{"id":"https://openalex.org/W7162779559","doi":"https://doi.org/10.48550/arxiv.2605.29401","title":"Rethinking Post-Training Recipes for Multimodal Time-Series Forecasting","display_name":"Rethinking Post-Training Recipes for Multimodal Time-Series Forecasting","publication_year":2026,"publication_date":"2026-05-28","ids":{"openalex":"https://openalex.org/W7162779559","doi":"https://doi.org/10.48550/arxiv.2605.29401"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.29401","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29401","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":"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.2605.29401","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137323462","display_name":"Haoxin Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Haoxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137371906","display_name":"Yichen Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Yichen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137392924","display_name":"Rajat Sen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sen, Rajat","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137377442","display_name":"B. Aditya Prakash","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prakash, B. Aditya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101056045","display_name":"Abhimanyu Das","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Das, Abhimanyu","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/T11918","display_name":"Forecasting Techniques and Applications","score":0.5012999773025513,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11918","display_name":"Forecasting Techniques and Applications","score":0.5012999773025513,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.11339999735355377,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.03660000115633011,"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/context","display_name":"Context (archaeology)","score":0.6205999851226807},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5698999762535095},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.489300012588501},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4867999851703644},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.3871000111103058},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.3677999973297119}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6559000015258789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6258999705314636},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6205999851226807},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5928999781608582},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5698999762535095},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.489300012588501},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4867999851703644},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.3677999973297119},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.28839999437332153},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2827000021934509},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.26489999890327454},{"id":"https://openalex.org/C193809577","wikidata":"https://www.wikidata.org/wiki/Q3409300","display_name":"Demand forecasting","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.29401","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29401","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":"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.2605.29401","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29401","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":"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Time-Series":[0],"Foundation":[1],"Models":[2],"(TSFMs)":[3],"excel":[4],"at":[5],"zero-shot":[6],"unimodal":[7],"forecasting":[8,39,115,137],"using":[9,117],"numerical":[10,51],"data,":[11],"but":[12],"unlike":[13],"LLMs":[14,43],"they":[15],"cannot":[16],"consume":[17],"multimodal,":[18],"non-numerical":[19],"context":[20],"that":[21,41,126],"often":[22],"shape":[23],"real-world":[24],"trajectories.":[25],"In":[26],"this":[27,31,109],"work,":[28],"we":[29],"bridge":[30],"gap":[32],"and":[33,64,121,124,134],"argue":[34],"for":[35,80],"a":[36,57,73,118],"multimodal":[37,105,114,136],"time-series":[38],"approach":[40,110],"post-trains":[42],"to":[44,75,87,94],"act":[45],"as":[46],"context-guided":[47],"revisors":[48],"over":[49],"strong":[50],"TSFM":[52,100],"priors.":[53],"We":[54,107],"introduce":[55],"PostTime,":[56],"post-training":[58],"recipe":[59],"combining":[60],"Supervised":[61],"Fine-Tuning":[62],"(SFT)":[63],"Reinforcement":[65],"Learning":[66],"with":[67,72],"Verifiable":[68],"Rewards":[69],"(RLVR),":[70],"along":[71],"methodology":[74],"generate":[76,88],"automated":[77],"reasoning":[78],"traces":[79],"forecast":[81,90],"revisions.":[82],"PostTime":[83],"teaches":[84],"an":[85],"LLM":[86,120],"context-conditioned":[89],"interventions":[91],"--":[92],"decisions":[93],"revise,":[95],"preserve,":[96],"or":[97],"ignore":[98],"the":[99,104,112],"prior":[101],"based":[102],"on":[103,111],"context.":[106],"evaluate":[108],"TimesX":[113],"benchmark":[116],"Gemma-3-4B":[119],"TimesFM-2.5":[122],"TSFM,":[123],"show":[125],"it":[127],"significantly":[128],"outperforms":[129],"standalone":[130],"TSFMs,":[131],"LLM-only":[132],"baselines,":[133],"existing":[135],"approaches.":[138]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-30T00:00:00"}