{"id":"https://openalex.org/W7155563110","doi":"https://doi.org/10.48550/arxiv.2604.21032","title":"Unlocking Multi-Spectral Data for Multi-Modal Models with Guided Inputs and Chain-of-Thought Reasoning","display_name":"Unlocking Multi-Spectral Data for Multi-Modal Models with Guided Inputs and Chain-of-Thought Reasoning","publication_year":2026,"publication_date":"2026-04-22","ids":{"openalex":"https://openalex.org/W7155563110","doi":"https://doi.org/10.48550/arxiv.2604.21032"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.21032","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.21032","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.21032","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084688455","display_name":"Dahun Kim","orcid":"https://orcid.org/0000-0003-1776-6195"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Dahun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114633766","display_name":"Ganesh Mallya","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mallya, Ganesh Satish","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5066709641","display_name":"Anelia Angelova","orcid":"https://orcid.org/0000-0003-1822-7943"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Angelova, Anelia","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/T10689","display_name":"Remote-Sensing Image Classification","score":0.8640999794006348,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.8640999794006348,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.04399999976158142,"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/T10111","display_name":"Remote Sensing in Agriculture","score":0.01510000042617321,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7430999875068665},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5735999941825867},{"id":"https://openalex.org/keywords/geospatial-analysis","display_name":"Geospatial analysis","score":0.5550000071525574},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5303999781608582},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.43050000071525574},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.4099000096321106},{"id":"https://openalex.org/keywords/data-space","display_name":"Data space","score":0.38940000534057617},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.32899999618530273}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7430999875068665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6938999891281128},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5999000072479248},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5958999991416931},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5735999941825867},{"id":"https://openalex.org/C9770341","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Geospatial analysis","level":2,"score":0.5550000071525574},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5303999781608582},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.43050000071525574},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.4099000096321106},{"id":"https://openalex.org/C2988382989","wikidata":"https://www.wikidata.org/wiki/Q370685","display_name":"Data space","level":2,"score":0.38940000534057617},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34299999475479126},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3174000084400177},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.26330000162124634},{"id":"https://openalex.org/C2779714256","wikidata":"https://www.wikidata.org/wiki/Q25305062","display_name":"Multiple Models","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.21032","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.21032","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.21032","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.21032","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":"Preprint"},"sustainable_development_goals":[{"score":0.513797402381897,"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multi-spectral":[0],"imagery":[1],"is":[2,47],"a":[3,59],"valuable":[4],"input":[5],"signal":[6],"for":[7,130,138],"Remote":[8,122],"Sensing":[9,123],"applications,":[10],"such":[11],"as":[12,104],"land-use":[13],"and":[14,17,49,97,101,114],"land-cover":[15],"classification":[16],"environmental":[18],"monitoring.":[19],"However,":[20],"generalist":[21,136],"Large":[22],"Multi-modal":[23],"Models":[24],"(LMMs)":[25],"are":[26],"typically":[27],"trained":[28],"on":[29,120],"RGB":[30,37],"images,":[31],"limiting":[32],"their":[33],"applicability":[34],"to":[35,94,133],"the":[36,40,68,83,87,110,128],"domain.":[38],"At":[39],"same":[41],"time,":[42],"training":[43],"multi-spectral":[44,65],"multi-modal":[45],"models":[46,137],"expensive":[48],"produces":[50],"uniquely":[51],"specialized":[52,139,149],"models.":[53],"To":[54],"address":[55],"this,":[56],"we":[57],"propose":[58],"novel":[60],"training-free":[61],"approach":[62,81],"that":[63,95],"introduces":[64],"data":[66],"within":[67],"inference":[69],"pipeline":[70],"of":[71,86],"standard":[72],"RGB-only":[73],"LMMs,":[74],"allowing":[75],"large":[76],"gains":[77,119],"in":[78,148],"performance.":[79],"Our":[80],"leverages":[82],"LMMs'":[84],"understanding":[85],"visual":[88],"space":[89,96],"by":[90],"adapting":[91],"non-RGB":[92],"inputs":[93],"injecting":[98],"domain-specific":[99],"information":[100],"Chain-of-Thought":[102],"reasoning":[103,145],"instructions.":[105],"We":[106],"demonstrate":[107],"this":[108],"with":[109],"Gemini":[111],"2.5":[112],"model":[113],"observe":[115],"strong":[116],"Zero-Shot":[117],"performance":[118],"popular":[121],"benchmarks.":[124],"These":[125],"results":[126],"highlight":[127],"potential":[129],"geospatial":[131],"professionals":[132],"leverage":[134],"powerful":[135],"sensor":[140],"inputs,":[141],"benefiting":[142],"from":[143],"rich":[144],"capabilities":[146],"grounded":[147],"data.":[150]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-25T00:00:00"}