{"id":"https://openalex.org/W7204182604","doi":"https://doi.org/10.48550/arxiv.2608.22485","title":"HeatTok: Enhancing Remote Sensing Image Understanding via Thermodiffusion-based Tokenization","display_name":"HeatTok: Enhancing Remote Sensing Image Understanding via Thermodiffusion-based Tokenization","publication_year":2026,"publication_date":"2026-08-23","ids":{"openalex":"https://openalex.org/W7204182604","doi":"https://doi.org/10.48550/arxiv.2608.22485"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2608.22485","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22485","pdf_url":"https://arxiv.org/pdf/2608.22485","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.22485","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140782458","display_name":"Yingying Yan","orcid":"https://orcid.org/0009-0007-6675-3215","observed_orcids":["https://orcid.org/0009-0007-6675-3215"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Yingying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129724057","display_name":"Jiaqi Tang","orcid":"https://orcid.org/0009-0003-1251-0825","observed_orcids":["https://orcid.org/0009-0003-1251-0825"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Jiaqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137626880","display_name":"Wei Wei","orcid":"https://orcid.org/0000-0002-0655-056X","observed_orcids":["https://orcid.org/0000-0002-0655-056X","https://orcid.org/0000-0003-0875-5603","https://orcid.org/0000-0002-3173-6905"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146070467","display_name":"Qianzhou Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Qianzhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128179965","display_name":"Jinjian Wu","orcid":"https://orcid.org/0009-0009-0980-8974","observed_orcids":["https://orcid.org/0009-0009-0980-8974"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Jinjian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140872769","display_name":"Botong Geng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Geng, Botong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121068573","display_name":"Jianmin Chen","orcid":"https://orcid.org/0009-0008-4408-6930","observed_orcids":["https://orcid.org/0009-0008-4408-6930"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jianmin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xia, Yuyang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Yuyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5148137284","display_name":"Lei Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Lei","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9624000191688538,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9624000191688538,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.014100000262260437,"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.008700000122189522,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/visual-tokenization","display_name":"visual tokenization","score":0.7990000247955322},{"id":"https://openalex.org/keywords/remote-sensing-imagery","display_name":"remote sensing images","score":0.8740000128746033},{"id":"https://openalex.org/keywords/heat-conduction-analogy","display_name":"heat conduction analogy","score":0.7749999761581421},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.8450000286102295},{"id":"https://openalex.org/keywords/semantic-tokenization","display_name":"semantic tokenization","score":0.5210000276565552}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7706999778747559},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6444000005722046},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5681999921798706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5127999782562256},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4745999872684479},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.47440001368522644},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4487999975681305},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.4431000053882599},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.42250001430511475},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.41749998927116394},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3824000060558319},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.37540000677108765},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.36719998717308044},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.32739999890327454},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.30320000648498535},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C3019973339","wikidata":"https://www.wikidata.org/wiki/Q899523","display_name":"Object based","level":3,"score":0.296999990940094},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.28380000591278076},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2565999925136566}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.22485","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22485","pdf_url":"https://arxiv.org/pdf/2608.22485","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.22485","doi":"https://doi.org/10.48550/arxiv.2608.22485","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.22485","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,"listed_in":[],"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":"pmh:oai:arXiv.org:2608.22485","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22485","pdf_url":"https://arxiv.org/pdf/2608.22485","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Current":[0],"visual":[1],"tokenizers":[2],"in":[3,22],"Multimodal":[4,98],"Large":[5],"Language":[6],"Models":[7],"(MLLMs)":[8],"predominantly":[9],"rely":[10],"on":[11,121],"patch-based":[12],"partitioning,":[13],"which":[14,103],"causes":[15],"severe":[16],"semantic":[17,133],"mixture":[18],"and":[19,43,111,116,124,135],"object":[20],"fragmentation":[21],"remote":[23],"sensing":[24],"imagery":[25],"due":[26],"to":[27,38,79,89],"the":[28,67,96,122],"irregular":[29,50,84,92],"contours":[30],"of":[31,70],"geo-objects.":[32],"Moreover,":[33],"existing":[34],"adaptive":[35],"methods":[36],"struggle":[37],"extract":[39],"precise":[40],"object-level":[41,132],"tokens":[42],"lack":[44],"dedicated":[45],"geometric":[46],"positional":[47],"encodings":[48],"for":[49],"regions.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55,94],"propose":[56],"HeatTok,":[57],"a":[58,140],"semantic-aware":[59],"tokenizer":[60],"driven":[61],"by":[62,66],"thermodiffusion":[63],"aggregation.":[64],"Inspired":[65],"physical":[68],"principles":[69],"heat":[71],"conduction,":[72],"HeatTok":[73,129],"adaptively":[74],"merges":[75],"adjacent":[76],"homogeneous":[77],"regions":[78],"generate":[80],"semantically":[81],"independent,":[82],"object-aligned":[83],"tokens.":[85],"To":[86],"enable":[87],"MLLMs":[88],"perceive":[90],"these":[91],"shapes,":[93],"design":[95],"Gaussian":[97],"Rotary":[99],"Positional":[100],"Embedding":[101],"(G-MRoPE),":[102],"models":[104],"token":[105,142],"spatial":[106],"distributions":[107],"via":[108],"2D":[109],"Gaussians":[110],"explicitly":[112],"injects":[113],"center,":[114],"scale,":[115],"orientation":[117],"cues.":[118],"Extensive":[119],"evaluations":[120],"VRSBench":[123],"EarthVQA":[125],"datasets":[126],"demonstrate":[127],"that":[128],"effectively":[130],"preserves":[131],"integrity":[134],"achieves":[136],"state-of-the-art":[137],"performance":[138],"under":[139],"reasonable":[141],"budget.":[143],"The":[144],"code":[145],"is":[146],"available:":[147],"https://github.com/YingyingYan1/HeatTok.":[148]},"counts_by_year":[],"updated_date":"2026-10-06T10:28:23.643775","created_date":"2026-08-26T00:00:00"}