https://openalex.org/W4414989992","https://openalex.org/W7121385775","https://openalex.org/W4413743541","https://openalex.org/W4409982896","https://openalex.org/W4404782812","https://openalex.org/W7168100775","https://openalex.org/W4321501196"],"abstract_inverted_index":{"The":[0],"integration":[1],"of":[2,16,59,85,151],"artificial":[3],"intelligence":[4],"with":[5,13,122],"scientific":[6,40,63,105],"discovery":[7],"has":[8],"entered":[9],"a":[10,56,67],"transformative":[11],"era":[12],"the":[14],"emergence":[15],"foundation":[17,60,138],"models.":[18],"These":[19],"large-scale":[20],"pre-trained":[21],"models,":[22,87],"characterized":[23],"by":[24],"their":[25],"ability":[26],"to":[27,95],"transfer":[28],"knowledge":[29],"across":[30],"diverse":[31],"tasks":[32],"and":[33,46,79,99,119,136],"domains,":[34],"are":[35],"revolutionizing":[36],"how":[37,90],"we":[38,88,127,146],"approach":[39],"problems":[41],"in":[42,62],"physics,":[43],"chemistry,":[44],"biology,":[45],"materials":[47],"science.":[48,141],"Moving":[49],"beyond":[50],"application-centric":[51],"overviews,":[52],"this":[53],"survey":[54],"offers":[55],"methodologically-driven":[57],"analysis":[58,84],"models":[61,139],"discovery.":[64],"We":[65,107],"propose":[66],"systematic":[68],"taxonomy":[69],"organized":[70],"along":[71],"three":[72,92],"orthogonal":[73],"dimensions:":[74],"data":[75,113],"modality,":[76],"model":[77,97],"architecture,":[78],"pre-training":[80],"paradigm.":[81],"Through":[82],"detailed":[83],"representative":[86],"examine":[89],"these":[91],"dimensions":[93],"interact":[94],"determine":[96],"capabilities,":[98],"identify":[100],"effective":[101],"combinations":[102],"for":[103,140],"different":[104],"tasks.":[106],"further":[108],"discuss":[109],"critical":[110],"challenges":[111],"including":[112],"scarcity,":[114],"physical":[115],"constraint":[116],"integration,":[117],"interpretability,":[118],"computational":[120],"accessibility,":[121],"concrete":[123],"technical":[124],"recommendations.":[125],"Finally,":[126],"outline":[128],"actionable":[129],"future":[130],"directions":[131],"toward":[132],"more":[133],"general,":[134],"physics-informed,":[135],"interpretable":[137],"To":[142],"facilitate":[143],"ongoing":[144],"research,":[145],"release":[147],"an":[148],"up-todate":[149],"repository":[150],"resources":[152],"at":[153],"https://github.com/":[154],"Pinlong-Zhao/Scientific-Foundation-Models.":[155]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-09T00:00:00"}