{"id":"https://openalex.org/W7161194482","doi":"https://doi.org/10.48550/arxiv.2605.13711","title":"MILM: Large Language Models for Multimodal Irregular Time Series with Informative Sampling","display_name":"MILM: Large Language Models for Multimodal Irregular Time Series with Informative Sampling","publication_year":2026,"publication_date":"2026-05-13","ids":{"openalex":"https://openalex.org/W7161194482","doi":"https://doi.org/10.48550/arxiv.2605.13711"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.13711","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13711","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":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.2605.13711","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136120815","display_name":"Hsing-Huan Chung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chung, Hsing-Huan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136156954","display_name":"Shijun Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Shijun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034731139","display_name":"Yoav Wald","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wald, Yoav","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136104371","display_name":"Xing Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Xing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136174851","display_name":"Suchi Saria","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saria, Suchi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136144576","display_name":"Joydeep Ghosh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ghosh, Joydeep","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/T13702","display_name":"Machine Learning in Healthcare","score":0.9710000157356262,"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"}},"topics":[{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9710000157356262,"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"}},{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.01590000092983246,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.0007999999797903001,"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/sampling","display_name":"Sampling (signal processing)","score":0.6650000214576721},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6092000007629395},{"id":"https://openalex.org/keywords/series","display_name":"Series (stratigraphy)","score":0.5626999735832214},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5615000128746033},{"id":"https://openalex.org/keywords/time-series","display_name":"Time series","score":0.5590999722480774},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.48249998688697815},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4706000089645386},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.46480000019073486},{"id":"https://openalex.org/keywords/timestamp","display_name":"Timestamp","score":0.4325000047683716},{"id":"https://openalex.org/keywords/carry","display_name":"Carry (investment)","score":0.4244000017642975}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.805400013923645},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6650000214576721},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6092000007629395},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.5626999735832214},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5615000128746033},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.5590999722480774},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.48249998688697815},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4706000089645386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4699999988079071},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46480000019073486},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.4325000047683716},{"id":"https://openalex.org/C2776299755","wikidata":"https://www.wikidata.org/wiki/Q432449","display_name":"Carry (investment)","level":2,"score":0.4244000017642975},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4162999987602234},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38839998841285706},{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.3779999911785126},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.37610000371932983},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3206999897956848},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.2856000065803528},{"id":"https://openalex.org/C9395851","wikidata":"https://www.wikidata.org/wiki/Q177929","display_name":"Stack (abstract data type)","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2702000141143799},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C2985139394","wikidata":"https://www.wikidata.org/wiki/Q49908","display_name":"Sampling scheme","level":3,"score":0.26589998602867126},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2563000023365021},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.2547999918460846},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.13711","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13711","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":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.2605.13711","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13711","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5068914890289307}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"irregular":[1,28,35],"time":[2,76,200],"series":[3,77],"(MITS)":[4],"consist":[5],"of":[6,40,203],"asynchronous":[7],"and":[8,15,31,37,49,68,92,116,129,136,144,163,201],"irregularly":[9],"sampled":[10],"observations":[11,41,205],"from":[12,112],"heterogeneous":[13,59],"numerical":[14,47,69],"textual":[16,50,67],"channels.":[17],"In":[18,170],"healthcare,":[19],"for":[20,56,100],"example,":[21],"patients'":[22],"electronic":[23],"health":[24],"records":[25],"(EHR)":[26],"include":[27],"lab":[29],"measurements":[30],"clinical":[32],"notes.":[33],"The":[34,103],"timing":[36],"channel":[38,202],"patterns":[39,114,128,159],"carry":[42,160],"predictive":[43,161],"signal":[44,162],"alongside":[45],"the":[46,117,142,171,199],"values":[48,179],"content.":[51],"LLMs":[52],"are":[53,180],"natural":[54],"candidates":[55],"processing":[57],"such":[58],"data,":[60],"given":[61],"their":[62],"extensive":[63],"pretrained":[64],"knowledge":[65],"spanning":[66],"domains.":[70],"We":[71],"introduce":[72],"MILM":[73],"(Multimodal":[74],"Irregular":[75],"Language":[78,89],"Model),":[79],"which":[80],"represents":[81],"MITS":[82,101,109,123],"as":[83,206],"time-ordered":[84],"triplets":[85],"in":[86],"Extensible":[87],"Markup":[88],"(XML)":[90],"format":[91],"fine-tunes":[93],"an":[94],"LLM":[95],"through":[96],"a":[97,189],"two-stage":[98,133],"strategy":[99],"classification.":[102],"first":[104],"stage":[105,119],"trains":[106,120],"on":[107,121,148],"value-redacted":[108],"to":[110,124,167,193],"predict":[111],"sampling":[113,127,158,208],"alone,":[115],"second":[118],"full":[122],"jointly":[125],"model":[126,134],"observed":[130],"values.":[131],"Our":[132],"(MILM-2S)":[135],"its":[137],"single-stage":[138],"counterpart":[139],"(MILM-Direct)":[140],"achieve":[141],"best":[143],"second-best":[145],"average":[146],"performance":[147],"multiple":[149],"EHR":[150],"datasets.":[151],"Further":[152],"value":[153,172],"redaction":[154],"evaluations":[155],"confirm":[156],"that":[157,164],"MILM-2S":[165,185],"learns":[166],"exploit":[168],"them.":[169],"pending":[173],"evaluation":[174],"we":[175],"introduce,":[176],"where":[177],"some":[178],"unavailable":[181],"at":[182],"prediction":[183],"time,":[184],"outperforms":[186],"MILM-Direct":[187],"by":[188],"larger":[190],"margin":[191],"compared":[192],"standard":[194],"evaluation.":[195],"For":[196],"MILM-2S,":[197],"preserving":[198],"value-pending":[204],"additional":[207],"information":[209],"further":[210],"improves":[211],"in-hospital":[212],"mortality":[213],"prediction.":[214]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-15T00:00:00"}